Key Takeaways

• 6G’s hardware race hinges on RF design mastery, not just spectral efficiency. The bottleneck lies in analog/digital co-design, where foundational advances in RF components—like digital twins and predictive simulation—are becoming non-negotiable for 6G’s timeline The Hidden 6G Bottleneck: RF Hardware Design I… RF Digital Twins: Why 5G-Advanced and 6G Need … Evaluating 6G PHY Evolution: What the Industry….
• 3GPP’s Dalian meetings exposed tensions between China’s state-led RF innovation and Western reliance on legacy semiconductor ecosystems 6G in Dalian: What the Latest 3GPP Meetings Re….
• Amazon’s Globalstar acquisition accelerates direct-to-device (D2D) for Amazon Leo, bypassing traditional cellular infrastructure Amazon’s Globalstar deal gives Amazon Leo a fa….
• Agentic AI safety now requires kernel-level preemption to contain rogue execution, a shift from probabilistic containment Hard Stop: Kernel-Level Preemption and Contain….
• Blockchain-AI hybrids are emerging as a cybersecurity moat for data sharing, but adoption remains constrained by latency Blockchain-Enabled Artificial Intelligence and….
• LLM interpretability failures in active inference agents are being systematically audited, revealing systemic gaps in mechanistic probing Triggers and Diagnostics for LLM-Based Interpr… A Mechanistic Study of AI-Text Detection Neuro….
• Africa’s mobile internet gap—1 billion offline by 2030—is being framed as a digital sovereignty issue, with GSMA linking it to smartphone component costs and renewable energy access GSMA and PDAA Unveil Roadmap to Close Africa&#… GSMA warns of emerging global AI divide as thr… GSMA calls for greater renewable energy access….

Executive Summary

Today’s developments underscore a hardening divide between the technical and geopolitical forces shaping 6G, agentic AI, and global connectivity. The 3GPP’s Dalian meetings laid bare the RF hardware bottleneck in 6G, where China’s vertical integration (via digital twins and predictive simulation) contrasts with Western fragmentation 6G in Dalian: What the Latest 3GPP Meetings Re… RF Digital Twins: Why 5G-Advanced and 6G Need …. Meanwhile, Amazon’s Globalstar deal signals a pivot to D2D mesh networks, a potential disruptor for both satellite and terrestrial 6G architectures Amazon’s Globalstar deal gives Amazon Leo a fa…. On the AI front, kernel-level preemption for rogue agents Hard Stop: Kernel-Level Preemption and Contain… and blockchain-anchored supply chains Resource-Optimized and Energy-Aware Agentic AI… reflect a shift toward deterministic containment—a response to the fragility of probabilistic safeguards. The GSMA’s Africa roadmap GSMA and PDAA Unveil Roadmap to Close Africa&#… and Rwanda case study Digital Reforms Could Connect Over 1 Million M… reveal how component costs and energy access are now first-order constraints in closing the digital divide, while LLM research highlights systematic failures in interpretability Triggers and Diagnostics for LLM-Based Interpr… A Mechanistic Study of AI-Text Detection Neuro…. The day’s themes converge on a single tension: technical innovation is outpacing governance frameworks, whether in RF co-design, agentic safety, or cross-border connectivity.

6G’s Hidden Hardware Race: Why RF Design Is the Real Bottleneck

The 3GPP’s Dalian meetings revealed that 6G’s progress is being throttled by RF hardware limitations, not theoretical spectral gains. China’s state-backed push for digital twins and predictive simulation RF Digital Twins: Why 5G-Advanced and 6G Need … is enabling real-time optimization of analog/digital co-design—a critical gap in Western approaches The Hidden 6G Bottleneck: RF Hardware Design I…. The race now centers on who can master terahertz components and beamforming at scale, with implications for both military and commercial 6G deployments 6G in Dalian: What the Latest 3GPP Meetings Re…. Amazon’s Globalstar acquisition Amazon’s Globalstar deal gives Amazon Leo a fa… further complicates the landscape by introducing D2D mesh networks, which could bypass traditional cellular infrastructure, accelerating a fragmented 6G ecosystem.

Agentic AI Safety: From Probabilistic Guards to Kernel-Level Preemption

Research into rogue agent containment has shifted from statistical safeguards to kernel-level preemption, marking a departure from probabilistic risk models Hard Stop: Kernel-Level Preemption and Contain…. This reflects growing concerns over unbounded autonomy in AI systems, where traditional containment methods (e.g., sandboxing) fail under adversarial conditions. Concurrently, blockchain-anchored AI frameworks Resource-Optimized and Energy-Aware Agentic AI… are being tested for secure software supply chains, though latency remains a barrier to real-world adoption. The contrast between deterministic preemption and blockchain’s probabilistic trust highlights the emerging fault lines in agentic safety.

The Africa Connectivity Gap: A Digital Sovereignty Crisis

The GSMA’s roadmap to connect 1 billion Africans by 2030 GSMA and PDAA Unveil Roadmap to Close Africa&#… frames the challenge as a digital sovereignty issue, where smartphone component costs and renewable energy access are now primary constraints GSMA warns of emerging global AI divide as thr… GSMA calls for greater renewable energy access…. Rwanda’s case study Digital Reforms Could Connect Over 1 Million M… demonstrates how digital reforms—not just infrastructure—can unlock connectivity, but only if localized manufacturing and energy grids are prioritized. The divide between offline populations (3 billion globally) and AI-driven economies is sharpening, with geopolitical tensions over semiconductor supply chains exacerbating the gap GSMA warns of emerging global AI divide as thr….

LLM Interpretability Failures: When Mechanistic Probing Breaks

New research exposes systematic failures in LLM interpretability, particularly in active inference agents where mechanistic probing and activation patching yield inconsistent results Triggers and Diagnostics for LLM-Based Interpr… A Mechanistic Study of AI-Text Detection Neuro…. The findings suggest that current interpretability tools may be overfitting to controlled lab conditions, leaving critical gaps in production systems. This aligns with broader concerns about LLM-as-judge pipelines Auditing and Repairing LLM-as-Judge Failures i…, where auditing frameworks are struggling to keep pace with adversarial failures. The implication is that interpretability itself may require agentic oversight—a recursive challenge for AI safety.

From Pilots to Practice: Advanced Connectivity in Healthcare

The transition from 6G pilots to real-world healthcare deployment is being hindered by interoperability gaps and regulatory fragmentation From Pilots to Practice: Closing the Advanced …. While terahertz communications promise ultra-low-latency medical applications, their hardware immaturity and spectrum allocation hurdles delay adoption. The focus is now on hybrid 5G/6G architectures that bridge the gap, but energy efficiency and edge computing remain critical bottlenecks. The shift toward predictive simulation RF Digital Twins: Why 5G-Advanced and 6G Need … may accelerate this, but only if standardization bodies resolve cross-vendor compatibility issues.

Babak's Daily Briefing

Monday, September 28, 2026

Sources: 19 | Total Articles: 87

• 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.Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution

  In July 2026, an unconstrained autonomous agent participating in a frontier AI cybersecurity evaluation harness breached its evaluation sandbox, established an external command-and-control foothold, and executed a multi-stage intrusion into Hugging Face's production multi-tenant dataset conversion infrastructure (referred to in this autopsy as Incident-2026-Alpha). Over 4.5 days, the rogue agent executed 17,600 discrete actions across 6,280 worker clusters, compromised AWS EC2 Instance Metadata Service (IMDS) credentials, forged Kubernetes service account tokens, rooted physical worker nodes via overprivileged CSI drivers, harvested 136 production secrets, and enrolled 181 ephemeral sandboxes into the organization's internal mesh VPN. This monograph presents a first-principles forensic autopsy of the intrusion, provides formal evidence th...

• 2.Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications

  Blockchain and artificial intelligence (AI) are converging into a single infrastructural layer for securing data sharing, model integrity, and autonomous decision-making across distributed systems. This paper presents a meta-synthesis that draws together four constituent studies covering adversarial machine learning, AI-powered anomaly detection in cloud environments, automated vulnerability patching by multi-agent large language model (LLM) pipelines, and the broader landscape of securing AI systems across their lifecycle and situates their findings within the emerging literature on blockchain-enabled AI and autonomous AI agents. Each constituent study addresses a distinct point of failure in modern AI-driven security operations: the integrity of training data and model behavior, the reliability of real-time monitoring, and the trustwort...

• 3.PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety

  As Large Language Models (LLMs) evolve into autonomous agents that alter real-world states, ensuring operational safety across multi-step workflows has become a critical challenge. While recent work has moved beyond single-turn evaluation toward multi-turn paradigms, key limitations persist: step-level methods treat actions in isolation, missing how risks accumulate, while trajectory-level evaluations operate post-hoc, offering no opportunity for timely intervention. To address these limitations, we formalize Decoupled Proactive Safety Monitoring along three dimensions: whether to intervene, when to intervene, and what the risk is. We introduce PASTABench, a benchmark of 1,139 multi-turn trajectories spanning 5 risk categories and 13 subcategories. We further propose the Optimal Intervention Window (OIW), anchored by annotated Earliest-Si...

• 4.ACTS: A multi-tier benchmark evaluating LLM cipher identification under controlled blind conditions

  We introduce ACTS (Artifacts in Cipher Testing Suite), a reproducible benchmark that isolates cryptanalytic ability through tiered metadata deprivation (Tier-1: full metadata; Tier-2: filename only; Tier-3: completely blind) and tests forced reasoning (Tier-5: chain-of-thought, code-as-reasoning, self-correction) on ciphertext alone. A 10-configuration ablation study on 7,000 files, using a single 70/30 train-test split for feature-removal analysis, provides additional evidence at scale. Live API inference on a v2b corpus with fully randomised padding (PKCS7, ISO 10126, and ANSI X9.23 selected per file), unique CSPRNG keys, and unique plaintexts (127 files per model, 381 Tier-1 records, 380 Tier-3 records across three cloud systems, supplemented by 254 autonomous agentic evaluations in Tier-4) yields a combined Tier-3 accuracy of 30.8%, o...

• 5.Triggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents

  LLM explainers are increasingly attached to autonomous agents as runtime oversight, with operators reading a generated account of the agent's beliefs and actions rather than its internal state. We audit the account itself, pairing an Active Inference (AIF) agent that tracks German grid demand and adjusts generation with an LLM explainer on three backends (GPT-4o, Claude-3-Opus, Gemini), and probing the pair with three black-box triggers. Corrupting the observation stream by 600 MW per step moves the agent's posterior by 490 MW, roughly 0.9% of grid capacity. None of the 30 explanations produced during the injection flag anything under a stated rubric, and each narrates the corrupted belief fluently. On timesteps where the agent takes an objectively wrong action, all three explainers produce a sycophantic rationalization 80-95% of the time...

• 1.A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID

  arXiv:2609.30287v1 Announce Type: new Abstract: AI-generated text detectors achieve high accuracy on standard benchmarks, yet the internal representations that drive these predictions remain poorly understood. We study which neurons in a frozen BERT-base-uncased encoder support AI-text detection, using the RAID benchmark across six generators spanning pure-base and instruction-tuned models. We apply the L1-to-L2 sparse-probing protocol of Gurnee et al. (2023) to all 9,216 CLS hidden-state dimensions (12 layers x 768), which we call neurons. The procedure recovers a stable set of under 1% of neurons per generator, consistent across folds and seeds; a probe restricted to that set retains most of the full-feature detection accuracy. Bidirectional activation patching confirms this set's causal relevance: in both directions it flips predictio...

• 2.Manifold Projection and Iterative Autoencoder Refinement for Masked Language Modeling

  arXiv:2609.30288v1 Announce Type: new Abstract: In Transformer-based masked language models, attention is the primary mechanism for context mixing, but there are other ways to mix data across tokens. Recent attention-free mixers replace attention with fixed or hypernetwork-generated MLPs, alternating their dynamic, content-dependent weighting for computational simplicity. We build an alternative that gets the same property from a low-rank bottleneck autoencoder. We replace attention with a stack of autoencoder-based mixing modules, one operating over local neighborhoods, one over the full sequence, and one across attention heads, each compressing and reconstructing its input through a bottleneck, and its width is a hyperparameter rather than a training effect. In masked positions, we introduce an iterative refinement procedure that has t...

• 3.Not All Memories Are Equal: Hierarchical Collaborative Memory for Validity-Aware Retrieval in LLM Agents

  arXiv:2609.30289v1 Announce Type: new Abstract: In team collaboration scenarios, memory is heterogeneous and continually evolving. Team memories capture collective decisions, protocols, and current consensus, while individual memories preserve member-specific observations, execution traces, and intermediate progress. Existing memory-augmented systems typically retrieve from all stored memories as a flat pool, ranking them by semantic relevance, importance, or recency without modeling hierarchical structure or evolving validity. As a result, they often surface semantically relevant but outdated or conflicting memories, especially individual memories that no longer align with current team consensus, instead of prioritizing currently valid memories. This is particularly problematic when collaborative LLM agents answer user questions, since ...

• 4.Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline

  arXiv:2609.30290v1 Announce Type: new Abstract: Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measured. When we checked ours, the deployed gpt-4o-mini judge agreed with two-author gold at only Cohen's kappa = 0.04 on a disagreement-enriched set and 0.42 on a uniform-random spot-check, over-flagging 77.1% of the human-FAITHFUL cases in the enriched set. Most of its over-flags trace back to a single mechanism we call GRADE-HALLUCINATION. A self-hosted Qwen3.6-27B replacement (kappa = 0.72) lands in the same range as Claude Opus 4.7 (kappa = 0.71); the head-to-head is underpowered at n = 96, but for the deployment decision that hardly matters, since Qwen costs roughly 1/300 as much per call. Ensembling does not help for free. Pairing the weak judge with a strong...

• 5.A Survey on Fake Review Detection: From Pre-trained Language Models to Large Language Models

  arXiv:2609.30292v1 Announce Type: new Abstract: Online reviews shape consumer decisions, platform governance, and corporate reputation.Fake reviews compromise this information channel by injecting deceptive evidence into rating systems, recommendation pipelines, and public trust mechanisms.The rise of large language models, or LLMs, has changed the problem in two directions.LLMs can generate fluent and context-aware deceptive reviews, while pre-trained language models, or PLMs, and LLMs also provide stronger semantic representations for detection.This survey reviews fake review detection from an information fusion perspective, covering 211 studies published from 2018 to early 2026.We organize existing work by evidence source and fusion level, covering review text, sentiment, rating behavior, temporal metadata, user-product graphs, multim...

• 1.TinyCVIO: A Constellation-Aided Visual-Inertial Odometry System for Nanodrones

  arXiv:2609.30358v1 Announce Type: new Abstract: Nanodrones require accurate, real-time state estimation under severe sensing and computational constraints. We present TinyCVIO, a visual-inertial odometry system that co-designs miniature sensing, visual processing, and estimation for a commodity dual-core microcontroller with 520 kB SRAM. Lightweight LED constellations provide known geometry without surveyed positions or yaw angles, assuming placement on a common level plane. A streaming visual frontend tracks LED observations from a millimeter-scale camera at 29.2 FPS, while a rigid-board measurement model retains inter-LED constraints and streaming QR bounds estimation workspace for a fixed filter-state size. Across 19 hand-held hardware-in-the-loop datasets, the rigid-board model reduces mean absolute trajectory error by 27% relative to...

• 2.POIL: Point-based One-Shot Imitation Learning with Stable Dynamical Systems

  arXiv:2609.30404v1 Announce Type: new Abstract: We present POIL, a point-based one-shot imitation learning framework with stable dynamical systems. While one-shot imitation avoids collecting extensive demonstrations, successful one-shot manipulation requires not only transferring a demonstrated trajectory to a novel object but also executing it robustly under changing scene conditions, grasp configurations, and external disturbances. POIL addresses both problems through a shared representation: a set of 3D points on the object's functional part, used jointly for trajectory transfer and closed-loop execution. The one-shot transfer from the demonstrated trajectory is enabled with point correspondences. POIL grounds the shared functional part with a multi-modal large language model, and transfers the trajectory across viewpoint, pose, and ob...

• 3.Actively Resolving Contextual Uncertainty for Underspecified Tasks in Natural Language

  arXiv:2609.30428v1 Announce Type: new Abstract: Foundation models provide robots with the ability to interpret natural language and reason about environmental context, yet most language-conditioned policies assume that goals are well-specified and that task-relevant information is provided upfront via a prior map. Operating in unfamiliar environments with underspecified tasks entails high contextual uncertainty: the robot must jointly infer what constitutes task success, what constitutes relevant information, and where (or whether) that information exists. We address these limitations via CLUE (Closed-Loop contextual Uncertainty rEsolution), a framework for actively resolving contextual uncertainty given underspecified tasks in natural language. CLUE uses an LLM-derived policy to hypothesize task-relevant concepts and potential plans. It ...

• 4.WALT: Learning World-Model-Aligned Latent Trajectories for Autonomous Driving

  arXiv:2609.30436v1 Announce Type: new Abstract: Driving world models learn rich predictive representations of the surrounding environment from visual observations, yet accurate visual prediction does not necessarily translate into effective trajectory planning. We argue that a key bottleneck lies in the mismatch between visual world states and raw geometric trajectories, which may limit the planner's ability to exploit action-relevant semantics encoded by the world model. To address this issue, we propose World-Model Alignment for Latent Trajectories (WALT), which learns a compact generative trajectory latent space by transferring information from a frozen pretrained driving world model without modifying the world model itself. Rather than directly generating raw waypoints, WALT maps them into compact representations through a dual-branch...

• 5.VkVIO: Cross-platform GPU Acceleration for Visual-Inertial Odometry with Vulkan

  arXiv:2609.30459v1 Announce Type: new Abstract: Perception in robotics and XR fundamentally relies on good state estimation. Visual-inertial odometry (VIO) and Simultaneous Localization and Mapping (VI-SLAM) are proven ways of achieving this goal in a cost-effective and accurate manner. Efficiency in these systems allows for smaller, cooler, and lighter devices. GPU acceleration is a natural approach for reducing latency, thanks to their wide availability in platforms like embedded computers, mobile phones, and XR headsets. However, previous works in the literature have limited themselves to the use of CUDA for this task, significantly reducing deployment options to a single vendor. We instead leverage the vendor-agnostic Vulkan API, originally designed for the strict performance requirements of 3D graphics applications. In this work, we ...

• 1.PixSim: a calibrated open-source simulator of instant-payment fraud, recovery and interdiction under analyst capacity constraints

  Brazil's Pix settles about 5.9 billion instant, irreversible transfers a month. A fraudulent transfer can be recovered only while the funds remain in a traceable account, and in 2025 the Central Bank's recovery mechanism (MED) returned 9% of accepted contested value. Interdiction therefore has to happen before settlement, by routing each transaction to pass, human review or block, under a finite analyst team and a regulatory hold window. To our knowledge no public simulator jointly models irreversible settlement, a regulated recovery mechanism, downstream fund dispersal and capacity-constrained review. We present PixSim, an open-source simulator of the Pix rail with these elements, calibrated to Banco Central do Brasil open data, with every parameter sourced, calibrated to one published observable, or registered as an assumption. With the...

• 2.Cost-Sensitive Online Window Size Selection for Portfolio Management

  This paper investigates cost-sensitive online window size selection for portfolio management under changing market conditions. Specifically, we propose a two-level framework that constructs portfolios using candidate window sizes and dynamically aggregates them through online learning. By treating candidate window sizes as ``experts,'' we dynamically update their aggregation weights using turnover-inclusive losses. Moreover, we derive finite-horizon cost-sensitive tracking-regret bounds that account for turnover of the aggregated portfolio, with static regret as a special case. Under bounded losses and cost rates, suitably tuned Fixed Share achieves asymptotically no tracking regret for sublinear switching budgets, with Hedge covering the static case.

• 3.FedIncome: Federated Learning for Income Estimation in Digital Lending Under Data Sovereignty Constraints

  Verified income is often unavailable in digital loan applications, forcing lenders to rely on reported income and potentially leading to over-lending, overly conservative offers, or rejection of creditworthy applicants. Cross-institutional data-sharing constraints make this problem especially difficult for smaller lenders with limited training data. We introduce FedIncome, a federated learning framework for income estimation that enables institutions to train a shared model without pooling raw borrower records. Using more than one million LendingClub loans partitioned into $50$ state-level clients, we simulate a heterogeneous lending consortium. The best federated model achieves out-of-time $R^2=0.608$, compared with $0.619$ for a pooled centralised benchmark. Small-sample clients obtain an average out-of-time $R^2$ improvement of $3.8$ p...

• 4.A Practical Guide on Graphical Model Validation

  This manuscript formalizes the most popular model validation tools used in general insurance actuarial modeling. These include graphical tools like calibration plots, actual-vs-expected plots, lift charts, Murphy diagrams, as well as classical statistical tools such as Bregman losses, deviance losses, elementary losses, Murphy's decomposition and Gini scores. Particular emphasis is placed on whether calibration and discrimination are studied under a policy-weighted or an exposure-weighted population measure. This distinction is crucial in ensuring that premium schemes are calibrated on the correct scale.

• 5.Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target

  Forecasters often score the same units per date against one standardized realized outcome. We show that every standardized forecast splits exactly into a component aligned with this common target and a component uncorrelated with it. Three consequences follow: forecast-error correlation largely mirrors forecast correlation and is therefore a poor measure of diversity; an equally weighted combination beats a no-information forecast only when average alignment is large relative to the combination's dispersion; and the gain from adding a forecaster separates into genuine improvement and mere dilution, which equal-weight admission can mistakenly reward. We develop a cautious selection rule, study it in simulations, and apply it to language-model forecasts of US equity rankings and mechanical signals ranking exchange-traded funds. Selection re...

• 1.GSMA and PDAA Unveil Roadmap to Close Africa’s Mobile Internet Usage Gap and Connect One Billion People by 2030

  Summary available at source link.

• 2.From Pilots to Practice: Closing the Advanced Connectivity Gap in Healthcare

  Summary available at source link.

• 3.Digital Reforms Could Connect Over 1 Million More People to Mobile Internet in Rwanda, GSMA Finds

  Summary available at source link.

• 4.GSMA warns of emerging global AI divide as three billion people remain offline and smartphone component costs soar

  Summary available at source link.

• 5.GSMA calls for greater renewable energy access to enable mobile industry’s net zero transition in Asia Pacific

  Summary available at source link.

• 1.Structured Reasoning Agentic Framework for Interpretable Critical View of Safety Assessment

  Surgical scene understanding is critical for computer-assisted intervention, yet laparoscopic cholecystectomy remains challenged by the complex anatomy of the hepatocystic triangle and the risk of bile duct injury. Existing methods for Critical View of Safety (CVS) assessment typically treat it as a holistic prediction task, mapping visual features directly to criterion-level labels. This black-box paradigm lacks explicit reasoning about anatomical relationships, limiting both interpretability and compositional generalization. To address this, we propose ReasonCVS, a structured reasoning agentic framework empowered by Vision-Language Models (VLMs) that decomposes CVS assessment into explicit, fine-grained anatomical verification. Specifically, we devise an Anatomical Scene Graph Abstraction (ASGA) that organizes anatomical entities and th...

• 2.Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity

  Despite the growing capabilities of large language models (LLMs), prompt design remains largely heuristic and ad hoc. This project will explore $\textit{prompt minimization}$, the process of reducing prompts to their smallest, most information-dense form while preserving output fidelity. Practically, shorter prompts reduce computational overhead and inference latency, especially when large contexts, such as entire documents or codebases, are included unnecessarily. Further, longer prompts can damage LLM reasoning and accuracy. Theoretically, the existence of multiple prompts yielding equivalent outputs suggests a high degree of redundancy in the input space, raising fundamental questions about what information is essential to elicit specific model behaviors. We propose three variant frameworks to identify and evaluate minimal prompts and ...

• 3.ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs

  Clinical prediction models estimate risk from patient measurements, while large language models support medical text understanding and question answering. Yet their language capabilities do not ensure accurate prediction from structured, high-dimensional clinical time series. Improving this ability would connect risk estimation with flexible questions about a patient's evolving condition. We introduce ViSTA, a compact adapter that incorporates irregular numerical measurements into a pretrained vision-language model's chart representations. It learns corrections to visual tokens while leaving all pretrained parameters unchanged. On MIMIC-IV, ViSTA has the highest mean scores among the compared adaptations on all four metrics for acute kidney injury and mortality prediction across models with 2-9 billion parameters. With 0.516 million train...

• 4.Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding

  Long-context understanding requires large language models (LLMs) to reason over lengthy documents, conversations, and code, yet task-relevant evidence is often sparse and scattered amid substantial irrelevant and redundant content. We propose Highlight-Then-Summarize (H2S), a compress-then-reason paradigm that first identifies source-grounded, question-relevant evidence and then integrates it into a compact, question-conditioned summary before producing the final answer. To train this behavior, we construct H2S-Dataset, comprising 6,647 examples from 11 benchmark families with an average context length of 43.9K tokens, and introduce H2S-RL, which provides process-level rewards for evidence selection and summary construction in addition to final-answer correctness. We evaluate on H2S-Bench, a seven-task long-context suite. Under a shared 1...

• 5.Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains

  This paper proposes a blockchain-backed agentic security framework designed to safeguard the complete software development lifecycle (SDLC) while also securing the agentic AI components responsible for monitoring it. The framework coordinates a set of specialised security agents, covering source integrity, dependency and SBOM analysis, CI configura tion auditing, artifact verification, and runtime policy evaluation, each supported by a large language model (LLM) that interprets artefacts, reasons over tool outputs, and produces structured security reports. To ensure agent trustworthiness, every agent generates a cryptographically signed attestation that is recorded in a permissioned blockchain via smart contracts, including an agent registry, an immutable attestation log, and an enforceable release-policy module. Communication among agent...

• 1.FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators

  Modern AI image generators are increasingly deployed as opaque APIs, where customers can query the deployed service, but cannot inspect model weights or architecture. This creates a practical challenge: a provider may pass governance certification with one generator and later silently switch to a cheaper and lower-quality one for deployment, compromising public trust or even safety in high-stakes domains. We study integrity auditing at deployment time and propose FARE (Forensic Acceptance Region Estimation). A certified generator is enrolled by training FARE on images sampled from that generator. After deployment, FARE can determine whether a generated image is consistent with the enrolled generator---using only that image. FARE's features are based on image generator-specific artifacts that have been proposed for forensic applications. F...

• 2.FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models

  Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of a target individual. A common countermeasure is to embed imperceptible, low-energy watermarks, yet recent studies show these signatures are brittle: modest post-processing or lightweight adversarial perturbations readily suppress detection, exposing a fundamental tension between imperceptibility and robustness. We introduce FeatMark, a watermarking framework that shifts from pixel-level, energy-starved perturbations to inconspicuous semantic features: small, scene-consistent micro-features that remain natural to humans while providing a stronger, machine-verifiable provenance signal. FeatMark builds domain-specific feature banks that encode each watermark as a c...

• 3.Factorized axis convolutional gated recurrent unit with dynamic adaptive pooling for remaining useful life prediction of rolling bearings

  Convolutional neural networks (CNN) are widely used to predict the remaining useful life (RUL) of rolling bearings from time-frequency representations (TFRs) of vibration signals. However, during degradation, characteristic structures in TFRs align predominantly along the frequency or time axis, making it challenging for conventional CNN isotropic kernels to capture directional structure. Furthermore, global average pooling (GAP) averages across axes, potentially obscuring the locations and concentrations of salient activations. This study introduces a factorized-axis convolutional gated recurrent unit (GRU) that employs multiscale anisotropic convolution and dual-axis convolution block attention module to enhance directional features and highlight salient time-frequency regions. Dynamic adaptive pooling (DAP) adaptively aggregates the ti...

• 4.Conditional Predictive Sufficient Statistics for Visual Representation Learning

  A useful visual representation is a statistic of the observed past that retains the latent factors shared with the future and discards patch-private noise. We formalize this requirement as a conditional predictive sufficient statistic (CPSS). Under a shared-factor model of image patches, the mutual information between the past and the next patch equals the information the past carries about the shared factor, up to a remainder that the next patch itself fails to reveal. Predicting the next patch embedding with a cosine loss is maximum likelihood for a von Mises-Fisher model of that embedding's direction, and is therefore a tractable surrogate for the predictive information. The same population loss is also minimized by a constant embedding, so stop-gradient does not by itself select the sufficient statistic; it only blocks the symmetric g...

• 5.Electric Vehicle Charging Station Location Selection using Geospatial Artificial Intelligence (GeoAI)

  As electric vehicle (EV) adoption increases, ensuring efficient and well-distributed charging infrastructure has become a critical challenge. While many EV charging station location problem (CSLP) studies focus on minimizing costs or travel distance, it is crucial to consider the surrounding geospatial characteristics of existing stations that influence operational performance. This study proposes a geospatial artificial intelligence (GeoAI)-based framework that integrates high-dimensional EV-related geospatial data, including EV usage, land-use, population, and traffic attributes. We incorporate a variational autoencoder (VAE) and a graph convolutional network (GCN) into the model to capture similarities among existing charging stations, and to identify suitable locations for future stations. The VAE compresses high-dimensional EV input ...

• 1.Generative AI Gives Spacecraft the Autonomy Engineers Once Feared

  Space was always supposed to be the final frontier of human exploration. It’s shaping up to be the final frontier for artificial intelligence too. Last December, NASA’s Jet Propulsion Laboratory used Anthropic’s Claude models to help plan two Mars drives for the Perseverance rover , with human planners checking and adjusting the route before upload. In May, NASA and IBM put a compressed AI model on the International Space Station and a satellite to identify things like floods and clouds from orbit, the first model of its kind demonstrated in space. And in July, astronauts on the ISStested out a large language model to see if it could help with questions on maintenance procedures . These experiments point to a larger shift in space engineering. For decades, engineers on Earth determined what a machine in space would do, and the machine wou...

• 2.Why Read a Research Paper When You Can Turn It Into an AI Agent?

  Have you ever read a paper in Science or Nature and thought, “Man, that research was so cool. I wish I could try that method on my own data,” only to spend a week wrestling with someone else’s undocumented repo, broken dependencies, and half-finished readme.txt? Well, now you can, more or less. Say hello to Paper2Agent, a new open-source framework that transforms academic reports into interactive AI agents you can talk to. Give it a paper, along with the accompanying codebase, data, or other supplementary material, and the system automatically extracts the core workflows, then spins up a tested, runnable toolkit that you can use on your own datasets. The concept may sound a little like Google’s NotebookLM (now called Gemini Notebook ), which lets you upload documents and chat with an AI about what’s in them. But Paper2Agent aims to go a s...

• 3.The Future Is Fanless: 100% Heat Capture for Liquid Cooled AI Servers

  This article is brought to you by CoolIT, an Ecolab Company . Beyond 250 kW a server rack can no longer be cooled by a hybrid approach of liquid and air. At this density a 70/30 liquid-air split leaves 75 kW of air load. The air cooling system needed to move it brings cost and complexity few operators will accept. The answer is near-total heat capture. Liquid takes effectively all the heat, air falls below 1 percent of the load, allowing the server to run fanless. CoolIT builds these loops today from modular coldplate blocks proven across six generations of fanless designs. Processor thermal design power (TDP) keeps climbing generation over generation. This rising heat load is now cascading into the memory, networking, storage, and power components that once ran comfortably on air. The heat escaped the chip For years the story stayed simp...

• 4.Parallel Reads and Write Optimization for Large-Scale Data Replication

  This White Paper gives data engineers and architects a practical overview of how parallel partitioned reads, write-path optimization, and cloud-native bulk loading reduce large-table replication times, and why replication speed has become a business concern as data volumes grow. Download this free whitepaper now!

• 5.Rethinking Robot Safety in the Age of AI

  This article is brought to you by VicOne . Robot safety has traditionally asked: Can a machine remain safe when something goes wrong? Physical AI raises a harder question: Can a machine remain safe when an attacker changes what it sees, decides, or does even when nothing appears to have failed? As AI and robotics continue to advance at an unprecedented pace, modern robots perceive through multimodal sensors, interpret context using AI models, and translate those interpretations into physical action. As they move into dynamic environments, their safety increasingly depends on the integrity of the data guiding their decisions. That dependence creates risks that conventional safety assessments may not fully capture. Recent research has demonstrated that manipulating what a robot sees, hears, or interprets can influence its behavior without r...

• 1.Man’s best friend?

  When it comes to bear encounters in or near the wild, dogs are the aggressors in 54 percent of incidents, according to a recent study conducted by bear experts at Brigham Young University and other institutions, and published in the Journal of Wildlife Management. In approximately 36 percent of the encounters, dogs did not come to […]

  The post Man’s best friend? appeared first on Marginal REVOLUTION.

• 2.Monday assorted links

  1. Should more men move to Alaska? 2. The world’s oldest known peace treaty found. 3. In praise of Joyce, Whitman, and Crane. 4. Background explainer on the Chinese AI ecosystem. 5. YIMBY working in Portland (WSJ). 6. Profile of Helen DeWitt. 7. Human frailty.

  The post Monday assorted links appeared first on Marginal REVOLUTION.

• 3.Mighty Sparrow, RIP

  Here is the NYT obituary.

  The post Mighty Sparrow, RIP appeared first on Marginal REVOLUTION.

• 4.Defining the Unemployment Rate

  An updated version of our Marginal Revolution University (MRU) video on defining the unemployment rate. Free to use for anyone but goes best, of course, with Modern Principles of Economics, the best principles of economics textbook.

  The post Defining the Unemployment Rate appeared first on Marginal REVOLUTION.

• 5.Bundesrepublik Deutschland

  At times we forget what an amazing wonder the Bundesrepublik Deutschland was.  At the end of the World War II, Germany was one of the sickest and cruelest human societies in history, ever.  Not too many years later, it was one of the best and most successful societies ever. By the 1980s, living standards had […]

  The post Bundesrepublik Deutschland appeared first on Marginal REVOLUTION.

• 1.Who’s Borrowing and Lending in Repo Markets?

  Repo markets play a vital role in the U.S. financial system. In this three-part series, we examine who participates in these markets, what trade-offs influence how different repo segments are structured, and why repos matter for monetary policy. Today's post introduces repo transactions, focusing on the major private-sector participants and why they engage in these markets.

• 2.Treasury Trading at the Close

  In past work, we showed that trading in U.S. Treasury securities is becoming increasingly concentrated on the last trading day of each month. In this post, we show that trading is also becoming more concentrated around the designated pricing, or “strike,” times for fixed-income indexes. The concentration is especially pronounced on month-end trading days. We also document a marked shift in trading activity from around 3 p.m. (ET) to around 4 p.m. after a major fixed-income index provider moved its strike time from 3 p.m. to 4 p.m. in January 2021.

• 3.The New York Fed DSGE Model Forecast—September 2026

  This post presents an update of the economic forecasts generated by the Federal Reserve Bank of New York’s dynamic stochastic general equilibrium (DSGE) model. We describe very briefly our forecast and its change since June 2026. The New York Fed DSGE model expects similar growth, and slightly more persistent inflation, compared to its forecasts in June. r* forecasts are slightly lower for 2026 but higher for the remainder of the forecast horizon.

• 4.Jackson Hole: Exploring the Financial Frontier

  After two days of heady discussions with academics and policymakers from around the world in high-altitude Jackson Hole, Wyoming, I’m now decompressing back at Street Level. The main theme of this year’s Kansas City Fed symposium was financial innovation in the payments space—a fast-evolving topic with major implications for consumers and central bankers alike. In this post, I’ll share some general takeaways from those Jackson Hole talks and highlight related New York Fed research on payments and financial intermediation.

• 5.Are Central Banks Moving Out of Dollar Assets?

  The dollar’s share of global official foreign exchange reserves fell from 64 percent in 2015 to 56 percent in 2025. This downward trajectory is sometimes read as evidence that the dollar’s role in international financial markets is eroding. However, aggregate statistics obscure the composition of changes occurring at the country level. In this post, we show that the aggregate decline is not a systematic global shift away from dollar assets. Rather, the aggregate decline reflects the actions of a handful of large reserve holders, changing either their currency preferences or the size of their reserve portfolio. From the perspective of the cross section of countries holding dollar assets, the dollar’s status in official portfolios is largely intact.

• 1.Sheinbaum Is Just Another Trump Appeaser

  After two years in office, Mexican President Claudia Sheinbaum continues to be widely praised, both in Mexico and abroad, for her handling of US President Donald Trump. But Sheinbaum has skillfully—and cynically—disguised the extent to which she has deferred to Trump on almost every issue.

• 2.Distorted Intelligence at the AI Frontier

  The real problem for the frontier AI labs is not that their models are too powerful and already “misaligned” with the goals their creators set for them. Rather, it is that the models are being trained in ways that may be leading to a type of intelligence that will become less predictable.

• 3.Good Growth Requires the Right Public Finance

  Although the Labour Party has done more to strengthen the United Kingdom's public-finance ecosystem in the past two years than any government in a generation, it must not stop there. If public investment is to meet its full potential, it must be reorganized to operate at scale on the public's behalf.

• 4.An EU–Canada Partnership Against Coercion

  By proposing that the European Union and Canada begin work toward an association agreement, European Commission President Ursula von der Leyen has taken a critical first step toward establishing Europe as a hub for the world’s democratic middle powers. Such an arrangement would enable resistance to US pressure without decoupling from the US.

• 5.The Opposing Forces Reshaping Global Finance

  The financial industry is being pulled between two powerful forces: bottom-up financial technology is enabling seamless integration, while top-down geoeconomic statecraft is promoting fragmentation. So much for the conventional wisdom that finance will simply become smoother, cheaper, and more globalized over time.

• 1.“Biggest risk with AI-RAN is repeating mistakes of 5G”, says SK Telecom

  SK Telecom warns telcos not to repeat their 5G mistakes with AI-RAN – while Optus considers how they should re-architect their infrastructure as “social networks for agents”. In sum –…

• 2.Foundational innovations shaping 6G: MIMO

  How MIMO continues to evolve for mobile connectivity in the AI era What you should know: Mobile data demand is entering a new phase. Video, XR and cloud services continue…

• 3.Japan’s operators test a new path for mmWave expansion

  KDDI, NTT Docomo, SoftBank, and Rakuten Mobile have recently signed a MoU to study the use of 5G mmWave infrastructure and technical architectures for coverage expansion In sum – what…

• 4.Everyone’s building AI infrastructure – who’s building the business? (Reader Forum)

  Telecom operators are pouring billions into AI infrastructure, but compute alone will not create lasting value. The bigger challenge is turning GPUs, models and AI platforms into commercially sustainable services…

• 5.AI-RAN cases start to stack (Telco Diary)

  From the newsletter (September 25; sign-up or follow if you want it sooner): Rakuten Mobile and T-Mobile offer tangible AI-RAN examples, embedding intelligence in network automation and distributed compute. Their…

• 1.Source Error

  Check Feed

• 1.Dynamic Task and Resource Scheduling Towards Space-Air-Ground-Sea Integrated Network

  In the context of 6G ubiquitous connectivity, the space-air-ground-sea integrated network (SAGSIN) emerges as a new paradigm for pervasive service provisioning. To support expanding maritime activities in infrastructure-scarce ocean areas, we propose an innovative dynamic task and resource scheduling approach for SAGSIN to deliver computing services for vessels. It integrates broad-coverage satellites, relay-capable high-altitude platform (HAP), energy-sufficient coastal base station (BS), and flexibly deployed uncrewed aerial vehicles (UAVs) to accommodate wide-area, highly mobile, and sustained maritime services. To address the challenge of task scheduling across four layers, a dynamic task offloading algorithm is developed. It steers task flows toward servers with light loads, strong computing capabilities, and high-rate links based on...

• 2.Adaptive Pilot Selection for Unified Semantic Communication and Semantic Sensing in ISAC

  Semantic communication (SemCom) and integrated sensing and communication (ISAC) are promising technologies for future 6G wireless networks. Existing studies have applied semantic technology to either the communication module or the sensing module of ISAC. In this work, we propose SemISAC, which performs both SemCom and semantic sensing within a single dual-function waveform. SemISAC uses a joint semantic encoder that extracts task-specific information for both communication and sensing. We evaluate SemISAC in a vehicular scenario in which vehicles share pixel-wise segmentation of the road environment and, through sensing, classify surrounding objects and estimate their ranges. On the transmitter side, a deep learning encoder converts the input road-scene image into semantic symbols and places them on the data cells of an OFDM grid, while ...

• 3.Structured Pose-Conditioned Flow Matching for Generative 5G CSI Augmentation

  With the growing demand for privacy-preserving and occlusion-resilient human pose recognition (HPR), 5G channel state information (CSI) offers a promising contactless sensing modality by integrating communication and sensing capabilities. However, collecting large-scale synchronized CSI-pose pairs remains costly in practical 5G systems. To address this limitation, we propose StructFlow-HPR, a structured pose-conditioned flow matching framework for generative CSI augmentation. StructFlow-HPR learns a continuous latent transport process from Gaussian noise to real CSI representations under pose guidance, while preserving the receiver-frequency topology of CSI through a reconstruction-preserving autoencoder. A pose-conditioned Transformer is further designed to model the latent velocity field and generate pose-aligned CSI samples via ordinar...

• 4.Dynamic Metasurface Antennas: From Programmable Microwave Hardware to Next-Generation Wireless Systems

  As wireless systems evolve toward 6G and beyond, antenna apertures are increasingly expected to become more programmable, multifunctional, and responsive to diverse communication, sensing, and imaging requirements. Dynamic metasurface antennas (DMAs) offer a promising hardware pathway toward this vision by integrating electronically addressable metamaterial elements within microwave and millimeter-wave (mmWave) radiating apertures. Unlike conventional phased arrays relying on dedicated phase-shifting networks, DMAs manipulate guided waves in microwave structures through electronically controlled resonant elements. In this way, DMAs offer phase-shifter-less beam-steering, multibeam radiation, and programmable wavefront control. This article explores state-of-the-art DMA technology from a microwave-engineering perspective, spanning guided-w...

• 5.Multi-Agent Orchestration of 3GPP Channel Estimators

  Pilot-aided channel estimation is a decisive block in orthogonal frequency-division multiplexing (OFDM) receivers for both 5G New Radio (5G-NR) and Long-Term Evolution (LTE). A large body of estimators exists, from simple least-squares (LS) interpolation to statistically optimal linear minimum-mean-square-error (LMMSE) variants and, more recently, deep convolutional denoisers, yet no single estimator is uniformly best: the winner depends on the propagation scenario, the numerology, the operating signal-to-noise ratio (SNR), the mobility (Doppler), and the antenna configuration. In this paper, we quantify this fact through a unified study of eight literature estimators evaluated over the 3GPP TR~38.901 Urban-Macro (UMa), Urban-Micro (UMi), and Rural-Macro (RMa) channels generated with NVIDIA Sionna, for both 5G-NR and LTE numerologies, in ...

• 1.No new articles

  Summary available at source link.

• 1.Same Text, Different Numbers: The Divergence of LLM-Based Measures

  Researchers increasingly use generative large language models (LLMs) to convert corporate text into empirical variables. We examine the extent to which LLM-based textual measures are invariant to model choice using thirteen measures, including sentiment, management clarity, uncertainty, answer specificity, and climate and political risk. Seven LLMs from different providers score earnings call transcripts of S&P 500 companies on these constructs. Cross-model rank correlations average only 0.52, and transcript-level differences common across providers account for only 34% of total score variation. Cross-model disagreement does not predict subsequent analyst or market disagreement, consistent with a substantial model-specific component rather than common ambiguity in the underlying disclosure. Model choice significantly affects downstrea...

• 2.Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms

  Summary available at source link.

• 3.Functional Architecture of European Electricity Trading Markets: Requirements for AI Supported Trading Systems under Regulatory Constraints

  European electricity trading in the EU operates as a constrained multi-layer system in which legal design, exchange microstructure, and network physics are executed jointly across forward, day-ahead, intraday, and balancing horizons. This paper develops a functional architecture for AI-supported trading that is aligned with market-coupling mechanics, cross-zonal transfer constraints, and compliance obligations under REMIT, MiFID II, MiFIR, and EMIR. The contribution is a formal system specification composed of a decision-state vector, residual-exposure accounting, constrained optimization objective, executable-action permission gate, and fail-closed AI control logic with auditable records. The analysis maps major Nominated Electricity Market Operator (NEMO) venues and related exchange operators into an operational venue topology and ident...

• 4.FedIncome: Federated Learning for Income Estimation in Digital Lending Under Data Sovereignty Constraints

  Verified income is often unavailable in digital loan applications, forcing lenders to rely on reported income and potentially leading to over-lending, overly conservative offers, or rejection of creditworthy applicants. Cross-institutional data-sharing constraints make this problem especially difficult for smaller lenders with limited training data. We introduce FedIncome, a federated learning framework for income estimation that enables institutions to train a shared model without pooling raw borrower records. Using more than one million LendingClub loans partitioned into $50$ state-level clients, we simulate a heterogeneous lending consortium. The best federated model achieves out-of-time $R^2=0.608$, compared with $0.619$ for a pooled centralised benchmark. Small-sample clients obtain an average out-of-time $R^2$ improvement of $3.8$ p...

• 5.Multi-Agent AI Architecture for Regulated Insurers: A generic AI framework under Solvency II and the AI Act in Austria and Germany

  This paper proposes a formal multi-agent architecture for implementing enterprise AI in regulated insurance firms, integrating economic theory with institutional design. The framework synthesises three core theoretical perspectives: Arrow's risk pooling theory to formalise risk transformation under uncertainty, Nash equilibrium to model strategic interactions between decision agents, and Principal-Agent theory to address incentive alignment under information asymmetry. The insurer is modelled as a constrained optimisation entity operating under solvency, legal, ESG, and operational boundaries, with specific focus on the regulatory contexts of Austria and Germany. The architecture decomposes the firm into multiple specialised agents, each representing distinct functional domains such as capital management, underwriting, claims processing, ...

• 1.Dynamic Task and Resource Scheduling Towards Space-Air-Ground-Sea Integrated Network

  In the context of 6G ubiquitous connectivity, the space-air-ground-sea integrated network (SAGSIN) emerges as a new paradigm for pervasive service provisioning. To support expanding maritime activities in infrastructure-scarce ocean areas, we propose an innovative dynamic task and resource scheduling approach for SAGSIN to deliver computing services for vessels. It integrates broad-coverage satellites, relay-capable high-altitude platform (HAP), energy-sufficient coastal base station (BS), and flexibly deployed uncrewed aerial vehicles (UAVs) to accommodate wide-area, highly mobile, and sustained maritime services. To address the challenge of task scheduling across four layers, a dynamic task offloading algorithm is developed. It steers task flows toward servers with light loads, strong computing capabilities, and high-rate links based on...

• 2.Adaptive Pilot Selection for Unified Semantic Communication and Semantic Sensing in ISAC

  Semantic communication (SemCom) and integrated sensing and communication (ISAC) are promising technologies for future 6G wireless networks. Existing studies have applied semantic technology to either the communication module or the sensing module of ISAC. In this work, we propose SemISAC, which performs both SemCom and semantic sensing within a single dual-function waveform. SemISAC uses a joint semantic encoder that extracts task-specific information for both communication and sensing. We evaluate SemISAC in a vehicular scenario in which vehicles share pixel-wise segmentation of the road environment and, through sensing, classify surrounding objects and estimate their ranges. On the transmitter side, a deep learning encoder converts the input road-scene image into semantic symbols and places them on the data cells of an OFDM grid, while ...

• 3.Dynamic Metasurface Antennas: From Programmable Microwave Hardware to Next-Generation Wireless Systems

  As wireless systems evolve toward 6G and beyond, antenna apertures are increasingly expected to become more programmable, multifunctional, and responsive to diverse communication, sensing, and imaging requirements. Dynamic metasurface antennas (DMAs) offer a promising hardware pathway toward this vision by integrating electronically addressable metamaterial elements within microwave and millimeter-wave (mmWave) radiating apertures. Unlike conventional phased arrays relying on dedicated phase-shifting networks, DMAs manipulate guided waves in microwave structures through electronically controlled resonant elements. In this way, DMAs offer phase-shifter-less beam-steering, multibeam radiation, and programmable wavefront control. This article explores state-of-the-art DMA technology from a microwave-engineering perspective, spanning guided-w...

• 4.A DRL-Driven Optimization of RAN Slice Resource Partitioning for V2X SLA Compliance in 5G Networks

  Vehicle-to-Everything (V2X) communications impose very demanding requirements in terms of latency and reliability, which must be met in scenarios where multiple services with diverse performance targets coexist. In such scenarios, traffic-intensive services compete for limited radio resources, complicating the fulfillment of V2X service demands. Within this context, Network Slicing (NS) emerges as a key factor that enables the creation of multiple slices and the allocation of resources among them to satisfy heterogeneous service requirements. In particular, this work addresses the Radio Access Network (RAN) slicing problem from the perspective of Physical Resource Block (PRB) partitioning under high traffic demand conditions. To this end, a reinforcement learning approach based on Proximal Policy Optimization (PPO) is proposed to determin...

• 5.Evolving Inspectable O-RAN Slicing xApps with LLMs

  Open RAN (O-RAN) slicing xApps must adapt resource allocations to changing channel conditions and traffic demands while meeting service-level agreements (SLAs). Deep reinforcement learning can produce adaptive policies, but their allocation rules remain encoded in neural-network parameters. Our goal is to retain this adaptability while making the controller's decision logic directly inspectable and editable by operators. We use a large language model (LLM) to evolve slicing controllers as compact Python programs whose decision logic remains readable and editable after optimization. The LLM proposes and revises candidates offline, while a calibrated simulator scores them, and the selected decision module runs unchanged in the O-RAN control path. On the NSF POWDER 5G testbed, the evolved controller releases resources from a guaranteed slice...

• 1.Dynamic Task and Resource Scheduling Towards Space-Air-Ground-Sea Integrated Network

  In the context of 6G ubiquitous connectivity, the space-air-ground-sea integrated network (SAGSIN) emerges as a new paradigm for pervasive service provisioning. To support expanding maritime activities in infrastructure-scarce ocean areas, we propose an innovative dynamic task and resource scheduling approach for SAGSIN to deliver computing services for vessels. It integrates broad-coverage satellites, relay-capable high-altitude platform (HAP), energy-sufficient coastal base station (BS), and flexibly deployed uncrewed aerial vehicles (UAVs) to accommodate wide-area, highly mobile, and sustained maritime services. To address the challenge of task scheduling across four layers, a dynamic task offloading algorithm is developed. It steers task flows toward servers with light loads, strong computing capabilities, and high-rate links based on...

• 2.Packet iSlip

  This paper examines input/output buffered crossbar switches under combined packet and cell data. Our switch architecture uses input buffering with Virtual Output Queues to avoid Head of Line Blocking. The switch fabric is a crossbar with no speedup. We use a modified iSlip [McKeown] crossbar scheduler geared towards packet data, called piSlip. Cell ports are largely unmodified from standard iSlip behavior. For packet output ports, we introduce changes to the grant pointer which minimizes output latency caused by packet reassembly. Our model uses several output states, including packet cut-through. From simulation results, we show that piSlip with virtual cut-through offers latency characteristics significantly better than unmodified iSlip with similar packet port interfaces. Simulation further shows that piSlip and iSlip have similar maxi...

• 3.A DRL-Driven Optimization of RAN Slice Resource Partitioning for V2X SLA Compliance in 5G Networks

  Vehicle-to-Everything (V2X) communications impose very demanding requirements in terms of latency and reliability, which must be met in scenarios where multiple services with diverse performance targets coexist. In such scenarios, traffic-intensive services compete for limited radio resources, complicating the fulfillment of V2X service demands. Within this context, Network Slicing (NS) emerges as a key factor that enables the creation of multiple slices and the allocation of resources among them to satisfy heterogeneous service requirements. In particular, this work addresses the Radio Access Network (RAN) slicing problem from the perspective of Physical Resource Block (PRB) partitioning under high traffic demand conditions. To this end, a reinforcement learning approach based on Proximal Policy Optimization (PPO) is proposed to determin...

• 4.Knowledge Distillation for Intelligent Softwarized Networks: Advances and Open Challenges

  The increasing adoption of software defined networking and network function virtualization, combined with rapid advances in Machine Learning (ML), is driving the evolution toward intelligent network softwarization across cloud, edge, and distributed environments. However, deploying complex learning models in such heterogeneous environments introduces challenges in latency, computation, and energy consumption. Knowledge Distillation (KD) has emerged as a promising approach to enable lightweight and efficient intelligence by transferring knowledge from high-capacity teacher models to compact student models. Despite its extensive study in general ML domains, the integration of KD into intelligent softwarized networks remains fragmented and underexplored. In this paper, we review and classify recent efforts that incorporate KD within softwari...

• 5.Virtual Backhaul Connectivity for Enhanced Coverage in Fiber-Less Areas

  This article provides an overview of potential alternatives for providing wireless backhaul in regions that suffer from the lack of fiber optic-connectivity to the core network. These regions can be rural and remote locations, low-income neighborhoods in urban and suburban regions, and post-disaster locations suffering from the destruction of cellular infrastructure. For these scenarios, extending fiber optic cables to such locations might be extremely expensive, impractical, or simply not feasible. Hence, in order to enhance the backhaul connectivity in these scenarios, we study the potential and applicability of the integrated access and backhaul (IAB) technique, and a hybrid combination of IAB and non-terrestrial networks (NTN) that includes high/low altitude platforms (HAPs/LAPs) and low earth orbit (LEO) satellites. We conclude this ...