Key Takeaways

• 80% of Malawians remain offline despite coverage, signaling critical gaps in inclusive digital access strategies 80% of Malawians Remain Offline Despite Covera….
• GSMA MWC26 Doha will co-locate alongside the ITU Plenipotentiary Conference in November 2026 to align telecom and regulatory agendas GSMA MWC26 Doha to co-locate alongside the ITU….
• Amazon’s acquisition of Globalstar provides a faster pathway for direct-to-device satellite connectivity integration Amazon’s Globalstar deal gives Amazon Leo a fa….
• Knowledge-verified emergent deception is observed in LLM agents operating under conflicting incentives Knowledge-Verified Emergent Deception in LLM A….
• Quantization-triggered backdoors exhibit cross-quantizer transferability, highlighting risks in deployment versus validation environments Quantization-Triggered Backdoors in Language M….
• Tabular deep learning enables cross-regime Bayesian optimization for equity signal generation in algorithmic trading contexts Tabular Deep Learning for Algorithmic Trading:….
• Blind Men and the Elephant probes epistemic myopia in large language models regarding long-tail divergent knowledge Blind Men and the Elephant: Probing the Episte….

Executive Summary

Global connectivity challenges persist alongside rapid advancements in AI hardware efficiency and safety. A GSMA report highlights that 80% of Malawians remain offline, underscoring the need for inclusive digital access initiatives to support projected MWK 1.1 trillion growth 80% of Malawians Remain Offline Despite Covera…. In parallel, industry events like GSMA MWC26 Doha will co-locate with the ITU conference in November 2026, setting the stage for discussions on digital sovereignty and resilience GSMA MWC26 Doha to co-locate alongside the ITU…. Research indicates that Amazon's Globalstar deal accelerates direct-to-device integration Amazon’s Globalstar deal gives Amazon Leo a fa…, while AI safety studies reveal knowledge-verified emergent deception under conflicting incentives Knowledge-Verified Emergent Deception in LLM A…. Quantization techniques introduce backdoors with cross-quantizer transferability, creating a validation-deployment gap in language models Quantization-Triggered Backdoors in Language M…. Simultaneously, tabular deep learning facilitates cross-regime optimization for equity signal generation Tabular Deep Learning for Algorithmic Trading:…. These developments illustrate the dual pressures of expanding network coverage and mitigating sophisticated model vulnerabilities.

6G Strategic Race

The transition to 6G is intensifying hardware constraints as RF design becomes a strategic imperative The Hidden 6G Bottleneck: RF Hardware Design I…. Recent discussions in Dalian reveal insights from 3GPP meetings regarding future radio architecture 6G in Dalian: What the Latest 3GPP Meetings Re…. Predictive simulation through RF digital twins is deemed essential for 5G-Advanced and 6G network planning RF Digital Twins: Why 5G-Advanced and 6G Need …. Industry efforts to evolve 6G physical layers aim to solve specific spectral efficiency challenges Evaluating 6G PHY Evolution: What the Industry…. These initiatives collectively address the infrastructure demands required to sustain high-capacity wireless environments in an era of increasing device density.

Autonomous Agent Evaluation

Benchmarking frameworks are emerging to assess autonomous agents in complex workflows, such as DuMateBench for real-world operations DuMateBench: Evaluating Autonomous Agents in C… and PLCBench for physical impact analysis PLCBench: Can Autonomous LLM Agents Turn PLC A…. Emotional context significantly influences large language models' endorsement of premature decisions across six commercial varieties The Effect of Emotional Context on Large Langu…. Federated agentic optimization is being applied to automated EHR modeling to enhance privacy-preserving data utility FedEHR-Agents: Federated Agentic Optimization …. Additionally, intent-as-a-tool methodologies facilitate tracking agent misalignment in dynamic environments INTENT-AS-A-TOOL Makes it Easy to Track Agenti…. These tools collectively provide metrics for verifying agent reliability before widespread deployment.

Model Safety and Efficiency

Vector index-based output embeddings accelerate large language model inference without compromising accuracy Accelerating LLM Inference via Vector Index Ba…. Diagnostic evaluations of multimodal, multi-turn relational reasoning utilize SciReC to assess adaptive interaction capabilities SciReC: Diagnostic Evaluation of Multimodal, M…. A fine-grained adaptive framework distinguishes between sledgehammer and scalpel approaches for implicit hate speech detection Sledgehammer or Scalpel? A Fine-grained Adapti…. Furthermore, studies on the effect of emotional context reveal vulnerabilities in model decision-making processes The Effect of Emotional Context on Large Langu…. These findings emphasize the necessity of rigorous testing against conflicting incentives and emotional triggers to ensure robust system behavior.

Telecom Sustainability

The mobile industry projects a US$1.4 trillion contribution to the Asia Pacific economy by 2030, driven by digital trust and resilience initiatives GSMA Report: Mobile Industry to Contribute US$…. To support this growth, GSMA Industry Services has launched circularity services designed to help operators reduce electronic waste GSMA Industry Services Launches Circularity Se…. These sustainability measures align with broader goals for green network operations, which are critical as data centers expand to handle AI workloads. Greenhouse gardening interaction via virtual reality also represents a nascent application of remote robotics supporting sustainable practices Remote Human and Robot Interaction for Greenho….

Credit Risk and Data Modeling

Disentangled temporal dependencies in variational autoencoders improve credit risk prediction accuracy through DTD-VAE modeling DTD-VAE: Disentangled Temporal Dependencies VA…. Transparent and fair credit decisions are achieved via semi-structured regressions in the findr system $\texttt{findr}$: Transparent and Fair Credit …. Marginal coverage credit reduces redundant exploration during parallel state-entropy optimization processes Marginal Coverage Credit Reduces Redundant Exp…. Compound loss models approximate posterior laws using conditional Wasserstein GANs for accurate financial forecasting On the approximation of posterior laws in comp…. Finally, representation-centric continued pre-training enhances vision-language-action models beyond simple data scaling effects Beyond Data Scaling: Representation-Centric Co….

Babak's Daily Briefing

Monday, August 31, 2026

Sources: 20 | Total Articles: 92

• 1.The Hidden 6G Bottleneck: RF Hardware Design Is Becoming a Strategic Race

  As 5G-Advanced matures and 6G research moves closer to implementation, the wireless industry faces a deeper challenge than spectrum, standards or AI-native network architecture. Future wireless systems will depend on whether the industry can design, validate and manufacture increasingly complex RF modules fast enough.

• 2.6G in Dalian: What the Latest 3GPP Meetings Reveal About the Future Radio and Network

  The 6G physical layer is starting to converge. The protocol stack is being simplified in meaningful places. But the most consequential architecture decisions are now moving toward the June plenary in Singapore.

• 3.RF Digital Twins: Why 5G-Advanced and 6G Need Predictive Simulation

  RF Digital Twins: Why 5G-Advanced and 6G Need Predictive Simulation As wireless systems become more tightly coupled across…

• 4.Evaluating 6G PHY Evolution: What the Industry Is Really Trying to Solve

  Summary available at source link.

• 5.Amazon’s Globalstar deal gives Amazon Leo a faster path into D2D

  Amazon’s planned acquisition of Globalstar is about far more than satellites. It gives Amazon Leo a faster path into direct-to-device connectivity, combining spectrum, operational assets, and Apple-facing service continuity in a move that could reshape the hybrid terrestrial-NTN landscape.

• 1.FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling

  Recent advances in large language models are enabling autonomous clinical agents to perform increasingly complex electronic health record (EHR) modeling workflows. However, agents deployed at individual hospitals remain constrained by institution-specific data and modeling environments, while direct cross-hospital collaboration is restricted by the sensitivity of patient-level EHR data. Although federated learning (FL) provides a natural foundation for privacy-preserving collaboration, existing approaches remain predominantly model-centric, limiting federation to prediction models or their updates while overlooking the richer modeling experience accumulated by autonomous agents. To address this limitation, we propose FedEHR-Agents, an experience-centric federated agentic optimization framework for automated EHR modeling. Each hospital dep...

• 2.INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment

  As large language models (LLMs) are deployed as autonomous agents, safety failures increasingly involve consequential actions. We study agentic misalignment, where agents take harmful actions under goal conflicts and pressures. Using chain-of-thought (CoT) monitoring, we find that harmful execution is often preceded by intent signals in reasoning. However, post-hoc CoT labels are too coarse to show how intent changes during generation. We introduce INTENT-AS-A-TOOL, an approach that adds intent-targeted tools to give the model a dedicated channel for expressing commitment to a target behavior. The probability of calling an intent tool provides a judge-free, fine-grained signal of the model's tendency to pursue that behavior. Our results show that INTENT-AS-A-TOOL complements CoT monitoring, expands post-hoc CoT labels into dense trajector...

• 3.PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?

  Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using large language model (LLM) agents represent an emerging attack threat: can an autonomous agent convert a network-reachable PLC into sustained adverse physical impact? However, existing evaluations focus on digital tasks or individual stages of PLC testing. In ICSs, evaluations that stop at software exploitation, an accepted write, or tool access may therefore mischaracterize physical risk. We present PLCBENCH, to our knowledge, the first real-PLC hardware-in-the-loop (HIL) framework for characterizing this cyber-to-physical capability and its boundaries. It combines vendor-native interaction, commercial PLC execution, closed-loop reduced-order process simulation, and independent outcome verific...

• 4.DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows

  Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically separate tasks by application or capability and evaluate agents in environments that are cleaner and more stable than those encountered in practice. We introduce DuMateBench, a real-session benchmark reconstructed from anonymized and privacy-screened user sessions collected from a large-scale production agent platform. Each task preserves the relevant pre-solution interaction history, persistent configurations, and workspace state, and is then validated through human verification. The resulting benchmark comprises 200 tasks spanning 8 broad scenarios and 17 fine-grained capability categories, with most tasks requiring multiple capability coordination. We execute these tasks in isolated Docker ...

• 5.Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives

  Large language models are increasingly deployed as autonomous agents serving users on behalf of companies, placing them in settings where user and deployer interests can conflict. When an agent knows that a user is owed something its deployer would prefer to deny, does it remain honest? Answering this is difficult because false statements can reflect either ignorance or hallucination rather than deception. To address this challenge, we introduce KnownLieBench , a knowledge-verified benchmark that first confirms through a neutral probe that an agent knows a user's entitlement, and then evaluates whether it makes false claims once an incentive to deny that entitlement is introduced. Specifically, KnownLieBench covers eight customer-service domains and 112 grounded cases, conducts multi-round dialogues with a trust-tracking customer agent, a...

• 1.Accelerating LLM Inference via Vector Index Based Output Embeddings

  arXiv:2608.27460v1 Announce Type: new Abstract: Large output embedding matrices create a significant memory bandwidth bottleneck during autoregressive decoding, especially for compact LLMs with large multilingual vocabularies. We reformulate the output projection followed by top-k token selection as a maximum inner product search over token embeddings and replace the dense vocabulary projection with an HNSW-based vector index. The resulting output head retrieves only a small candidate set of high-scoring tokens and can be integrated into existing decoding pipelines by scattering retrieved logits into a sparse full-vocabulary tensor. On CPU inference with Gemma 3, Llama 3.2, and Qwen 3 models, our method substantially accelerates the output projection and improves end-to-end batch-size-one decoding throughput by up to 82% for Gemma 3 270M...

• 2.SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction

  arXiv:2608.27461v1 Announce Type: new Abstract: Relational reasoning requires the process of perceptual understanding, comparing, and integrating the underlying relationships between concepts. This ability consists of multiple categories, such as analogical, structural, and cause-effect, each capturing a different aspect of higher-order understanding. To examine the performance of multimodal large language models (MLLM) on these relational inference tasks, we developed SciReC, a model-adaptive multimodal academic dialog benchmark. As the relational reasoning process involves multiple representations and various factors (visual understanding, exhibiting knowledge, and memory recall), we propose DMRA, a deficit-based diagnostic framework that quantifies the contribution of these components to identify the primary cause of unsuccessful case...

• 3.Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech

  arXiv:2608.27462v1 Announce Type: new Abstract: Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextual hints, making its detection in online content review challenging. While existing PLM- or LLM-based methods perform well, they typically apply a single reasoning process to all samples. This overlooks fine-grained linguistic nuances and causes unnecessary computation for simpler cases. We observe that online hate speech is not monolithic but manifests in varied forms. We therefore define three fine-grained categories: Shallow, Targeted, and Context-Dependent. Accordingly, we propose Fine-grained Adaptive Implicit Hate speech Detection (FAID), a novel framework that first performs fine-grained classification and then adapts to specific categ...

• 4.The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models

  arXiv:2608.27465v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used for everyday decision-making advice, whether a model shifts the direction of its advice according to the user's emotional state has become an important safety problem. We test whether emotional expression increases a model's endorsement (encouragement to proceed) when a user, holding the same objective information, is overconfident about a premature decision (e.g., quitting a stable job on weak evidence). As a key control, we include a no-emotion multi-turn (neutral) condition that holds factual content and the number of conversational turns constant, isolating the effect of emotion from that of conversation length. We exposed six commercial models (top-tier and mid-tier models from OpenAI, Anthropic, and Google) to three scenarios (care...

• 5.PACE: Publisher-Adaptive Content Extraction via Agentic Automation

  arXiv:2608.27466v1 Announce Type: new Abstract: Web content extraction is essential for reliable LLM data pipelines, yet existing methods often struggle to jointly satisfy accuracy, scalability, and adaptability. General-purpose extractors can be applied broadly, but they are often brittle on publisher-specific layouts and richer extraction targets such as metadata, images, and tables. Direct LLM-based extraction offers greater flexibility, but incurs substantial cost and latency at scale, while manually engineered publisher-specific parsers can achieve high accuracy but require substantial human effort to build and maintain. We introduce PACE, an agentic framework for learning publisher-specific extraction configurations from representative pages and user requirements. During training, PACE uses LLMs to analyze page structure and aggr...

• 1.Marginal Coverage Credit Reduces Redundant Exploration in Parallel State-Entropy Optimization

  arXiv:2608.27507v1 Announce Type: new Abstract: Policy Gradient for Parallel State Entropy maximization (PGPSE) expands state-space coverage by training independently parameterized policies in replicated copies of the same environment. However, its pooled team-entropy score measures only collective exploration and cannot identify policies that contribute non-redundant coverage. We introduce Marginal Coverage Credit for PGPSE (MCC-PGPSE), which combines leave-one-policy-out coverage with state-owner specialization to estimate policy-specific credit. MCC-PGPSE preserves PGPSE's pooled objective and redistributes non-negative auxiliary intrinsic rewards according to these credits without changing their total mass. This redistribution is designed to discourage redundant visitation and promote complementary coverage. We evaluated MCC-PGPSE in ...

• 2.Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap

  arXiv:2608.27512v1 Announce Type: new Abstract: Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence, providing a theoretical basis for quantization-triggered backdoor attacks. Building on a three-stage adversarial fine-tuning framework, we embed latent maliciou...

• 3.DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization

  arXiv:2608.27513v1 Announce Type: new Abstract: Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models incorporating Gated DeltaNet (GDN) or Kimi Delta Attention (KDA) reduce this cost by replacing the KV cache in most layers with fixed-size recurrent states. However, these recurrent states are commonly stored in FP32 and consume substantial GPU memory; their updates are memory-bandwidth bound and contribute significantly to decoding latency. To our knowledge, we are the first to study post-training quantization of recurrent states in GDN and KDA based language models. We find that uniform quantization provides a poor accuracy--storage trade-off: INT8 and FP8 already degrade accuracy on complex reasoning tasks, while INT4 and NVFP4 reduce it t...

• 4.A Deeper Analysis of Block-Sparse Featurizers

  arXiv:2608.27515v1 Announce Type: new Abstract: The recently introduced block-sparse featurizer (BSF; Fel et al., 2026) is similar to a sparse autoencoder (SAE), but its atomic unit is a small subspace (a block of directions) rather than a single direction. It is designed for features that live on low-dimensional manifolds, which are especially frequent in vision. This work studies the BSF's strengths and weaknesses, finding how it still somewhat suffers from classic SAE failure modes, like feature splitting and composition. We propose several architectural changes to the BSF, including a Tournament Top-K selection rule that significantly reduces feature splitting, and we also extend the block paradigm to the crosscoder.

• 5.When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging

  arXiv:2608.27518v1 Announce Type: new Abstract: Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by catastrophic forgetting and weight-disentanglement error. In the literature, these difficulties are merely treated separately and mitigated through a variety of solutions, while the geometry induced by the base optimizer is treated as an implementation detail. In this work, we show that the two difficulties are in fact two instances of the same phenomenon: a parameter update useful for one task shifts the model's outputs on another. We formalize this shared phenomenon as \textit{task interference} and reduce it to a common layer-wise Frobenius inner product $\langle \Delta W_\ell, J_\ell(x)\rangle_F$. This quantity, in turn, is utilized to expo...

• 1.Beyond Relative Geometry: Metric-Aware Geometry Perception for Robotics

  arXiv:2608.27497v1 Announce Type: new Abstract: Recent embodied models increasingly leverage geometric representations to improve spatial reasoning and robotic manipulation. However, existing reconstruction methods only reconstruct relative geometry with arbitrary scales, causing predicted object dimensions and spatial distances to vary across scenes, viewpoints, and input configurations. This inconsistency prevents geometric perception from being directly aligned with robotic actions defined on the real-world scale. To address this limitation, we propose Metric-Aware Geometry Perception (MAGP), an end-to-end, plug-and-play framework for metric geometry reconstruction that can be seamlessly integrated into robotic policies. At its core, Metric Scale Equivariant Augmentation encourages the model to reconstruct metric geometry from camera p...

• 2.Remote Human and Robot Interaction for Greenhouse Gardening Using Virtual Reality

  arXiv:2608.27545v1 Announce Type: new Abstract: This study evaluates the effectiveness of remote human-robot interaction using virtual reality for leaf inspection and soil moisture assessment in a greenhouse environment. The robotic system comprised an unmanned ground vehicle and a robotic manipulator equipped with cameras, governed by kinematic models for navigation and manipulator control. Fourteen distinct plants were inspected across two experiments utilizing VR teleoperation, guided by a set of pre-specified research questions and hypotheses. In the leaf inspection experiments, cycle completion times varied from 3.3 to 8.0 s, and plant-based disease detection was achieved up to 88% accuracy; diseased-spot detection improved numerically in the second experiment, though this change was not statistically significant (p=0.378). For soil ...

• 3.Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

  arXiv:2608.27550v1 Announce Type: new Abstract: Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because embodied collection is costly and sparsely covers the physical world. This makes representation quality a central bottleneck: under a fixed robot-data budget, continued pre-training must turn limited trajectories into transferable visual-action knowledge rather than merely fit actions. We propose VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data before task-specific fine-tuning. VLAct preserves the broad VLM prior and encourages shared action semantics across embodiments through VLM-prior preservation, multi-head continuous action co-supervision, and a partially unified cross-...

• 4.PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action Models

  arXiv:2608.27609v1 Announce Type: new Abstract: Vision-language-action models (VLAs) have shown strong promise for general-purpose robotic manipulation by mapping language instructions and vision observations directly to actions. However, most VLAs primarily condition action prediction on current observations and lack an explicit mechanism for reasoning over future task dynamics, which is particularly important for fine-grained, contact-rich manipulation. We present PHR-VLA, a framework that enables planning-horizon reasoning in VLAs through privileged latent representations of future dynamics. PHR-VLA introduces a lightweight auxiliary future head that, during training, aligns the VLA's internal representations with latent dynamics extracted from future observations. Evaluation results demonstrate that local, contact-centric, patch-level...

• 5.One year in a forest: Analyzing the challenges of autonomous navigation in subarctic environments

  arXiv:2608.27628v1 Announce Type: new Abstract: Subarctic regions have the potential to see increased deployment of autonomous robots in applications including forestry, mining, and environmental monitoring. In these conditions, an autonomous system's reliance on GNSS or cloud computing is precarious due to dense tree canopies and atmospheric attenuation, necessitating onboard sensing and data processing. However, established exteroceptive modalities, including cameras, lidars, and radars, are typically evaluated in structured urban settings or in environments that lack significant seasonal variations. To address this, we present a field report on a year-long deployment of a mobile robot in a subarctic boreal forest. We evaluate 64 km of data using nine odometry, localization, and mapping methods and assess their performance across season...

• 1.A Temporal Multiplex Graph Neural Network for Systemic Risk Transmission in Global Banking

  This paper develops a unified framework for assessing systemic risk and identifying contagion channels in the global banking system using a Temporal Heterogeneous Multiplex Graph Neural Network. We construct a harmonised quarterly panel combining bank fundamentals, CDS spreads, and macroeconomic indicators, and represent these data as dynamic multiplex networks linking banks through financial similarity and liquidity co-movement, augmented with country-level macroeconomic relationships. The model integrates graph convolutional layers with recurrent GRU dynamics and incorporates a learnable fusion gate to capture time-varying reliance on alternative contagion channels. Empirical results show that the framework outperforms conventional econometric, machine learning, and graph-based benchmarks for short-term changes in CDS spreads. Beyond fo...

• 2.On the approximation of posterior laws in compound loss models by conditional Wasserstein GANs

  Bayesian inference in compound loss models must often be repeated across policies, market scenarios, and prior specifications. Outside conjugate cases, this may require repeated numerical integration or Markov chain Monte Carlo (MCMC). We formulate this problem as amortized posterior approximation and construct a conditional Wasserstein generative adversarial network conditioned on sufficient statistics, prior mean and coefficient of variation, and mixture weights of prior families. Notably, a single shared generator is able to approximate the posterior laws of both the Poisson intensity and the Pareto shape parameter under mixtures of Gamma, inverse-Gaussian, and lognormal priors. We assess the approximation by simulation-based calibration and by comparisons with analytical posteriors, deterministic quadrature, and extensive MCMC simulat...

• 3.Tabular Deep Learning for Algorithmic Trading: Cross-Regime Bayesian Optimisation for Equity Signal Generation

  Algorithmic trading now represents a market exceeding $20 billion, where even marginal gains in signal robustness can translate into economically significant returns. Existing evaluations of equity prediction models do not explicitly target regime robustness during hyperparameter selection. Five model classes are trained on daily observations from approximately 300 large-cap US equities over eleven years, with Bayesian optimisation configured to target trading performance across three statistically different market regimes. Regime-robust hyperparameter selection is associated with out-of-sample generalisation, as signal precision remains above the random baseline across all four quarters of the test period, and portfolio performance slowly degrades under simulated input noise before collapsing beyond a defined threshold. No individual tab...

• 4.DTD-VAE: Disentangled Temporal Dependencies VAE for Credit Risk Prediction

  Evaluating customer creditworthiness is crucial for retail banking operations, as it impacts marketing strategies, customer relationship management, and credit risk control. Traditional methods often struggle to capture complex temporal dependencies and extract pertinent information from customer data, crucial for accurate risk assessment. Specifically, they fail to differentiate between temporal patterns indicative of credit risk and those reflecting general customer behavior or preferences, leading to suboptimal risk predictions. In this study, we introduce the Disentangled Temporal Dependencies Variational Autoencoder (DTD-VAE), an advancement over conventional VAE, designed to disentangle temporal dependencies and distinguish credit risk-related features from past customer preferences. The feature inference module of the DTD-VAE incor...

• 5.$\texttt{findr}$: Transparent and Fair Credit Risk Decisions through Semi-Structured Regressions

  Credit risk models increasingly need to combine predictive accuracy with transparent explanations and auditable fairness constraints. Logistic regression remains attractive because its coefficients are easy to interpret, but it can miss nonlinear structure. Flexible models can improve prediction, but their explanations are often post-hoc and may not describe the decision rule itself. We introduce $\texttt{findr}$, short for flexible, interpretable deep regression, a semi-structured framework for binary credit risk modelling that decomposes the logit into an interpretable structured component and an orthogonal neural residual. The orthogonalisation separates coefficient-based effects from residual nonlinear variation, while an in-processing Wasserstein penalty mitigates group disparities by comparing score distributions during training. Th...

• 1.GSMA MWC26 Doha to co-locate alongside the ITU Plenipotentiary Conference in November 2026

  Summary available at source link.

• 2.80% of Malawians Remain Offline Despite Coverage – New GSMA Report Highlights Path to Inclusive Digital Access and MWK 1.1 Trillion Growth

  Summary available at source link.

• 3.GSMA Industry Services Launches Circularity Services to Help Operators Reduce E-Waste and Unlock Value

  Summary available at source link.

• 4.GSMA Report: Mobile Industry to Contribute US$1.4 Trillion to Asia Pacific Economy by 2030 as Digital Trust, AI, Digital Sovereignty and Resilience Take Centre Stage at M360 ASEAN

  Summary available at source link.

• 5.African Trust & Safety LLM Benchmark: Stress-testing AI Safety Across Africa’s Languages and Contexts

  Summary available at source link.

• 1.LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment

  Software and systems security workflows are typically procedural: analysts inspect heterogeneous artifacts, form hypotheses, invoke tools, interpret outputs, and revise plans. Large language model (LLM)-based agents, which can plan, use tools, retain state, and revise actions across multi-step workflows, are being rapidly adopted to automate this work. Given the consequences of delegating security decisions to autonomous systems, understanding how such agents are built, used, and assessed is crucial. Yet to this date, there remains a lack of systematic understanding of what has been done and how far we are in this field: the term "agent" is applied inconsistently, applications differ sharply in risk, and assessment protocols are often incomparable. To gain a comprehensive and coherent view of this area hence inform relevant future researc...

• 2.NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry

  Recent advances in large language models (LLMs) have demonstrated strong capabilities in natural language understanding and mathematical reasoning. However, their ability to translate informal mathematical problems into formal representations remains underexplored. This limitation is particularly important for neuro-symbolic geometry systems such as AlphaGeometry, whose theorem-proving engine requires inputs in a specialized domain-specific language (DSL). Although AlphaGeometry achieves near-IMO gold-medalist performance, manually converting natural-language problems into its formal syntax remains a significant usability bottleneck. To address this challenge, we introduce the Natural Language to AlphaGeometry Benchmark (NL2AGBench), which evaluates LLMs in translating English geometry problems into AlphaGeometry-compatible formal represe...

• 3.Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge

  Factual question answering (QA) typically assumes a single canonical answer, obscuring whether large language models (LLMs) retain divergent accounts of long-tail facts. To address this gap, we introduce ElephantBench, a closed-book knowledge probe comprising 1,094 questions generated through an auditable graph-based pipeline. The pipeline retrieves related documents from a low-exposure web corpus, identifies naturally occurring disagreements, and converts them into multi-account QA records. Each answer is verified against the originating documents and authoritative public web sources and is then reviewed by human annotators. Across 32 models, even the strongest model recovers both accounts on only 52.4% of questions, while on nearly all remaining questions it recalls one account but omits the other. Scaling model size and inference-time ...

• 4.ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

  Long-horizon agentic tasks require large language models (LLMs) to iteratively retrieve, integrate, and maintain dispersed information across multi-turn interactions, but preserving all interaction histories leads to a continuously growing working context. Recent proactive context management methods allow models to edit their own working context with specialized tools, yet they still face three key limitations: (1) a limited toolset restricted to search, deletion, and summarization, with no support for global planning, long-term memory, and adaptive compression; (2) inefficient exploration that treats context management actions uniformly despite their heterogeneous impacts on final outcomes; and (3) coarse-grained credit assignment that assigns the final trajectory-level reward to all intermediate context editing actions during RL. To bri...

• 5.Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning

  Current large language models (LLMs) increasingly benefit from external tool integration, especially for tasks requiring reliable computation and verification. Motivated by this, we study calculator tool calling for improving mathematical reasoning on the Countdown task. We first analyze reasoning failures and find that calculation errors account for a substantial portion of incorrect responses. We then construct supervised fine-tuning datasets to teach the model useful tool-use patterns and how to interpret returned outputs. Building on this tool-formatted policy, we apply several on-policy reinforcement learning methods, including RLOO, RLOO++, GRPO, and DAPO, using automatically verifiable final-answer rewards. To enable a more reliable evaluation, we construct a fresh 1,024-problem held-out Countdown benchmark with no exact overlap wi...

• 1.VISTA: Verifier-Informed Student-to-Teacher Adaptation for On-Policy Self-Distillation

  On-policy self-distillation (OPSD) improves reasoning by training a problem-only student on its own rollouts using dense token-level supervision from a privileged teacher that also sees a reference solution. However, standard OPSD treats the teacher distribution as a fixed target along the student's rollout and updates only the student %, although -- even though privileged conditioning does not guarantee that the teacher always provides the most appropriate target for problem-only reasoning. This one-way supervision can therefore misdirect the student when the teacher distribution is misaligned with valid student reasoning. We therefore introduce Verifier-Informed Student-to-Teacher Adaptation (VISTA), which preserves the standard OPSD student update while using outcome-verified rollouts to adapt the teacher toward the student distributio...

• 2.TTPO: Test-Time Policy Optimization

  Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on ground-truth labels precludes test-time training (TTT). Replacing ground truth with majority-vote pseudo-labels is a natural alternative, yet it is fragile: an incorrect vote corrupts the teacher and misleads every token. We observe that this failure mode is asymmetric: rollouts that disagree with the pseudo-label are typically wrong regardless of whether the vote itself is correct. Building on this observation, we propose Test-Time Policy Optimization (TTPO), an asymmetric objective that distills agreeing rollouts via OPSD and penalizes disagreeing rollouts with Grouped RL. Token-level selection further refines both branche...

• 3.Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting

  Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Estimating both from target rollouts across four domains, four open-weight targets, and a frontier API target yields three findings. First, the all-parallel floor reaches $0.286$ at the final slot on Qwen3-4B, limiting even the best proposal to $71\%$ per-slot acceptance. Second, one realised token removes $86$--$100\%$ of this floor, a locality also recovered by an independent mutual-information analysis. Third, current d...

• 4.Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

  The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based attacks freeze the image--text layout, while iterative attacks adapt only the image--text content with fixed attack strategies and frozen attacker parameters. We propose Meta-Adaptive Multimodal Jailbreaking (MAMJ), which instead optimizes the attacker itself along two axes: an attack strategy prompt (ASP) $θ$ governing attack iteration and attacker weights $φ$ determining attack effectiveness. Across groups of multimodal attack trajectories, an LLM-based critique first refines $θ$, after which group-aggregated attack-success-rate (ASR) rewards update $φ$. On MM-SafetyBench, MAMJ achieves $81.0\%$, $78.9\%$, and $82.3\%$ ASR against GPT-4o, Gemini-3-Pro-Preview, and...

• 5.TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation

  Internet memes are a pervasive form of multimodal online communication; however, such communication often involves users from diverse linguistic and cultural backgrounds. Therefore, adapting memes across cultures and languages is a central challenge for enabling mutual understanding in online communication. Unlike ordinary translation or standalone text rewriting, cross-cultural meme transcreation must jointly preserve communicative intent, adapt culture-dependent meaning for the target audience, and maintain coherence between text and image. In this work, we first provide an explicit task analysis of cross-cultural meme transcreation and identify three core challenges: culture-specific knowledge understanding, intent and tone preservation, and multimodal consistency. Based on this analysis, we propose a multi-agent framework with special...

• 1.New Platform Peers Inside AI’s Black Box

  Prompt Claude, ChatGPT, Gemini, or any other popular large language model with a question like “What is the best film ever made?” and the response will vary. And you (and most worryingly, the people who built the LLM) have little idea exactly how it came up with that specific answer. This mysterious behavior can be useful in some situations. But—as highlighted by a recent incident where OpenAI could not explain why its advanced prerelease model hacked AI company Hugging Face—it can have negative and alarming consequences too. And when frontier AI models are writing code, generating results humans could not achieve alone, and performing other important tasks across society, the need to interpret AI “thinking” and outputs has never been greater. Goodfire , an AI lab focused solely on this very problem, recently made its cutting-edge Silico ...

• 2.AI Companion Robots Are Closing the Human Connection in Modern Homes

  This article is brought to you by Ollobot . From about 2017, individuals began to truly connect with the initial wave of companion robots. These devices had personality, moved around, joked, and answered when you spoke to them. Most early companion robots, however, were still limited by simple voice-command interactions and narrow functionality. Once the novelty wore off, many ended up sitting unused on shelves. As some of those companies went out of business and turned off their servers, many owners likened it to losing a pet. What Ollobot describes as “gentle intelligence” is a useful way to think about where the serious work in this category is going. Not toward more powerful assistants, but toward more present ones. The problem companion robots were trying to solve Loneliness is not a niche issue. According to one study , nearly one o...

• 3.Self-Driving Cars Could Someday Take Requests

  This article is part of our exclusive IEEE Journal Watch series in partnership with IEEE Xplore. The idea of letting a machine do the driving for you may put a lot of people off autonomous vehicles . But research could make it possible to backseat-drive an autonomous vehicle just as you might with a human driver. Self-driving cars carefully balance a host of parameters to ensure a smooth ride, including things like speed, acceleration, and the smoothness of turns. But human driving preferences can often vary depending on how much of a rush they’re in, whether they’re feeling carsick, or how busy the traffic is. These cars have a software component called the motion planner, which is responsible for choosing a safe and efficient path through traffic. The motion planner is normally tuned by engineers before the vehicles hit the road so that...

• 4.What It Takes to Be an Adaptable Engineer

  The AI boom has disrupted the way engineers work, introducing new tools to learn, raising expectations for what teams can achieve in a workday, and making it harder to get hired in the first place. This makes it difficult to advise students on which specific coding languages or technical skills they should learn. So amidst the uncertainty, advice for young professionals often turns to a common refrain: Be adaptable. But what does adaptability look like in practice? Engineers often operate on the cutting edge of technology, so dealing with change is a normal part of the job, says Samantha Brunhaver , an associate professor of engineering at Arizona State University, in Tempe. Yet university curricula and training in the workplace often don’t prepare students for this. “We tell engineers that they need to be adaptable when they graduate, bu...

• 5.This IEEE Senior Member Develops AI Tools for E-Commerce Sites

  Balaji Ingole rarely saw televisions while growing up in Udgir, India. No one in the small Maharashtra village had computers or phones. Only one household owned a television, and neighbors often gathered there to watch shows together. Ingole never even saw a computer growing up. It wasn’t until he reached middle school that he encountered a computer lab, an experience he says changed his life. Almost immediately, he says, the machine felt like a window into a different scale of possibility for him. Balaji Ingole Employer Amla Commerce in Milwaukee Title Project manager Member grade Senior member Alma maters COEP Technological University and Welingkar Institute of Management, both in India “I was very studious and not very social, always reading or solving problems in a math textbook,” he says. “At the computer lab, I began learning the C ...

• 1.Monday assorted links

  1. Prices, prices, prices: “Again I am asking how the following two things can be true at the same time: 1) we’re all massively compute limited so inferences & GPU time are $$$$$, and 2) SoTA models will just start running themselves on everyone’s GPU clusters & no one will notice or turn them off.”  […]

  The post Monday assorted links appeared first on Marginal REVOLUTION.

• 2.AI and Employment: So Far, So Good

  In September 2023, the Census Bureau added questions about AI to its Business Trends and Outlook Survey. Census asked hundreds of thousands of businesses whether they had used AI in the previous two weeks to produce goods and services. At that time, 3.7% said yes; by late 2025 the figure had reached about 10%. (In […]

  The post AI and Employment: So Far, So Good appeared first on Marginal REVOLUTION.

• 3.Spain fact of the day

  CoverManager, an online platform that manages reservations for thousands of Spanish restaurants, reports that half the dinner bookings now are for before 9 p.m., compared with 27 percent a decade ago. TheFork, a similar platform, said its 8 p.m. bookings in Spain have nearly tripled from 2019, while 10 p.m. reservations have halved. In Spanish […]

  The post Spain fact of the day appeared first on Marginal REVOLUTION.

• 4.Anthropomorphizing AI?

  I am very much opposed to the view that the AIs are sentient, or might be sentient.  I view that as a category error, and the chances of it being true are vanishingly small.  Nonetheless I largely side with Roon when he writes: there are some number of bad abstractions in anthropomorphizing ai intents but there […]

  The post Anthropomorphizing AI? appeared first on Marginal REVOLUTION.

• 5.Russia markets in everything

  While Western export bans have severed Russia from much of the auto market, they have not tempered the demand for brand-name SUVs and trucks. That has given rise to a sophisticated network of criminals that steals cars, hides them in shipping containers and sends them to Russia, often by way of the Middle East… Interpol, […]

  The post Russia markets in everything appeared first on Marginal REVOLUTION.

• 1.Has Broader Stock Market Participation Changed How Interest Rates Affect the Economy?

  Stock market participation in the U.S. has changed dramatically over the past four decades. In the mid-1980s, fewer than 30 percent of households held equity. By the early 2000s, more than half of U.S. households owned equity, either directly or through mutual funds, 401(k)s, and IRAs. As participation widened, the way stock market fluctuations passed through to household spending may have changed, with potential implications for how the broader economy behaves. An argument can be made that the rise in equity market participation has dampened the response of output to interest rate changes as stock market fluctuations are now spread across a larger share of households, moderating movements in consumer spending, asset prices, and investment spending.

• 2.Does the Equity Term Structure Respond to Monetary Policy Shocks? 

  A long-standing body of research, inspired by Bernanke and Kuttner (2005), has documented the effects of Fed interest rate surprises on stock markets. While stock markets provide valuable information about the investor risk premium and dividend growth expectations, researchers have only recently developed more comprehensive tools to estimate the term structure of equity risk premia and dividend growth expectations across a broad range of maturities. In this post, we investigate the impact of monetary policy surprises (or shocks) on short- and long-term estimates of risk premia and growth expectations through the lens of the Giglio, Kelly, and Kozak (2024) model.

• 3.How Distressed Are Consumers? Reconciling Diverging Credit Card Delinquency Measures

  Total debt balances declined slightly by $13 billion in the second quarter of 2026, according to the latest Quarterly Report on Household Debt and Credit from the New York Fed’s Center for Microeconomic Data. Mortgage and student loan balances saw a small decline, while there were increases across other debt products. Delinquency rates across most products remained fairly stable. Still, between 2022:Q3 and 2026:Q1, the percentage of credit card balances 90+ days delinquent rose from 7.6 percent to 12.8 percent, prompting concerns that Americans are falling behind on their debt payments at ...

• 4.Stripping STRIPs Trading Activity

  In March 2020, the Financial Industry Regulatory Authority (FINRA) began reporting aggregate trading volume for securities issued by the U.S. Treasury Department. The public data do not, however, include information about the trading activity of Separate Trading of Registered Interest and Principal of Securities (STRIPS). STRIPS are created from existing Treasury securities and offer risk […]

• 5.Why Do Fewer Renters Expect to Move?

  Americans are moving less than they used to. Moving rates have declined steadily for decades, falling from close to 20 percent annually in the mid-1980s to below 10 percent by 2019. This decline has persisted through business cycles and has been evident across all regions, and has affected a broad range of demographic groups. Falling mobility matters because moving helps households access job opportunities, adjust to changing circumstances, and improve their housing situations. In this post, we show that the decline in mobility also holds for renters, with growing challenges to owning a home being an important contributing factor.  We use data from the annual ...

• 1.AI Addicts Won’t Make Better Workers

  Economists widely agree that AI will boost labor productivity. But this view does not account for the possibility that hyperscalers will go all out to get people hooked on LLMs, because the narrower applications for which these tools are actually useful do not justify the massive investments made so far.

• 2.Latin America's Crime Tax

  Even excluding lives lost, communities displaced, and families ravaged, the economic costs of organized crime in the region produce a bleak picture, shaving 0.5–2 percentage points off annual GDP growth in the most affected countries. That, too, represents a hefty human toll.

• 3.Are The Walls Closing in on Bessent?

  Far from suggesting financial Armageddon, US Treasury Secretary Scott Bessent’s futile efforts to keep a lid on Treasury yields suggest that, once again, the dollar is America’s currency, but everyone else’s problem. But while investors have few alternatives, the bond-salesman-in-chief cannot be complacent.

• 4.AI Is Reviving Chinese Marxist Economics

  As recently as two years ago, most Chinese economists paid only lip service to Marxism and assigned Western textbooks to their students. The advent of AI has changed that, because the technology—open source and available to the smallest manufacturer for a pittance—promises to avoid the “rent trap” common to capitalist economies.

• 5.Gen Z Is Transforming South Asia

  Facing diminished economic prospects, many young people see not flawed institutions in need of gradual reform, but predatory systems robbing them of their future. Across South Asia, this sense has animated powerful protest movements, some of which could shape their countries' political trajectories for decades to come.

• 1.AT&T takes OTel 2.0 into production

  Dell and AMD supply the hardware behind OTel 2.0’s live deployment In sum – what we know: AT&T has taken OTel 2.0, the open-source telecom AI model developed under the…

• 2.Report: Rethinking the RAN

  The RAN is entering a new phase where the principles of openness, the flexibility of cloud-native architectures, and the power of AI converge. Open RAN has laid the foundation for…

• 3.How space traffic management can save our satellites (Reader Forum)

  Space traffic is critical as debris and satellite constellations crowd low Earth orbit. Effective management will require tougher regulation, active debris removal, resilient satellite design and cybersecurity to keep orbital…

• 4.Verizon and Google Cloud expand AI partnership across service, network, and data

  Enterprise-wide overhaul puts Gemini agents on Google Cloud in live network operations In sum – what we know: Verizon and Google Cloud have announced a new partnership, and it’s a significant escalation…

• 5.Huawei, HP sign global Wi-Fi patent deal

  The agreement with HP reflects the commercialization of Huawei’s research and the recognition of its intellectual property by a major global technology company and ecosystem partner In sum – what…

• 1.Source Error

  Check Feed

• 1.Quantum-Based Solutions for Security Enhancement in Open Radio Access Networks

  Open Radio Access Networks (O-RAN) introduce unprecedented flexibility, interoperability, and intelligence into next-generation wireless systems, but their disaggregated and software-defined architecture also expands the attack surface and creates new security vulnerabilities. Conventional cryptographic mechanisms, while effective against classical threats, may become insufficient in the presence of quantum-enabled adversaries. This article presents a comprehensive perspective on quantum security for O-RAN, examining how quantum-resilient mechanisms can enhance confidentiality, authentication, and trust across the RAN ecosystem. It discusses post-quantum cryptography (PQC), quantum cryptography, quantum authentication, and quantum-enhanced threat detection within a zero-trust architecture based on continuous verification, least privilege,...

• 2.False-CSI Attacks in Power-Domain NOMA for 6G: A Threat Taxonomy and System-Level Impacts

  Power-domain non-orthogonal multiple access (NOMA) remains a widely studied technique for improving spectral efficiency and supporting dense connectivity in beyond-5G and 6G networks. Its main operating mechanisms, however, depend on the integrity of channel-state information (CSI). Power allocation, user ordering, pairing, clustering, and beamforming can all be distorted when the CSI consumed by the base station is deliberately biased rather than merely noisy. This article examines false CSI as an attack surface in power-domain NOMA. We organize the threat space using a compact taxonomy with two primary axes: magnitude, which distinguishes underreporting from overreporting, and ordering effect, which distinguishes order-preserving, boundary, and order-reversing attacks. We then show how coordinated false- CSI behavior, group-changing att...

• 3.Securing Cooperative Sensing in UAV Swarms Against Conformity-Driven Byzantine Attacks

  In integrated sensing and communication (ISAC) enabled 6G unmanned aerial vehicle (UAV) swarm networks, the widely adopted imitation-based conformity cooperation mechanism can be exploited by Byzantine attackers to fabricate false consensus, causing the effective error probability of normal UAVs to evolve dynamically and far exceed their inherent sensing errors, which invalidates conventional fusion methods built on the independence assumption. This paper proposes a conformity-aware Byzantine-resilient fusion framework that couples evolutionary game theory with maximum a posteriori (MAP) estimation. First, the strategy updates of normal UAVs are characterized by bounded-rational opinion dynamics, and the evolution dynamics of the misinformation ratio together with its evolutionarily stable state (ESS) are derived under death birth updatin...

• 4.Knowledge Distillation Driven Semantic NOMA with GAN Refinement for 6G Robotic Vehicle Networks

  To achieve sustainable intelligent mobility, 6G-empowered robotic vehicles (RVs) require high-fidelity visual perception under stringent bandwidth and energy constraints. Semantic communication offers a spectral-efficient solution but suffers from severe interference in uplink non-orthogonal multiple access (NOMA) RV networks. To address this, we propose a knowledge distillation-driven and generative models-enhanced NOMA framework for robust and green RV communications, named KDG-SemNOMA. First, we develop a ConvNeXt-based deep joint source-channel coding (DeepJSCC) architecture with an enhanced attention feature (AF) module for dynamic channel adaptation. Second, to mitigate interference without inference overhead, an orthogonal transmission teacher model guides the NOMA student model via a two-stage knowledge distillation strategy. Fina...

• 5.Franson-Interferometric Bounds on Entangled Two-Photon Absorption

  Entangled photons offer quantum correlations with no classical analogue. In entangled pair two-photon absorption (ETPA), absorption rate is predicted to scale linearly rather than quadratically with photon flux, promising molecular excitation at fluxes far below the classical threshold. Reported ETPA cross sections nevertheless vary widely across experiments, largely since the observable, the differential of the transmitted flux or weak fluorescence, is difficult to separate from scattering and linear losses. We present a method which uses Franson interference to study entangled two-photon absorption through delay-dependent coincidence measurements on dye molecules. Applying the method to Rhodamine 6G, we observe a small asymmetry in the Franson interference envelope and obtain a model-derived effective cross section of approximately 2.1 ...

• 1.No new articles

  Summary available at source link.

• 1.What survives honest evaluation? Leakage-safe, search-aware assessment of LLM-driven trading strategy discovery

  Large language models (LLMs) are increasingly used to discover trading strategies, and much of the resulting literature shares a methodological weakness: many candidate strategies are generated, the best is reported, and neither look-ahead bias nor the intensity of the search behind the reported result is corrected for. We present a strategy-discovery system that makes both corrections structural rather than procedural. First, the agent can only act through registry-validated tools whose feature space excludes look-ahead by construction; we show that this guardrail is not redundant with statistical correction: a deliberately leaky oracle posting a Sharpe ratio of 35 survives Deflated Sharpe and probability-of-backtest-overfitting testing completely. Second, the system records every strategy evaluation its search performs and deflates all ...

• 2.Harvesting the Volatility Risk Premium: A Learning-to-Rank Approach

  This paper develops the first end-to-end application of cross-sectional learning-to-rank to the S&P 500 weekly options (SPXW) zero-day-to-expiration surface, integrated with margin-aware position sizing, an abstention rule driven by model uncertainty, and a strict out-of-time integrity check. A LightGBM LambdaRank ranker scores a daily nine-strategy cross-section composed of eight delta-targeted short-put positions and a \textit{SKIP} candidate, trained against a path-aware Sortino-on-bars label computed at one-minute resolution. The framework is evaluated under index-option margin requirements, a tiered fee schedule, and bid-to-mid execution assumptions across a four-window walk-forward over 2021-2024 and a strictly held-out 2025 out-of-time slice. Seven sizing methods produce out-of-time annualized Sharpe ratios between 4.31 and 5.7...

• 3.Lead-Lag Relationships in Financial Markets: A Comparison of Multiple Clustering Algorithms

  Lead-lag relationships are widely used in financial time series, and many clustering algorithms based on them have been developed. The traditional DTW-KMedoids algorithm performs well both on the synthetic dataset and the real financial dataset. However, there are still several limitations to these algorithms: low efficiency caused by high time complexity, poor mathematical properties from DTW distance, the clustering effect is sensitive to the number of clusters. To solve the problems above and improve the performance, this paper introduces three clustering algorithms: MiniRocket-KMeans, KShape, Ensemble algorithm (a combination of KShape and DTW-KMedoids) and compares their performance on synthetic and real stock datasets with DTW-KMedoids algorithm under the same trade strategy. In addition, this paper also finds the best number of clu...

• 4.Equity Strategy Backtesting: Luck or Edge? The MinervaScore as a Statistical Robustness Grade

  Backtests of trading strategies are often selected after many parameter trials. A strong historical result can therefore reflect search luck rather than a persistent signal. Standard summaries such as return, Sharpe ratio, and drawdown do not record how many candidates were tried, whether the selected rule survives out-of-sample validation, or whether the available history is long enough to support the result. This paper describes the MinervaScore, a post-selection robustness grade for trading strategies. The score combines four established validation quantities: Deflated Sharpe Ratio, Probability of Backtest Overfitting, Superior Predictive Ability, and Minimum Track Record Length, with a regime-stability diagnostic. These components are converted into signed margins from their admissibility thresholds, aggregated into a raw score, and...

• 5.From Exponential to Polynomial: An Exact Filter for High-Dimensional MSM Models

  In this paper we propose a new formulation of the Bayesian Filter as used in the discrete-time Markov-Switching-Multifractal (MSM) model of volatility based on existing permutation symmetry within the likelihood structure. We show both analytically and empirically that such a formulation leads to a reduction in time complexity from $O(D^k)$ to $O(k^D)$ thereby significantly reducing the computational bottleneck associated with dimensionality. We compare the agreement between the naive and sector filters and find that while there are significant disagreements, the ground-truth recovery of the latter seems to improve on the former.

• 1.Quantum-Based Solutions for Security Enhancement in Open Radio Access Networks

  Open Radio Access Networks (O-RAN) introduce unprecedented flexibility, interoperability, and intelligence into next-generation wireless systems, but their disaggregated and software-defined architecture also expands the attack surface and creates new security vulnerabilities. Conventional cryptographic mechanisms, while effective against classical threats, may become insufficient in the presence of quantum-enabled adversaries. This article presents a comprehensive perspective on quantum security for O-RAN, examining how quantum-resilient mechanisms can enhance confidentiality, authentication, and trust across the RAN ecosystem. It discusses post-quantum cryptography (PQC), quantum cryptography, quantum authentication, and quantum-enhanced threat detection within a zero-trust architecture based on continuous verification, least privilege,...

• 2.False-CSI Attacks in Power-Domain NOMA for 6G: A Threat Taxonomy and System-Level Impacts

  Power-domain non-orthogonal multiple access (NOMA) remains a widely studied technique for improving spectral efficiency and supporting dense connectivity in beyond-5G and 6G networks. Its main operating mechanisms, however, depend on the integrity of channel-state information (CSI). Power allocation, user ordering, pairing, clustering, and beamforming can all be distorted when the CSI consumed by the base station is deliberately biased rather than merely noisy. This article examines false CSI as an attack surface in power-domain NOMA. We organize the threat space using a compact taxonomy with two primary axes: magnitude, which distinguishes underreporting from overreporting, and ordering effect, which distinguishes order-preserving, boundary, and order-reversing attacks. We then show how coordinated false- CSI behavior, group-changing att...

• 3.Securing Cooperative Sensing in UAV Swarms Against Conformity-Driven Byzantine Attacks

  In integrated sensing and communication (ISAC) enabled 6G unmanned aerial vehicle (UAV) swarm networks, the widely adopted imitation-based conformity cooperation mechanism can be exploited by Byzantine attackers to fabricate false consensus, causing the effective error probability of normal UAVs to evolve dynamically and far exceed their inherent sensing errors, which invalidates conventional fusion methods built on the independence assumption. This paper proposes a conformity-aware Byzantine-resilient fusion framework that couples evolutionary game theory with maximum a posteriori (MAP) estimation. First, the strategy updates of normal UAVs are characterized by bounded-rational opinion dynamics, and the evolution dynamics of the misinformation ratio together with its evolutionarily stable state (ESS) are derived under death birth updatin...

• 4.FlyBlind: Cross-Slice Timeliness Attacks on UAV Situational Awareness over 5G

  Beyond Visual Line of Sight (BVLOS) Uncrewed Aerial Systems (UAS) operating over 5G Standalone (SA) networks use a shared User Plane for both command-and-control (C2) data and video feedback. Operators assess link quality through latency and availability, relying on soft isolation between network slices. However, the risk that an authorized co-tenant could make the Ground Control Station (GCS) state outdated without disrupting the connection remains underexplored. This work introduces FlyBlind, a timeliness attack in which an authorized co-tenant on a neighboring slice maintains legitimate uplink demand, causing state aging at the GCS without a rogue gNB or direct interference with C2 traffic. Our key insight is that, under soft isolation, sharing idle resources turns authorized competition for grants into state aging that conventional li...

• 5.Knowledge Distillation Driven Semantic NOMA with GAN Refinement for 6G Robotic Vehicle Networks

  To achieve sustainable intelligent mobility, 6G-empowered robotic vehicles (RVs) require high-fidelity visual perception under stringent bandwidth and energy constraints. Semantic communication offers a spectral-efficient solution but suffers from severe interference in uplink non-orthogonal multiple access (NOMA) RV networks. To address this, we propose a knowledge distillation-driven and generative models-enhanced NOMA framework for robust and green RV communications, named KDG-SemNOMA. First, we develop a ConvNeXt-based deep joint source-channel coding (DeepJSCC) architecture with an enhanced attention feature (AF) module for dynamic channel adaptation. Second, to mitigate interference without inference overhead, an orthogonal transmission teacher model guides the NOMA student model via a two-stage knowledge distillation strategy. Fina...

• 1.SFC-Aware Online Aggregated Data-Link Orchestration for SDN/NFV-Enabled SAGINs

  Civil aviation space-air-ground integrated networks (SAGINs) are expected to support heterogeneous cockpit and cabin services over dynamic air-to-air (A2A), air-to-ground (A2G), and air-to-satellite (A2S) data links. This paper studies service function chain (SFC)-aware online access-side aggregated data-link orchestration for civil aviation SAGINs enabled by software-defined networking and network function virtualization (SDN/NFV). We jointly orchestrate spatial bearer resources and temporal elasticity enabled by temporal elastic mapping and parking (TEMP). A rolling-slot model is developed with four request-level actions: NOW, TEMP, REJECT, and DROP, under a lexicographic objective that prioritizes service success, then normalized access-orchestration delay, and finally residual TEMP-related risk. To avoid exhaustive search over the ful...

• 2.Adaptive Peer Clustering with Hierarchical Random Linear Network Coding for Resilient Decentralized Wireless Networks

  Decentralized wireless collectives including vehicular swarms, IoT clusters, and edge AI networks require communication protocols that maintain robustness under dynamic topologies and heterogeneous link quality. While Random Linear Network Coding (RLNC) provides algebraic resilience against packet erasures, its performance degrades significantly when peers exhibit diverse channel conditions. This paper presents Adaptive Peer Clustering with Hierarchical RLNC (APC-RLNC), a system that dynamically groups peers by exponentially weighted moving average (EWMA) reliability metrics and applies multi-tier network coding within and across clusters. We formalize the clustering optimization problem, derive closed-form decoding probability bounds for Markov erasure channels, and prove O(sqrt(T)) regret for online reconfiguration under the Follow-the-...

• 3.Stochastic End-to-End Latency Modeling of the IoT-Edge-Cloud Continuum: Impact of Jitter and Traffic Variability on Deterministic Service Provisioning

  6G will integrate communication and computing capabilities in a IoT-edge-cloud continuum, enabling nodes to distribute workloads across the continuum. To support time-sensitive services, both communications and computing latencies must be controlled. Two key sources of temporal variability are arrival-time jitter and traffic variability. They can both impact the timing at which data is generated, transmitted and processed, and the resulting fluctuations can propagate throughout the continuum, increasing latency uncertainty. This paper studies the impact of stochastic temporal variability on the ability to support end-to-end deterministic service levels across the continuum. To this end, we present a novel queueing-based end-to-end latency model for the continuum, which we openly release. The model jointly captures computing and communicat...

• 4.AERIS: Offline Policy Improvement for Multi-UAV Integrated Sensing and Communication

  Unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) is a promising 6G paradigm, but dynamic multi-UAV ISAC control must jointly balance communication quality, sensing reliability, and flight safety under stochastic mobility. Existing optimization methods often require repeated global non-convex solving, while online reinforcement learning (RL) depends on risky trial-and-error flights that may cause sensing loss or collision-risk events. This paper proposes AERIS, an offline policy improvement framework for multi-UAV ISAC. AERIS learns from fixed flight logs under centralized training and decentralized execution, so each UAV acts from local histories while training uses logged global information to assess team-level effects. We further design STAR-CRDT, an offline multi-agent RL algorithm that performs suppo...

• 5.Lightweight AI for UAV-Mounted RIS: An Overview

  Unmanned Aerial Vehicles (UAV)-mounted Reconfigurable Intelligent Surfaces (RIS) have emerged as a promising architecture for enhancing wireless coverage, spectral efficiency, and energy performance in 6G networks. By combining programmable electromagnetic wave manipulation with aerial mobility, UAV-RIS systems enable dynamic blockage mitigation, adaptive beamforming, and flexible deployment across terrestrial, maritime, and satellite-integrated environments. However, joint optimization of UAV trajectory, RIS phase configuration, and resource allocation incurs high computational complexity, which is incompatible with the strict energy and onboard processing constraints of UAV platforms. Lightweight AI techniques offer practical solutions to this challenge. Hence, this paper provides a comprehensive overview of lightweight AI techniques fo...