Babak's Daily Briefing

Monday, October 12, 2026

Sources: 17 | Total Articles: 70

More Developments

• 3.Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents

  LLM-based agents are entering decision-support roles in defence staff work, where the obligations they must respect are already written down and binding, and where retraining is not available as a control because models arrive as procured components. What can be placed under engineering control is the interface between the agent and the systems it acts on. Those obligations are at once spatial, temporal and text-semantic, and a violation typically lives in the composition of a multi-step interaction, which is why per-event guardrails miss sequential tool-attack chains. We present a multi-aspect runtime-verification framework that decomposes a natural-language policy clause into a typed spatial/temporal/semantic triple over one canonical event stream, checks each aspect with its own monitoring specification, and fuses the verdicts through ...

• 4.Wiki-Talkie: Multilingual Benchmarking of Persona-Based Agents on Real-World Discussions

  LLMs are increasingly deployed as autonomous agents in social environments, making it critical to study their ability to faithfully simulate human interactions. Central to this is grounding agents in realistic user personas, yet existing datasets rely on fictional personas and are limited to a handful of languages, lacking the empirical grounding necessary to evaluate behavioral fidelity across diverse populations. We introduce Wiki-Talkie, a multilingual dataset of real-world conversations from Wikipedia Talk pages across five languages spanning two language families: Germanic (German, English) and Romance (Spanish, French, Italian), paired with personas derived from real user communities and encompassing sociodemographic attributes, self-descriptions, and behaviorally grounded interaction traits. Using Wiki-Talkie, we evaluate agent int...

• 5.Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference

  LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare. The agents are typically heterogeneous, each holding a private preference that it pursues but does not reveal. Inferring such hidden preferences from behavior has been a subject of long-standing research in game theory and multi-agent systems. The core challenge lies in maintaining a belief over every agent's preference and updating it from the agents' observed actions. Existing LLM orchestrators carry that belief as prompt text with no explicit update rule. This lets early errors persist and propagate rather than be corrected. We therefore propose \textbf{HARP} (Heterogeneous-preference Agent oRchestration via Preference inference), a novel framework that moves the belief out of the prompt. S...

• 1.AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits

  arXiv:2610.12545v1 Announce Type: new Abstract: Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning. Diffusion LLMs partially mitigate this limitation but still cannot flexibly insert or remove arbitrary numbers of tokens from a pre-generated context. We design AutoIndexer as a generative model with a novel training and decoding mechanism that simulates a Chain of Edits, allowing the model to flexibly modify its prior outputs in hindsight via token insertions, substitutions, and deletions. The model learns to predict marker tokens for opening and closing edits, simultaneously moving a cursor to positions in the existing token sequence, analogous to a text editor. Training sequences are obtained ...

• 2.SWE-Duel: Towards a Self-Scaling Arena for Coding Agents

  arXiv:2610.12569v1 Announce Type: new Abstract: Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead aim to be self-scaling: its tasks and oracles are created at evaluation time, so no content exists in advance to leak, and its difficulty is set by the participating agents rather than fixed at release. We introduce SWE-Duel, an arena in which two coding agents evaluate each other over mirrored Red-Blue turns. In each turn, the Red agent works on a real repository across three context-isolated sessions. It proposes and implements a new feature with feature tests, then embeds a subtle bug in that feature along with sealed bug-triggering tests. The resulting pull request is admitted only if (1) it passes the featur...

• 3.Contextual Correction of Parallel Draftsfor Speculative Decoding

  arXiv:2610.12570v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones provide strong predictions, while drafting multiple future positions in parallel avoids the sequential cost of autoregressive generation. This parallelism, however, comes at a cost. Tokens within a draft block are predicted without access to the realized identities of preceding draft tokens, removing intra-block dependencies that would naturally be available under autoregressive generation. We introduce DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores these dependencies ...

• 4.CLUE: A Contrastive Learning Framework for Unsupervised Event Type Induction and Annotation

  arXiv:2610.12580v1 Announce Type: new Abstract: Event ontology is the foundational framework for defining events in a dataset. Event type induction generally involves domain experts who define guidelines for creating event types and their names based on the dataset's domain and scope. However, this process is resource-intensive in terms of annotation costs and is prone to human biases. To alleviate the need for manual event ontology creation, we propose the CLUE framework for event type induction, naming, and annotation. Our main contributions in this work are: 1) designing a novel joint embedding representation for expressing both the verb-centric view and the semantic view of events; 2) event type induction using contrastive loss guided clustering; 3) event naming and refinement. Experiments demonstrate the effectiveness of our method....

• 5.One Model to Loop Them All: Elastic Latent Recurrence for Language Models

  arXiv:2610.12582v1 Announce Type: new Abstract: A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a non-recurrent model of the same size, a one-loop tax that makes a separate non-recurrent model the better choice whenever latency matters. We present Elastic Latent Recurrence (ELR), a recipe for training looped language models without this tax. At one loop, an ELR model costs the same to serve as a non-recurrent model of the same size and, trained on the same data, reaches similar accuracy. Each additional loop then buys more accuracy for more inference compute. Three choices make this work: a gated state update with a learned step size, loop counts mixed within ...

• 1.Algebraic Integer Quantization for Machine Learning Applications

  arXiv:2610.12494v1 Announce Type: new Abstract: In this article, we propose algebraic integer number formats (AINF) as a framework for highly configurable and accurate compressed computation. A key property of AINF is its straightforward reduction to purely integer arithmetic, enabling error-free multiply-accumulate operations. We develop a matrix multiplication engine that exploits this property, obtaining performance within a predictable factor of the most efficient numerical counterparts on modern hardware accelerators. Another key advantage of AIQ is the freedom to select algebraic integers tailored to the numerical characteristics of a given use case, offering optimization opportunities that are fundamentally unavailable in floating-point or fixed-point formats. Motivated by these properties, we introduce algebraic integer quantizati...

• 2.Kairos: Toward a Byte-Level Foundation Model for Every Modality

  arXiv:2610.12495v1 Announce Type: new Abstract: Small language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-DeltaNet linear attention and sliding-window attention over shared projections (LiZAttention2), block-wise Attention-Residual aggregation, a sparse Mixture-of-Experts (MoE) feed-forward layer and a multi-scale byte-level codec, trained with a uniform-noise denoising objective over one byte space shared by text, image, audio, video, lidar and control streams; this report asks whether the combination optimizes at all before asking whether it is useful. We give code-derived algorithms for each component, including a cross-session recurrent-state memory gate, then run convergence sanity checks: overfittinga single 440-byte sentence at 1--15M parameters,...

• 3.An Input-Dependent Readout Phase for Resonant Sequence Models

  arXiv:2610.12496v1 Announce Type: new Abstract: Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives content-dependent memory at the cost of FFT-based training, while a fixed transition keeps the O(T log T) convolutional path but reads memory the same way for every input. ResonatorLM, a recent model of the second kind, reads a bank of damped complex oscillators through a fixed learned phase per head. We make that readout phase a function of the current token, which adds input dependence to the read only, keeps the convolution exact, and costs 0.2 percent more parameters. An analysis of the untrained bank shows that phase does encode elapsed time, but an ordinary token falls below the background within 2-8 steps and no choice of damping extends li...

• 4.CircuitTree: Composing Circuits into A Syllable Transcriber

  arXiv:2610.12520v1 Announce Type: new Abstract: The goal of circuit discovery is to decompose a monolithic neural network into tiny modular subnetworks which are interpretable in the sense that each does an identifiable subtask. We develop a practical method for composing arbitrarily many circuits into a single model. We propose a greedy, density-scaled composition algorithm that overcomes limitations of previous attempts to compose circuits by naive union, then generalize it to $N$ circuits via CircuitTree, a new data structure built on a $\Theta(N\log N)$ tree-compose schedule. We compose circuits pruned from HuBERT for classifying individual phonemes into a syllable classifier, a capability none of the 39 phoneme circuits has individually. Chaining CircuitTrees into a hierarchy-of-circuits pipeline, we transcribe open syllables at 64.8...

• 5.Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights

  arXiv:2610.12527v1 Announce Type: new Abstract: Distribution operators need visibility of behind-the-meter photovoltaic (PV) generation, yet most residential customers are observed only through net smart meters. Deep-learning-based PV disaggregation can restore this visibility, but its operational value depends on whether the model serves known customers, new customers, future periods, or new regions. We quantify this dependence using four deployment regimes that separate household transfer from temporal extrapolation, applied to Ausgrid smart-meter data with cross-dataset adaptation to the Pecan Street data. Using a fixed training protocol, we benchmark representative deep sequence architectures for PV disaggregation under regime-matched evaluation. At a fixed 48-hour context length, daylight mean absolute error (MAE) of the best model r...

• 1.Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback

  arXiv:2610.12549v1 Announce Type: new Abstract: Embodied coding agents construct robot policies from natural-language instructions by generating executable programs and refining them from execution feedback. This refinement assumes that execution feedback reveals whether the task succeeded and, after a failure, provides sufficient evidence to guide program revision. Aerial manipulation violates this assumption in two ways. Payload constraints restrict onboard camera coverage and leave task-critical outcomes outside the robot's view (partial observability), while strong dynamic coupling and limited control margins make physical interactions fragile (limited interaction robustness) and leave failure causes unresolved. Re-examining the same feedback cannot recover observations that were never collected or separate failure causes that the ava...

• 2.PanTact: Teaching Whole-Body Dexterity with a Wearable Contact Interface

  arXiv:2610.12558v1 Announce Type: new Abstract: Humanoid robots have many degrees of freedom and contact surfaces, yet most loco-manipulation research restricts manipulation to the hands and avoids other body contacts with the environment. To extend manipulation beyond the hands, we present PanTact, a system that learns humanoid whole-body dexterity, the capability to manipulate with any suitable body surface, directly from robot-free human demonstrations. Our key idea is to use contact as manipulation-centric information that transfers across embodiments. Contact locations and timing specify the interactions needed to accomplish a task, while the robot chooses how to coordinate its body to realize them within its own physical constraints. Specifically, PanTact captures, learns, and executes whole-body contact via: 1) a wearable, robot-fr...

• 3.What Should Embodied Agents Remember? Benchmarking and Evaluating Memory Modality for Embodied Agents

  arXiv:2610.12561v1 Announce Type: new Abstract: Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks and the model inference costs of constructing and using memory. We introduce MeMoREval, a benchmark for studying this problem through a controlled experience-request protocol. Agents first experience a sequence of events without knowing the subsequent tasks, and subsequently they use memory to respond to information and action requests without receiving new observations. The benchmark comprises 53 tasks across four simulated indoor environments and measures task success alongside...

• 4.CASTER: Formalizing Zero-Shot Manipulation from Synthetic Videos as Constrained Optimization

  arXiv:2610.12567v1 Announce Type: new Abstract: Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can now prompt these generators to make synthetic videos of the task. On the plus side, these synthetic videos take place in the robot's current environment, and do not require actual human teaching. However, while the generated videos appear to show plausible motions, they lack both physical consistency and robot grounding, and thus the robot cannot directly roll out the trajectory shown by the video. In this paper we seek to formalize the process of going from synthetic video generation to real-world robot trajectories for zero-shot manipulation tasks. We recognize that this problem is an instance of constrained optimization. The object trajector...

• 5.Graph-Based Heuristics for Minimum Constraint Removal in Cluttered Robot Motion Planning

  arXiv:2610.12609v1 Announce Type: new Abstract: Humanoid and service robots operating in clut- tered human environments may encounter motion planning problems that are infeasible when all surrounding objects are treated as fixed obstacles. The Minimum Constraint Removal problem, which we refer to as MCR, addresses this situation by identifying the minimum number of constraints, such as movable objects, whose removal enables a collision-free path. However, computing an optimal MCR solution is NP-hard. In this work, we propose a graph-based heuristic pipeline that combines bidirectional feasible-set generation with fixed- length searches over reduced MCR graphs. We further derive an extended feasible-set generator for instances in which the candidates produced by the first generator do not contain a complete optimal removal set. Across six ...

• 1.CorrFlow: Exact and Permutation-Equivariant Flow Matching on the Correlation Elliptope

  Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry. Their generation therefore involves two distinct problems. First, every output must remain on the correlation elliptope, irrespective of how its variables are ordered. Second, the generator must learn the domain-specific distribution occupied by empirical data inside that valid space. Existing financial image generators mix these problems: they learn ordered matrix entries and repair invalid draws afterward. We introduce CorrFlow, which separates them. A generalized Fisher transform maps full-rank correlation matrices bijectively to unconstrained coordinates, guaranteeing valid outputs without projection. A graph flow-matching network learns the empirical distribution in those coordinates and is permutation equivar...

• 2.$L_0$ Feature Selection via Monte Carlo Tree Search in High-Dimensional Financial Regression

  Feature selection is a central problem in high-dimensional financial regression, where large numbers of engineered variables and strong correlations among predictors reduce model stability and interpretability. $L_1$ regularization (Lasso) is widely used for sparse regression, but its shrinkage can be restrictive when informative signals are spread across correlated variables. Exact sparse regression avoids this shrinkage but requires solving a combinatorial optimization problem that is computationally difficult and is typically fit to minimize in-sample rather than out-of-sample error. This paper presents a feature selection framework based on Monte Carlo Tree Search with Generalized Nested Rollout Policy Adaptation (GNRPA). Feature selection is formulated as a sequential decision process, and candidate subsets are scored by their out-of...

• 3.A Distributional Framework for Behavioral Characterization and Risk Management of Large Language Models

  Large language models are stochastic by nature. Repeated executions under the same experimental conditions may produce different responses. We propose a framework that can be applied across the model lifecycle, from task design to residual behavior and continuous monitoring. The method consists of building an empirical response distribution estimated through Monte Carlo simulation. Semantic interventions are introduced to study how these distributions change. We illustrate the framework with two different tasks, borrower classification and music album recommendation, and quantify the resulting distributional changes. The framework is linked to model risk management and governance by measuring robustness and control effectiveness, and characterizing residual behavior. Since it relies only on observed responses, it can also be applied to bl...

• 4.Market Impact Estimation via Causal Foundation Models

  When a trader executes a large order, the relevant question is not \emph{what will the price be?} but \emph{what would the price have been had I not traded?} Market impact is thus a causal quantity, yet classical models (Almgren--Chriss, propagators) regress price on flow, which is biased whenever informed flow moves prices through information as well as trading. We present a proof-of-concept \emph{Causal Market Simulator}: a continuous-time causal prior-data fitted network (PFN) trained on a synthetic market prior in which a hidden informational flow confounds the flow--price relation by construction, with confounding strength an exact per-episode knob. On this prior, the naive estimator's bias follows a closed form we confirm empirically (up to 68\% overestimation), while the PFN tracks the unbiased true-parameter oracle at high confoun...

• 5.Deep Learning vs. Statistical Models for Multi-Horizon Price Forecasting of Second-Hand Electronics: A Systematic Benchmark

  Forecasting resale prices of used electronics is critical for subscription-based platforms where pricing errors translate directly into risk. Unlike structured financial markets, second-hand electronics exhibit high volatility, sparse listing histories, and non-normal price dynamics - yet no systematic time-series benchmark exists for this domain. This paper presents the first multi-horizon benchmark of statistical and deep learning forecasting models for used electronics price prediction. We use a large-scale dataset of daily price listings from Polish online marketplaces (January 2022 to March 2025, 100+ smartphone and laptop models) and evaluate eleven models across six horizons from 1 to 365 days, covering classical methods (ARIMA, ETS, Theta), recurrent and convolutional networks (LSTM, TCN), and modern deep architectures (N-BEATS, N...

• 1.GSMA Reports: India’s Next Digital Chapter Must Turn Scale into Economic Growth and Trust

  Summary available at source link.

• 1.Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing

  Semantic query engines ask a large language model (LLM) to judge individual rows, and benchmarks compare these engines on the quality of a few executions at temperature 0. We measure how much another execution changes. We re-execute the text and tabular workloads of SemBench, LRO-Bench, and UDA-Bench through their own harnesses, log every one of 1.2 million model calls, and reanalyze SemBench's published executions. At temperature 0, between 0.07% and 10.2% of rows change their operator output over five executions, depending on the model, and up to 24.0% on one task. Plans amplify these changes exponentially in the number of rows an answer exposes, as a possible-worlds model predicts: on UDA-Bench, a few percent of extracted values change, but about two thirds of the answers do. In SemBench's published results, 21% of text results change ...

• 2.Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction

  Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune an LLM to generate revisions or feedback, we learn where to intervene in failed rollouts and determine how to redirect them. To choose where to intervene, we train a 130K-parameter MLP head on a frozen encoder using only final-answer correctness. For redirection, we find that under a fixed generation budget, the tested inline injections fail to reliably redirect reasoning, whereas presenting the same instruction in a new user turn changes the model's course. The resulting correction framework, UPTURN (User-Prompt TURN injection at a learned position), requires no LLM fine-tuning: it retains a selected prefix, injects an instruction as a new user turn, and regenerates the suffix. Across four r...

• 3.Agentic Large Language Models

  Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has made them a favorite tool for writing, answering questions, and much more. Their answers already influence our decisions and our actions. What would happen if LLMs themselves could act in the world directly? What would happen if LLMs could interact with each other? Agentic LLMs combine the power of large language models with the ability to act in the real world. In this book we will discuss how agentic LLMs work, how they act, how they interact, and what this means for us, as users.

• 4.Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits

  Reinforcement learning (RL) has emerged as a key paradigm for improving large language model (LLM) agents, enabling stronger reasoning, planning, and tool-use in interactive environments. However, existing agent RL methods remain fundamentally constrained by an on-policy reasoning bottleneck: when tasks exceed the model's current capability boundary, effective trajectories become extremely sparse and training often collapses. We introduce Rollout-Time Intervention (RTI), a technique designed to elicit successful trajectories beyond the policy's intrinsic exploration capacity. RTI operates by leveraging reward-side evidence (i.e., evaluation rubrics) during rollout to convert erroneous trajectories into successful ones, providing effective learning signals for tasks that the policy rarely solves on its own. Although intervention trajectori...

• 5.MoPrO-SD: Modular Prompt Optimization for Stance Detection

  Stance detection remains challenging for large language models (LLMs) due to implicit opinions, sarcasm, and context-dependent expressions of stance. Although automatic prompt optimization offers an alternative to fine-tuning without updating model parameters, existing structured approaches are not specifically designed around stance-label semantics and class-specific ambiguities. We introduce MoPrO-SD, a stance-specific prompt optimization framework that decomposes prompts into functional semantic modules and refines them sequentially using LLM-based feedback. We study three refinement strategies: instruction-only optimization (I), instruction with reasoning (I+R), and instruction with per-example reasoning (I+R+E), using class-conditioned errors for stance-label refinement. We also introduce VaccineStance, a new human-annotated benchmar...

• 1.Multi-Stream Attention Residuals

  Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth axis. Inspired by the success of multi-head attention along the sequence axis, we introduce Multi-Stream Attention Residuals (MSAR), an extension of AttnRes that generalizes this mechanism to multi-head depth attention, yielding substantial performance gains with minimal additional overhead. MSAR draws stream diversity from sequence context through multi-scale causal convolutions, allowing different heads to retrieve historical representations through distinct contextual views while preserving the integrity of the hidden representation. The retrieved streams are combined through lightweight adaptive mixing to generate the single-stream layer input. By retaining single-stream sources a...

• 3.PDE-PFN: Prior-Data Fitted Neural PDE Solver

  Motivated by the success of large language models (LLMs) with broad generalizability and robustness to noisy or unreliable pre-training data, we explore in-context prediction of PDE solution fields using approximate pre-training data. In addition, inspired by the posterior predictive mean-based inference mechanism of the in-context learning in prior-data fitted networks (PFNs), we propose PDE-PFN, a prior-data fitted neural solver that approximates the posterior predictive mean of PDE solutions via in-context learning. PDE-PFN builds on a PFN architecture with self- and cross-attention mechanisms of Transformer and is pre-trained on noisy approximate solutions generated by physics-informed neural networks, serving as diverse but not necessarily exact priors. Through experiments on a range of two-dimensional PDEs, we demonstrate that PDE-P...

• 4.DAG Structure Learning with Node-Varying Heavy-Tailed Disturbances

  DAG structures can be learned from observations by incorporating acyclicity via smooth constraints, such as DAGMA's log-determinant function. Typically, observations and the underlying DAG are related through linear structural equation models, with Gaussianity assumption on the disturbances at each node. Extending DAG learning methods that account for scale and tail behavior of disturbances that vary across nodes remains a challenge. We propose a node-varying Student-$t$ DAGMA that jointly estimates the graph structure, node-specific disturbance scales, and the degrees-of-freedom parameter. A Gaussian scale-mixture representation yields an iteratively reweighted formulation that down-weights large standardized residuals. Building on existing results, we also establish identifiability of the graph and disturbance parameters. Synthetic expe...

• 5.Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers

  In this paper, we propose Data-Adaptive Mahalanobis Cross-Head Attention (DAMCHA), a simple and effective attention mechanism that generalizes Multi-Head Attention (MHA) through the lens of metric learning. Standard MHA implicitly learns a static, head-wise Euclidean similarity corresponding to the diagonal blocks of a unified cross-head metric matrix, discarding all off-diagonal interactions across heads. DAMCHA addresses this limitation via two key innovations. First, it learns the full cross-head metric matrix, inducing a Mahalanobis-like similarity that explicitly captures inter-head interactions beyond the restricted block-diagonal structure of MHA. Second, it parameterizes the metric matrix as an input-dependent function, enabling the attention geometry to dynamically adapt to the intrinsic manifold structure of the data rather than...

• 1.Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy

  If you’ve ever wondered how Claude and similar AI agents can answer complex questions in seconds and where they get the information, you’re not alone. Gurmeet Saran works to find that answer every day as an engineer at Anthropic in San Francisco, the AI research company behind Claude. The IEEE senior member is developing an infrastructure to understand the mechanics behind the chatbot’s behavior and to ensure its underlying architecture produces reliable outputs. Gurmeet Saran Employer Anthropic in San Francisco Title Member of technical staff Member grade IEEE senior member Alma maters University of Kalyani, in India; Birla Institute of Technology and Science, in Pilani, India “My job is to make sure the data is accurate, structured, and trustworthy, and that private data stays private,” he says. “As I learned earlier in my career, priva...

• 2.Learning to Play Like a Pro: Adaptive Motion Planning and Tracking for Humanoid Robots

  This White Paper provides roboticists and control engineers with a comprehensive overview of how motion planning and motion tracking can be decoupled to preserve professional athletic style in humanoid robots, and why adaptive, speed-aware control is essential for closing the gap between simulation and real-world deployment. What you will learn about: Why combining a professional athlete’s motion style with reliable task performance remains an open challenge in humanoid ball-sports robotics, and how separating a high-level planner from a low-level tracker addresses this trade-off. How motion data extracted from broadcast video and motion-capture recordings can be reconstructed, retargeted, and physically corrected into reference motions a humanoid robot can safely track. Why the sim-to-real transition introduces compounding tracking error...

• 3.Master AI Chip Principles With New IEEE Design Program

  Today’s engineers face an unprecedented acceleration in AI hardware complexity, as explained in the recent research article “ Revisiting Edge AI: Opportunities and Challenges .” The article examines the rapid growth of edge AI and the challenges it creates, including resource constraints, model architecture limitations, and network demands across edge-AI deployments. The acceleration is driven by a fundamental shift in how modern AI models are built and scaled. As the models have become much larger and more complex, they are computationally more demanding because they contain more parameters and require more calculations. To meet the demands of scaling deep neural networks, the industry is increasingly developing AI chips that are designed for specific tasks. One major reason is that moving data between memory and the processor has become...

• 4.The U.S. Nuclear Plant Fleet Is Leaning Into AI

  If there is any place that would be off-limits to AI, the control room of a nuclear power plant certainly sounds like one. The nuclear industry is historically cautious and risk averse—understandable given the possible catastrophic consequences of an accident or a mistake. Even well-trained managers struggle with the operational complexity of a nuclear reactor. It’s not the kind of setting that seems well suited to a powerful but error-prone new technology. Reality tells a startlingly different story. A variety of companies have begun to offer AI solutions for nuclear power. This year, nearly the entire fleet of 94 U.S. nuclear reactors has been offered the chance to integrate AI into its operations, and most have taken it. In August, California-based Atomic Canyon launched NIVA , the Nuclear Industry Virtual Assistant, which was develope...

• 5.HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object Interaction

  This White Paper gives robotics researchers and engineers an overview of a new large-scale motion capture dataset built to close the data gap limiting humanoid robot learning. It also shows how policies trained on the dataset transfer to a real humanoid robot. What you will learn about: Why humanoid robot learning, a central problem in embodied AI and Physical AI, needs data that internet video and existing motion capture datasets cannot provide. How FrameNet , a linguistic framework for human action, can guide motion capture collection to systematically cover a broad range of whole-body motion. Why synchronized object trajectories and meshes make human-object interaction data useful for teaching robots real-world tasks such as carrying, pushing, and pulling. How reinforcement learning policies trained on this motion capture data improve ...

• 1.Michael Woodford, Nobel Laureate

  I think of Michael Woodford as the kind of economist who studies something very specific very intensively and tries to get it just right.  But in his case he is not studying something small and irrelevant, he is studying “monetary policy.” I think of him as the economist who put monetary policy and “monetarism” — […]

  The post Michael Woodford, Nobel Laureate appeared first on Marginal REVOLUTION.

• 2.Robert E. Hall, Nobel Laureate

  Alex has already covered this, I will add a few remarks. First, every Bob Hall paper is interesting!  Only a handful of economists can say the same.  Every paper has an idea, and some sort of novel contribution.  His lesser-known papers can be as thought-provoking as the more famous ones. Here is Bob on scholar.google.com.  […]

  The post Robert E. Hall, Nobel Laureate appeared first on Marginal REVOLUTION.

• 3.The Nobel Prize Goes to Robert Hall and Michael Woodford

  Twenty-five years ago Tyler told me he thought Robert Hall should win the Nobel. He has been a contender for so long today’s award was a surprise! Hall has an unusual number of unexpectedly creative papers. His best known is on consumption. Start with the textbook Keynesian model: Y = C + I + G […]

  The post The Nobel Prize Goes to Robert Hall and Michael Woodford appeared first on Marginal REVOLUTION.

• 4.Michael Woodford Wins Nobel

  No one since Milton Friedman has done more to shape how central bankers think about their jobs than Michael Woodford. Woodford’s Interest and Prices (2003) has been called the central bankers’ bible. If you have read a speech by a Fed governor in the last twenty years you have read Woodford, even if his name […]

  The post Michael Woodford Wins Nobel appeared first on Marginal REVOLUTION.

• 1.Prices, Prices, Prices: Overall Inflation and the Costs You Care About

  As fall starts to show itself in cooler weather, I want to discuss a topic that usually raises temperatures: inflation. Like a budget-conscious consumer, the Federal Reserve is highly attuned to changes in the price of goods and services; minimizing such swings is one of the Fed’s primary duties, after all. But how does the Fed’s view of prices differ from that of a consumer? And how does the Fed go about stabilizing prices writ large when it lacks the ability to set prices directly? In this post, I explore that apparent paradox from the perspective of a central banker (though I remain a budget-conscious consumer when off duty).

• 2.AI Adoption and Employment Expectations: Evidence from a Survey of Small Business Owners

  There is little consensus on the effect of AI adoption on employment. Economy-wide measures of pay and headcount have moved little even as AI adoption has spread rapidly, yet narrower measures document declining hiring for workers at the start of their careers or in AI-exposed occupations. In this post, we revisit this topic for U.S. small businesses. We use data from the 2025 Small Business Credit Survey (SBCS) to examin...

• 3.Firm Heterogeneity and the Response of Investment to Monetary Policy

  It is well known that monetary policy affects firms’ investment decisions. But which firms are the most responsive to changes in interest rates? And does this responsiveness vary over time? The literature has given diverse answers to this question, focusing on characteristics such as firm size, age, and financial position, and mostly studying these traits in isolation. In this post based on a recent Staff Report, we explore how investment responsiveness to monetary policy changes across firms and over time. We find that investment by most firms in most time periods responds little to monetary policy. For some firms in some periods, however, investment is very responsive to changes in interest rates. While these instances of strong sensitivity correlate with several fir...

• 4.How Fast Do Tariffs Pass Through into Consumer Prices?

  There has been a lot of interest in how tariffs affect consumer prices (for example, Cavallo et al. 2021, 2025). In this post, we present results from our new research paper that estimates the effects of the 2025-26 tariffs on retail consumer prices. We find that for every percentage point increase in average tariffs, consumer goods prices increase by about a quarter of a percent after one year. Roughly two-thirds of the effect arises because tariffs raise the prices of imported consumer goods. The remaining third arises indirectly: tariffs increase the prices of goods made in the U.S. because producers pay more for imported par...

• 1.Will the Bardella Scandal Sink Le Pen?

  The scandal over antisemitic comments made by the far-right National Rally's Jordan Bardella could die down quickly, enabling Marine Le Pen to stick to her current plan: win the 2027 presidential election and name Bardella her prime minister. But there are two other possible scenarios, neither of which would be good for Bardella.

• 2.Can China and America Handle Being Ordinary?

  For at least a generation, China's "economic miracle" allowed its people to look at Americans not as inhabitants of a richer world, but as potential peers. But now the two societies are peers in a different sense, because the Chinese are increasingly suffering the same rude awakening that Americans did when their own miracle ended.

• 3.How to Improve Global Mineral Governance

  The race to secure critical minerals has intensified at the same time as the international community has recognized the need for more sustainable and responsible mining practices. Translating the resulting frameworks and guidelines into concrete action will require consolidating Global South policy and advocacy networks.

• 4.A Global Debt Crisis Is Looming

  After a decade of debt accumulation, higher interest rates and growing refinancing needs have left the global economy increasingly exposed to shocks. And now ongoing conflicts are driving up energy prices, fueling renewed inflationary pressures and revealing dangerous cracks in the existing debt architecture.

• 5.Europe Must Look Beyond the US and China to Solve Its Productivity Problem

  Given America and China’s lead in AI and other cutting-edge innovations, it is not surprising that much of the European economic policy debate revolves around the need to emulate and catch up with these two technological superpowers. In fact, neither the US nor China offers a relevant or attractive model for Europe.

• 1.Stuck in the basement – where European fiber goes to stall (Analyst Angle)

  European fiber networks pass millions of apartment buildings, but subscriber take-up remains stubbornly low in several major markets. Maravedis examines why building density alone fails to drive adoption, and where…

• 2.A peak inside Vodafone Business – a very British telco AI strategy? (Telco Diary)

  From the newsletter (October 9; sign-up or follow if you want it sooner): Vodafone’s investor day revealed the scale and shape of its enterprise business, from £1.85 billion in annual…

• 3.SpaceX grabs “earthquake” 800 MHz deal as Starlink rocks US telcos

  SpaceX’s proposed acquisition of Grain Management’s 800 MHz spectrum portfolio strengthens Starlink Mobile’s push into terrestrial wireless. But coverage is not capacity, and building a competitive nationwide network could cost…

• 4.Wi-Fi 8 – the defensive frontline for ISPs against AI-driven cyberattacks (Reader Forum)

  Wi-Fi 8 could give ISPs a new line of defense against AI-driven cyberattacks, embedding inference hardware in residential gateways. Airties CEO Metin Taskin argues operators must pair next-generation chipsets with…

• 5.T-Mobile uses AI to reshape network investment and resilience

  Speaking during Deutsche Telekom’s AI Investor Day, John Saw, chief technology officer at T-Mobile highlighted Customer-Driven Coverage (CDC) as one of the company’s biggest AI-driven changes in how it approaches…

• 1.RAPID: Proactive Rate Control for Enabling High Data Rate and Low Latency in 5G Edge Networks

  Many 6G use cases such as tactile Internet and eXtended reality applications would simultaneously require a high data rate and low latency wireless connectivity.It is increasingly being realized that the current transport protocols relying on packet loss and delay are insufficient to satisfy the data rate and latency requirements of such applications. To address this problem, we propose RAPID, a transport layer solution designed for private 5G edge networks, where the bottleneck is located at the base station. We show that by regulating the send rate to maintain a target physical resource block utilization, we can achieve high data rate, low latency communication. We design a simple yet effective policy that adapts to the dynamic nature of wireless channel conditions. In a multi-UE scenario with two RAPID flows and one TCP Cubic flow, our...

• 2.On the Alignment Between Spectral Efficiency and Positioning Accuracy in Multi-LEO Clusters

  Low Earth Orbit (LEO) satellite constellations are expected to play a key role in future 6G Non-Terrestrial Networks (NTNs), where dense deployments enable cooperative multi-satellite processing for communication and positioning. While existing works have addressed communication and localization objectives separately, the correlation and alignment between these objectives remain largely unexplored. In this paper, we investigate the correlation between Spectral Efficiency (SE) and positioning accuracy in cooperative multi-LEO satellite clusters. We consider an uplink direct-to-device scenario in which multiple satellites jointly process user signals and evaluate cluster performance using SE and Position Error Bound (PEB) metrics. We derive Time-of-Arrival (TOA)-based and Doppler-based PEBs, while communication performance is quantified thr...

• 3.Stacked Intelligent Metasurface-Based MultiModal Feature Fusion for Collaborative Inference in Edge Networks

  In navigating the challenges of computational and communication overhead within the 6G-era Collaborative Inference (CI), this paper explores the feasibility of employing Stacked Intelligent Metasurface (SIM) to perform CI, termed SIM-CI. The SIM functions as a physical computing unit, receiving multi-user Over-The-Air (OTA) aggregated features within the same spectrum. It thus executes the necessary spatial-frequency combining and inference in a single physical wave propagation.SIM-CI also incorporates a tri-heterogeneity robustness adapter to address the network heterogeneity, such as multi-modal data and user inference models, as well as a quality-aware contrastive approach that align features from different modalities and extraction levels into a unified feature space. Considering the heterogeneous and dynamic channels, we further inte...

• 4.Multistatic Terahertz ISAC for Object Shape Identification

  6G networks are expected to sense their surroundings using the same waveforms that carry data. We ask how much can be learned about the shape of an object from the terahertz echoes that user equipment transmissions produce as they scatter from that object on their way to a ceiling-mounted access point, with no sensing hardware beyond the communication link itself. We build a physics-based multistatic forward model at a 300 GHz carrier with 50 GHz of bandwidth, combining Physical Optics (PO) and Physical Theory of Diffraction (PTD) scattering with an image-source multipath lattice, molecular absorption and directional horn antennas. The model makes explicit a property of the PO mechanism hierarchy that is usually left implicit. Six physically distinct mechanisms share only three frequency exponents, so the spectral slope does not by itself...

• 5.Event-Native Immersive Communication for 6G: From Multimodal Streams to Event Beliefs

  The development of multimodal sensing capabilities is crucial for realizing immersive communications and enabling rich, natural remote interactions in future sixth-generation~(6G) communications. However, transmitting high-dimensional sensory streams places substantial pressure on wireless resources and leaves a fundamental question unresolved: what information about the underlying physical process should be preserved across wireless delivery? To address this issue, we establish an event-native immersive-communication framework in which a service-relevant physical event defines the communication object, while event beliefs represent the information available to transceiver agents before and after wireless delivery. Based on this event-native framework, we further propose event-belief deficiency (EBD) to evaluate quality of experience (QoE...

• 2.FOMO: FLEX Options and Market Outcomes

  FLEX options are customized exchange-traded contracts allowing participants to choose nonstandard strikes, expirations, exercise styles, and settlement terms while retaining central clearing. We investigate whether single-name FLEX activity leaves measurable footprints in regular listed-option markets and underlying equities. Using a linked dataset of FLEX consolidations, daily open-interest files, listed-option chains, equity returns, and corporate actions over 250 trading days (March 2025-March 2026) across 41 underlyings and 53 event dates, we document three primary empirical findings: (1) Matched-control difference-in-differences estimates reveal a robust post-event increase in listed-option open interest (beta = 0.3061, p = 0.0042, Benjamini-Hochberg p = 0.0168). (2) FLEX activity is strongly selected into high implied-volatility (IV...

• 3.The Financing of Debt Relief: Intermediary Liquidity and the Value of Borrower Information

  I study how intermediary liquidity affects mortgage resolution using 1.9 million Ginnie Mae buyout options from 2019 to 2022. When funding markets froze in 2020, nonbank issuers repurchased far fewer delinquent loans than depositories servicing loans in the same pools and, within the same issuer and month, shifted repurchases away from large balances, the loans that require the most cash. About $19 billion of repurchases were delayed, and most were completed later. A model of rationing by value per dollar of cash explains this pattern and shows that borrower information is most valuable when funding is intermediate.

• 4.From a Hierarchy of Stochastic Differential Equations to a Hierarchy of Generalized Beta Distributions

  We introduce a mean-reverting stochastic differential equation with a three-component stochastic term and show that it generates a hierarchy of steady-state (stationary) distributions. At the top level, the hierarchy is described by a modified-Beta distribution, while one- and two-parameter reductions produce compact-support, power-law-tailed, and exponential-type limiting families within a single stochastic framework. We then construct two generalized extensions of this hierarchy. In the first, the power transformation is applied directly at the level of the stochastic differential equation; in the second, the same transformation is applied only after the stationary modified-Beta hierarchy has been obtained. While these two procedures agree on important lower branches and limiting cases they generally differ at the top level. The gener...

• 5.DSTNet: Dynamic Spectral Trajectory Network for Causal Multi-Horizon Financial Forecasting

  Wavelet-based financial forecasters typically use the transform only to denoise, or reduce it to a single spectral snapshot at the forecast origin, and the convolution that produces the coefficients is usually bilateral, so it can read past the forecast origin. DSTNet instead retains the recent evolution of filter-bank magnitudes as a causal Dynamic Spectral Trajectory, built from seven trailing technical indicators over a twenty-day lookback with a one-sided Morlet-derived filter bank and an explicit burn-in for the left-boundary transient. A factorized Scale-Temporal Spectral Transformer attends along the time and filter-bank axes separately, a learned gate fuses the spectral branch with a CNN-BiLSTM, and horizon-specific gates emit one, three, five, and ten day forecasts in a single pass. We evaluate seven equity indices and gold under...

• 3.Moving Target Defense in SDN-enabled EV Charging Network

  Software-Defined Networking (SDN) is emerging as a promis- ing technology for EV Charging infrastructure (EVCI) since it enables flexible, programmable control of EVCI networks, yet its security gain to EVCI remains underexplored. SDN-enabled EVCI faces an increas- ing number of cyber threats arising from the convergence of IT and OT components; in particular, low-rate Denial-of-Service (DoS) attacks. Ear- lier works identify a trend toward low-rate attacks in OT networks that may exhaust SDN switch flow tables and which can result in disabling the entire charging sites without triggering volume-based defenses. In this paper, we propose CS-SHIELD, a Moving Target Defense mecha- nism for SDN-enabled EVCI communication. We showcase the imple- mentation of the proposed mechanism that detects malicious flow table rules via cross-layer identit...

• 4.From Echoes to Evidence: Cooperative Fusion for Integrated Sensing and Communication

  Cooperative integrated sensing and communication (ISAC) can support shared situational awareness for unmanned aerial vehicles (UAVs), road vehicles, and industrial mobile robots such as automated guided vehicles (AGVs). Yet multipath can make nodes agree on a virtual target while useful weak echoes remain unexploited. This paper develops cooperative fusion that separates association confirmation, state refinement, and residual recovery. A cellular reference signal model accommodates arbitrary node counts, three-dimensional motion, monostatic and bistatic links, nuisance parameters, and correlated errors. We characterize report distinguishability under bounded bias and shared-reflector ambiguities that survive additional nodes. Minimax estimation yields directional weak-report refinement that preserves confirmed associations and limits bia...

• 5.Adaptive E2E Monitoring Path Selection with Deep Reinforcement Learning in Multi-domain Optical Networks

  Network slicing over multi-domain optical networks enables resource isolation for high-bandwidth, virtually-dedicated networks. However, guaranteeing end-to-end (E2E) performance remains challenging when domains withhold internal topology and performance metrics from external entities. Under this limited visibility, a control function (slice coordinator) needs to select E2E monitoring paths to detect and localize link failures. This paper formulates two complementary optimization problems, the initial and progressive monitoring path selection problems, which together realize closed-loop autonomous monitoring at the slice coordinator level. The initial problem maximizes failure coverage without prior information, while the progressive problem concentrates additional paths around suspected failure locations identified from prior monitoring....