# Research Papers — 2026-09 · bundle page 147 of 266 > Full-text markdown of papers #7301–7350 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/147 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/146.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/148.md) ### Physics-Informed Hemodynamic Modeling for Data-Free Prediction and Sparse-Data Assimilation Authors: Xi Chen, Jianchuan Yang, Hongde Li, Guangxin He, Qiuyu Ye, Qiang Luo, Mao Chen, Wenqi Hu Published: 2026-09-16 Categories: eess.IV, cs.AI arXiv: https://arxiv.org/abs/2609.19290v1 Clinical decision-making for coronary intervention relies mainly on angiography and fractional flow reserve (FFR). However, angiography is two-dimensional and lacks depth information for 3D lesion characterization, while FFR provides only a single functional index, offering limited hemodynamic insight. Among existing methods, numerical analysis is computationally expensive, whereas learning-based approaches require extensive supervision and often lack physical consistency. To address these limitations, we propose physics-informed hemodynamic modeling, an integrated deep learning framework for 3D coronary blood flow analysis from dual-view angiography. First, an attention-enhanced CNN reconstructs coronary geometry from angiography. The resulting point clouds are then mapped to a reference domain and Fourier-encoded for joint representation. A decoupled network separately predicts velocity and pressure fields, with embedded physical priors enabling efficient transfer across physiological conditions. Across 32 clinical patients evaluated under four flow conditions, the trans-stenotic pressure-drop mean absolute percentage error was 2.02%, while the velocity and pressure relative-L2 errors were 0.054 and 0.023, respectively. Validation against hospital-measured FFR further achieved 93.8% diagnostic accuracy (30/32; exact 95% CI, 79.2%-99.2%). The framework also supports illustrative revascularization comparisons and sparse-data assimilation, with the full angiography-to-hemodynamics pipeline completed within 20 minutes per patient. --- ### Learning-Induced Dynamical Transition in Recurrent Neural Networks Authors: Varun Vaidya Published: 2026-09-16 Categories: cs.LG, cond-mat.dis-nn, nlin.CD arXiv: https://arxiv.org/abs/2609.19288v1 Learning in recurrent neural networks can fundamentally reshape their underlying dynamics, transforming initially chaotic activity into stable task-dependent behavior. We develop a non-equilibrium dynamical mean-field theory(DMFT) to describe this transition during learning. We show that a slow feedback-driven learning process generates an evolving effective feedback strength that drives the network through a transition from chaotic to stable dynamics defined by a bifurcation of the DMFT solution. By deriving the two-time correlation function throughout learning, we identify a critical feedback strength and a corresponding learning rate dependent critical time separating these regimes. The transition arises from the progressive deformation of an effective dynamical landscape by the growing learned feedback structure. Starting from the untrained state, the theory predicts the time evolution of the network output during training and shows quantitative agreement with numerical simulations. --- ### Radio-Frequency Convolutional Neural Networks Authors: Zhihui Gao, Shi-Yuan Ma, Yiran Chen, Dirk Englund, Tingjun Chen Published: 2026-09-16 Categories: cs.LG, cs.ET, eess.SP, physics.app-ph arXiv: https://arxiv.org/abs/2609.19279v1 Running artificial intelligence (AI) models directly on edge devices such as smartphones, wearables, and drones offers low latency, pervasive scalability, and data privacy, but these devices rarely carry the computing capability that modern neural networks demand. Edge accelerators have been developed in response, yet each adds computing hardware to devices already constrained in size, weight, power, and cost (SWaP-C). An alternative lies in what these devices already carry: the frequency mixer in every wireless radio multiplies signals in time, natively performing convolution in the frequency domain. Here we introduce radio-frequency convolutional neural networks (RF-CNNs), which repurpose existing communication hardware for CNN inference. Multi-channel convolutions are mapped onto frequency tones for a passive mixer to execute in a single pass. We experimentally demonstrate that RF-CNN runs deep CNNs up to 26.4 million parameters and nine layers from classification of wireless signals and images to controllable image generation, close to full-precision performance. Because the weights arrive over the air and the analog hardware is shared with communication, the edge device spends energy only on data preparation and readout-down to 0.72 femtojoules per multiply-accumulate, two orders of magnitude less than it would cost on an added digital processor. These results suggest that deployed wireless infrastructure can bring efficient, state-of-the-art AI inference to the billions of devices it already connects. --- ### Characterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responses Authors: Mahsa Amani, Seungeon Lee, Abhisek Dash, Asmaa El Fraihi, Yunah Jang, Elisabeth Kirsten, Qinyuan Wu, Krishna P. Gummadi, Manish Gupta, Abhilasha Ravichander, Muhammad Bilal Zafar, Soumi Das Published: 2026-09-16 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.19244v1 Conversational LLM agents increasingly rely on Web search, yet the end-to-end lifecycle of agentic search remains poorly understood. We present the first study of Web search across four major conversational platforms (ChatGPT, Claude, Grok, and DeepSeek), combining real-world user interactions (invivo) with controlled experiments using the same platform's models by their APIs (invitro). We investigate the quality of agentic decisions to invoke Web search, their strategies to formulate queries, the potential domain preferences in the search results they receive, and the choices they make when transforming search results into grounded responses. We find that Web-search decisions vary substantially across platforms and models, while more frequent Web-search invocation does not necessarily yield better response quality. We further show that conversational agents employ different complex querying strategies and that platform specific search engines return search results from their preferred domains. Finally, although responses are largely grounded in search results, some claims rely on uncited search results, raising concerns about attribution and reliability. Our findings have important implications for the design of future AI agents and Web search tools optimized for conversational retrieval. --- ### Randomized SVD Approximations for Spectral Co-Clustering of Word-Document Matrices Authors: Fateme Mazdarani, Carlos Toxtli Published: 2026-09-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.19243v1 Spectral co-clustering is a useful tool for discovering latent structure in word-document matrices, but its reliance on singular value decomposition (SVD) can make standard formulations expensive on high-dimensional data. This paper presents two randomized approximations for normalized spectral co-clustering of bipartite text data when the numbers of document and word clusters may differ. The first method uses randomized SVD through random projection, while the second combines partial SVD with element-wise random sampling. Across real-world and synthetic datasets, both methods reduce runtime relative to the full-SVD baseline, but their behavior depends on matrix sparsity. The random projection method is the more reliable approximation across the tested settings, whereas the sampling-based method is most useful on denser matrices and provides limited benefit on already sparse text data. These results show that randomized approximations for spectral co-clustering should be selected according to the underlying structure of the data. --- ### Block Parallelism For Efficient Distributed Long-Context Diffusion Language Model Training Authors: Tarun Suresh, Pranshu Chaturvedi, Hangoo Kang, Parth Shroff, Ishan S. Khare, Hermann Kumbong, Azalia Mirhoseini Published: 2026-09-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19242v1 Block diffusion language models (BDLMs) combine autoregressive dependencies across blocks with parallel denoising within blocks, but long-context training is constrained by distributed attention communication and activation memory. Conventional context parallelism (CP) shards the combined clean-plus-corrupted sequence by position, communicating shared clean K/V together with block-specific corrupted K/V and their gradients. We observe that the BDLM objective separates over target blocks. We introduce block parallelism (BP), a new distributed parallelism dimension that assigns each corrupted-block computation to one rank. To scale BP to long contexts, we introduce context-sharded block parallelism (CSBP), which also shards the shared clean sequence across those ranks. CSBP keeps corrupted K/V and gradients local, avoids replicated clean prefixes, and preserves BDLM training semantics. On 16 H200 GPUs at 256K context, CSBP improves throughput over the best baseline by 1.18-1.45x for supervised fine-tuning and 1.27-1.33x for conversion of autoregressive models to BDLMs, while matching or reducing peak HBM. Full-model speedup reaches 1.61x at 512K. On eight H100 GPUs, CSBP accelerates DFlash2 speculative-decoder training by 2.48x at 512K and 7.59x at 1M. In matched 12-hour DiffusionGemma 26B-A4B SFT runs, CSBP achieves higher pass rates at every trained checkpoint on SWE-bench Verified and Terminal-Bench Lite. Code: https://github.com/ScalingIntelligence/Turbo-dLLM --- ### RAUL: Reference-Assisted Ureteroscopy Localization for Skill Assessment Authors: Fangjie Li, Mai Bui, Charan Mohan, Michael Miga, Matthieu Chabanas, Nicholas Kavoussi, Jie Ying Wu Published: 2026-09-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19236v1 Objective: Incomplete navigation of anatomy during ureteroscopic kidney stone surgeries can contribute to repeat interventions. While skilled surgeons have lower reintervention rates, there are no objective metrics to quantify scope-navigation performance to evaluate when a trainee becomes skilled. This work aims to recover ureteroscope trajectories from endoscopic video and derive navigation metrics to quantify differences in skill. Methods: We propose RAUL, a reference-assisted reconstruction framework for recovering ureteroscope trajectories from ureteroscope videos only in phantoms. For each phantom, we use a slow, high-quality reference exploration video to generate a reference reconstruction. We localize subsequent exploration videos against this reference. We evaluate localization accuracy against electromagnetically tracked scope pose. We compute navigation metrics from phantom exploration trajectories to compare surgical residents across experience levels. Results: The proposed reference-assisted framework achieves a mean translation root mean square error of $0.5 \pm 0.1$ mm across 9 phantoms. Compared to standard Structure-from-Motion (SfM), the proposed pipeline increases frame-wise localization coverage from $50.5 \pm 14.9\%$ to $86.1 \pm 7.2\%$ of all video frames. The reconstructed trajectories revealed significant differences between high- and low-experience trainees in established navigation metrics. Conclusion: RAUL enables substantially more complete recovery of ureteroscope trajectories from videos compared to standard SfM pipelines, enabling trajectory-based skill assessment without additional tracking equipment. Significance: To the best of our knowledge, this is the first use of video-only recovery of ureteroscope trajectories without external tracking sensors for skill assessment, supporting scalable automated assessment of ureteroscopy navigation skill. --- ### The AR Fairness Metamodel: A Structured Framework for Fairness Measures Authors: Julian Alfredo Mendez, Timotheus Kampik Published: 2026-09-16 Categories: cs.CY, cs.AI, cs.LO, cs.MA, cs.PL arXiv: https://arxiv.org/abs/2609.19234v1 This paper presents the AR fairness metamodel, a framework designed to represent, analyze, and compare different fairness scenarios. The metamodel considers key elements, such as agents, resources, and their attributes, and enables the systematic definition and comparison of various fairness measures. We provide examples involving both discrete and continuous measures, including equality, equity, group fairness, individual fairness, the Gini index, the Theil index, Jain's fairness index, and a detailed fairness measure for Australia's Child Care Subsidy. We also explore relationships among group fairness, individual fairness, and envy-freeness, supported by formal proofs. At the conceptual modeling level, our approach builds on the Tiles framework, which offers modular components that can be connected to capture diverse fairness definitions. The goal is to make AR-based fairness definitions practical and adaptable across contexts, providing a clear way to define, compare, and evaluate them. An implementation of the Tiles framework is available as an open-source tool, and can support fairness modeling and evaluation across a wide range of applications. --- ### Open ultrasound foundation model for robust segmentation and clinical measurement across heterogeneous settings Authors: Chao Qin, Fahad Shahbaz Khan, Salman Khan, Sarim Ather, Siddiq Anwar, Rao Muhammad Anwer, Shadab Khan Published: 2026-09-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19230v1 Ultrasound is the most widely deployed imaging modality worldwide, yet clinical AI remains fragmented into narrow single-task models that fail when device, operator, or anatomy changes. Here we present SonoCorpus, an open resource unifying 456,963 images and 1,626,085 expert masks from 53 public datasets spanning 24 clinical applications and 17 countries, and SonoBase, an interactive segmentation foundation model pretrained on it. Across fifteen evaluation datasets introducing new organs, devices, operators, and geographies, SonoBase outperforms SAM2, MedSAM2, and the concept-promptable MedSAM3 on every dataset and matches per-dataset specialist models trained on the same data; on fully external data it exceeds the accuracy these baselines achieve on their own in-distribution benchmarks. Ejection fraction derived from its segmentations falls within inter-observer variability (6.63\% error), with fewer misclassifications at the defibrillator-candidacy threshold than either promptable baseline (13\% versus 18--42\%); fetal head-circumference (1.81~mm) and gestational-age (1.2 days) errors fall below inter-observer variability. Where a baseline fails outright, one in four test cases, SonoBase recovers a usable segmentation in 81\% of them, including on handheld probes operated by minimally trained users in two low- and middle-income countries (Sierra Leone and Tanzania). Five labeled examples can help the model adapt to a new setting, and the identical training protocol transfers well to newer models such as SAM3, locating the advantage in ultrasound-specific pretraining rather than any single architecture. To ensure reproducibility and enable the community to build on SonoBase as a platform, we release all checkpoints, optimizer states, data-split indices, deduplication hashes, and starter code. --- ### PAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated Workflows Authors: Tao Huang, Guosen Wu, Chen Hou, Guolong Zheng Published: 2026-09-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.19226v1 AI-mediated platforms coordinate work through LLM agents acting for different principals. In these workflows, privacy loss can be created before a final answer appears: a memory write, shared-workspace update, inter-agent message, or tool event may impose downstream exposure cost on another principal. We model this failure mode as a privacy-propagation externality, where the cost of a raw disclosure depends on topology and fanout as well as content. We present PAPC, a platform-mediated mechanism that intercepts information-moving events before they update shared state or external channels. PAPC combines policy, provenance, topology/fanout, privilege, and content signals to allow an event, release a policy-safe abstraction, quarantine raw content, block a transition, or narrow onward rights. The model explains why final-output control misses intermediate exposure costs and why high-fanout objects amplify propagation. Across retrieval-memory and multi-agent workflow benchmarks, PAPC preserves deterministic task completion and eliminates measured exact raw-value and external raw-value exposure. The results position event-level mediation as a platform-governance primitive for agent-mediated online work. --- ### When a High Score Is an Illusion: Certifying Genuine versus Repackaged Forecasting Skill Authors: Pin Ni, Francesca Medda, Ramin Okhrati Published: 2026-09-16 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.19223v1 Ranks depend on the observations used for comparison. Reusing those observations can add association between forecast and outcome rank contrasts even when the evaluated forecast and outcome stay fixed. We characterize assignments that preserve association between specified population-rank contrasts, including forecast rank minus baseline rank compared with outcome rank minus baseline rank. Conditional on independent training, whole trajectories are sampled independently from a common law, with unrestricted dependence within each trajectory. The expected score separates into its target and an explicit interaction between map pairs. When reassigning references, we keep the learned maps, reference law and coefficient row sums fixed. Zero weighted reference overlap for every map pair is necessary and sufficient for preservation uniformly over permitted maps and laws. An unbiased three-trajectory kernel estimates the interaction; independent evaluation and validation provide finite-sample lower bounds. Complete U-statistics estimate the same target directly when all draws can be recombined. Sharp shared-baseline ranges, including ties, tighten both constructions. In a Beijing air-quality archive, interaction accounts for 91.4% to 94.5% of seven learned forecasts' expected shared scores under the empirical archive law. Separate results address category-fitting error and temporal feedback. In a matched category-control null experiment, distinct references reduce rejections from 402 to 41 out of 1,000 panels. --- ### 4D Radar Perception Algorithms for Autonomous Driving: A Review Authors: Xumin Wu, Jun Zhou, Jilin Mei, Chen Min, Yu Hu Published: 2026-09-16 Categories: cs.RO, cs.CV, eess.SP arXiv: https://arxiv.org/abs/2609.19216v1 Research on 4D millimeter-wave radar perception algorithms has flourished in recent years, extending from signal processing and object detection to semantic segmentation, motion estimation, occupancy prediction, and dynamic scene reconstruction. This review organizes the field according to the evolution of perception tasks and algorithms. It first introduces radar fundamentals, data representations, and quality-enhancement methods, and then reviews object-level perception, motion and localization, local and dense spatial perception, and dynamic scene understanding. Across these directions, we compare radar-only learning, multimodal fusion, and cross-modal supervision and knowledge distillation. Particular attention is paid to how elevation, Doppler measurements, and radar physical priors are exploited across tasks. We further summarize the task coverage, input data, annotations, and evaluation protocols of existing datasets, clarifying the empirical support for different research directions. Finally, we discuss the common challenges and future directions of 4D radar perception for autonomous driving. This review provides a task-oriented perspective on the transition from sparse object perception to dynamic spatial understanding. --- ### Perceptual Refinement of an End-to-End Video Streaming Pipeline via Generative AI Layers Authors: Emanuele Artioli, Farzad Tashtarian, Christian Timmerer Published: 2026-09-16 Categories: eess.IV, cs.AI, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2609.19215v1 Traditional codecs treat every region of a frame alike; a generative layer can instead degrade the regions a viewer attends to least and reconstruct them at the client. We present PRESLEY, which extends the prior conference work ELVIS by replacing destructive block removal with adaptive in-place degradation under a removability mask, signaling per-block strength in a bit-packed side channel, and restoring via generative backbones conditioned on transmitted visual priors rather than unconditioned in-painting. We separate the problem into three goals: choosing which blocks to degrade, degrading them so the encoder spends fewer bits, and restoring them. Against its predecessor at matched rate, PRESLEY achieves a decisive mean -56.4% BD-rate reduction on delivered background quality across 13 rate ladders spanning multiple codecs and dataset families. Against pristine baselines, PRESLEY defines the operating regime of generative transport: delivering substantial bitrate savings (up to -29.4% BD-rate) and superior background quality (17/23 sequences) in the target bit-starved regime, while maintaining foreground fidelity bit-exact. We further map where the theoretical headroom in this class of architecture lies. Using an exact leave-one-superblock-out combinatorial oracle as an additive empirical bound, we show that existing complexity heuristics already capture 83.3% of bit-cost savings, bounding remaining cost-axis headroom at about 5% of total bitrate. We then identify and model the primary unaddressed axis -- post-restoration damage -- which disperses widely (4.9-8.4 dB). We prove that this damage is predictable before transmission (held-out rho = +0.400), establishing the feasibility of transmit-time restorability modeling and defining the roadmap for joint rate-distortion-restoration selection rules. --- ### Layer-wise Curriculum Learning for Efficient LLM Compression Authors: Donggeon Lee, Dooyeon Na, Seungmin Oh, Jongbin Ryu Published: 2026-09-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.19213v1 In this paper, we introduce layer-wise curriculum learning for efficient LLM compression. The proposed method facilitates the knowledge transfer from the teacher model to the student model, utilizing a curriculum learning approach that begins with easier optimization tasks and progressively tackles harder ones. In order to adopt the layer-wise learning in LLM compression, we partition the whole model into multiple segments consisting of layers, thereby enabling more computationally efficient knowledge transfer for LLMs. Based on our theoretical analysis of cumulative error phenomenon, layer-wise curriculum learning accelerates convergence while stabilizing the knowledge transfer process. In addition, we present a feature caching method with a multi-threading strategy to efficiently address feature misalignment across layers, maximizing GPU utilization. Consequently, our method exhibits advanced model compression performance, as well as high computational efficiency in terms of minimized memory usage and short training hours. Experiments on multiple datasets show that the proposed method achieves state-of-the-art performance while reducing GPU memory usage and training hours by more than 50\% on BERT and GPT-2. Moreover, it outperforms the other pruning methods on LLaMA-family and Qwen models under the same training hours, with a lower GPU memory footprint. --- ### What Do Current Systematic Generalization Tasks Miss? A Reasoning-Centered Analysis Authors: Chengwen Qi, Deheng Ye, Yatao Bian Published: 2026-09-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.19212v2 Systematic generalization, the ability to solve novel problems by recombining known atomic elements, is central to human intelligence but difficult to study rigorously under controlled settings. Existing studies therefore rely on simplifications such as elemental composition, productivity-based tests, and action-explicit goals, which make systematic generalization easier to study but omit some essential aspects of this capability. To characterize what these simplifications miss, we adopt a reasoning-centered lens and introduce TranSGrid, a testbed that brings deductive, inductive, and abductive reasoning together within a unified task. Experiments with seven Transformer models on 4,800 TranSGrid instances show that all models perform much worse on TranSGrid than on a held-out test set: the largest model solves 79.6% of the test set, but only 55.3% of TranSGrid and 15.8% of the hardest subset. The gap remains within the training length range, showing that productivity alone is not sufficient to evaluate systematic generalization. Additionally, we reintroduce the other two simplifications into TranSGrid: one variant limits interactions among action effects to approximate elemental composition (reducing the inductive demand); the other makes goals action-explicit (reducing the abductive one). In both, solve rates return to roughly the test set level, showing that either simplification alone is enough to reduce TranSGrid to an ordinary held-out test set. Together, our results show that existing tasks reduce either or both of the inductive and abductive demands of systematic generalization, and that comprehensively measuring this capability requires a task that involves all three forms of reasoning. --- ### Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation Authors: Naga Venkata Sai Jitin Jami, Thomas Altstidl, Sebastian Hoefler, Jonas Mueller, Dario Zanca, Bjoern Eskofier, Heike Leutheuser Published: 2026-09-16 Categories: cs.SI, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.19210v1 Graph neural networks are widely used for transductive node classification, with accuracy typically measured on randomly drawn train/validation/test splits. Reported accuracy has been shown to shift substantially across different random splits of the same dataset, making published comparisons between architectures unreliable. The classical remedy in non-graph settings is stratified $k$-fold cross-validation, which ensures each test fold reflects the full class distribution of the dataset. We argue that class stratification alone is insufficient for graphs: nodes are not isolated but connected, and folds that differ in their distribution of local neighbourhood homophily expose the model to systematically different relational conditions that directly affect message-passing behaviour. The resulting cross-fold variation reflects the homophily composition of each split, inflating reported variance beyond what model behaviour alone would produce. To address this, we propose \hp{}, a topology-aware stratification procedure that treats node homophily as the primary stratification axis, aligning folds with respect to local relational consistency alongside the class marginal that standard stratification already controls. Stratifying on homophily alone does not guarantee class balance, so \hp{} incorporates class label as a secondary axis, preserving class representativeness as a natural consequence of the procedure. We evaluate \hp{} on a broad benchmark suite comprising 15 node-classification datasets spanning the full homophily spectrum and 7 GNN architectures. \hp{} achieves a mean stability rank of 1.49 compared to 2.31 for random $k$-fold, achieving the lowest mean stability rank on 13 of 15 datasets while preserving class balance close to class-stratified splits and substantially better than random. We argue that homophily-aware split construction merits broader adoption for GNN evaluation. --- ### Generative Query Suggestion via Intent Coverage and Query-Level Credit Assignment Authors: Xinpeng Liu, Lu Ma, Jiayi Qiao, Mengyu Zhou, Linglong Li, Xiaofeng Bian, Haonan Chen, Xiaoxi Jiang, Guanjun Jiang Published: 2026-09-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19209v1 Generative query suggestion aims to enhance user engagement by anticipating user intents and recommending relevant follow-up queries. A central challenge is to generate slates whose individual queries are useful while the slate covers distinct intents. We propose an Intent-Driven Query Suggestion Framework with dual-stage optimization. First, intent-aware diversity modeling constructs intent-aligned supervised fine-tuning (SFT) data and uses an Intent-Aware Diversity Reward to optimize intent coverage. Second, query-level credit assignment routes individual quality signals to the corresponding query tokens while sharing a slate-level diversity signal across the slate. Experiments on a large-scale production dataset, including online A/B testing and offline evaluation, show improvements in click-through rate, query quality, and intent coverage. --- ### MeshKV: A Network-on-Chip KV Cache Fabric for Scalable Transformer Decoding Accelerators Authors: Dong Liu, Yanxuan Yu Published: 2026-09-16 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2609.19207v1 Autoregressive transformer decoding is constrained by irregular key-value (KV) cache movement on tiled accelerators. Prior compression and DRAM-placement systems still concentrate traffic on centralized memory paths that bottleneck long-context serving. We present MeshKV, a KV cache fabric that moves blocks as packetized flows over a lightweight NoC. It co-designs (i) TaKV affine striping to spread homes and cut hotspot load, (ii) Mare multicast with verified duplicate suppression, and (iii) Pad, which overlaps prefetch, tile multiply, and streaming softmax behind credit-aligned FIFOs. Together they convert bisection back-pressure into useful KV transfer. On our 8x8 FPGA implementation with LLaMA-2-7B and Mistral-7B at 8K-32K, MeshKV reduces interconnect traffic by up to 58%, improves KV bandwidth utilization by 2.1x, and delivers up to 1.9x multi-stream throughput. --- ### REACT: A Fully Spiking State-Space Model for Real-Time Event-Driven Temporal Perception Authors: Geoffroy Keime, Nicolas Cuperlier, Benoit R. Cottereau Published: 2026-09-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.19204v1 Robotic systems operating in dynamic environments require visual perception that evolves continuously with the incoming sensory stream. Event cameras provide microsecond temporal resolution and asynchronous sensing, but most learning-based methods accumulate events into frames or temporal bins, introducing an integration delay that can limit fast reaction. Here we propose REACT, a fully spiking state-space model for event-driven temporal perception that processes raw events one by one, without temporal accumulation. REACT uses a complex-valued spiking neuron, C-SiLIF, whose continuous-time dynamics are driven by the physical inter-event interval, allowing its internal state to evolve at the temporal resolution of individual events. We evaluate REACT on gesture recognition and time-to-collision (TTC) estimation from full-field event streams, without a target bounding box or localization input. On EvTTC, REACT achieves a 9.59% relative TTC error with 4.6 ms end-to-end inference latency, within 0.15 percentage points of the best learned method while requiring no target prior. At the dataset's mean approach speed, this latency corresponds to only 4 cm of vehicle motion, compared with 1 m for the fastest competing learned method. REACT further supports anytime TTC prediction, zero-shot transfer to a different driving sequence, and INT8 quantization, reducing the estimated energy consumption from 18.5 to 2.8 mJ per 32,768 events. These results show that event-driven spiking state-space dynamics can provide low-latency, continuously updated temporal perception for reactive robotic systems. --- ### Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer Authors: Suparna Bhattacharya, Tarun Kumar, Cong Xu, Satish Kumar Mopur, Jiahao Li, Ashish Mishra, Aalap Tripathy, Annmary Justine Koomthanam, Martin Foltin, Ian Foster Published: 2026-09-16 Categories: cs.AI, cs.LG, cs.MA, cs.OS arXiv: https://arxiv.org/abs/2609.19203v1 AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as protocols (e.g., MCP, A2A) ease tool/agent connectivity, each framework embeds an implicit runtime for state, memory, budgets, and guardrails, making behavior non-portable and governance brittle. It mirrors computing before operating systems, when every program re-implemented basic services. This position paper argues that the field now needs a Foundation Model Operating System (FMOS) -- a system layer that virtualizes FM interactions analogous to how virtual machines abstract physical hardware, giving applications the illusion of dedicated, trustworthy FM instances with effectively unbounded capabilities. Internally, the FMOS orchestrates knowledge across memory tiers, model selection and resource allocation, and verification and policy enforcement. Like the human brain switching between fast intuition and slow deliberation, the FMOS learns when to intervene and when to let inference proceed directly and continuously adapting its policies based on operational experience. --- ### Federated Soft Clustering via Generalized Total Variation Minimization Authors: Shamsiiat Abdurakhmanova, Alexander Jung Published: 2026-09-16 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.19202v1 We study federated soft clustering over federated learning (FL) networks of devices that each hold a private local dataset and fit a personalized Gaussian mixture model (GMM). Generalized total variation minimization (GTVMin) couples the local maximum likelihood problems through a graph regularizer that penalizes a discrepancy between the models of connected nodes. The choice of discrepancy measure is a key design decision: we compare a squared Euclidean distance between model parameters, which requires component matching, with two measures that compare the local model distributions directly and hence need no matching: a Monte-Carlo approximated Kullback-Leibler (KL) divergence and a closed-form maximum mean discrepancy (MMD). All three resulting GTVMin instances are optimized by synchronous projected gradient updates; for the smooth MMD instance we provide a convergence guarantee to stationary points. We characterize their computational cost and evaluate their robustness to data heterogeneity. --- ### Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code Authors: Jisoo Kim, Taeyoon Kwack, Jinwoo Jang, Woo Kyung Kim, Honguk Woo Published: 2026-09-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.19199v1 Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in legal logic and evidence. We present Code-as-Auditor, an LLM-based framework that extends the model's reasoning capability toward structured and evidence-grounded compliance assessment. The framework translates regulatory information into (1) formalized checklists and executable decision trees, encoding regulations and conditions as interpretable code structures. During inference, each checklist item is (2) dynamically expanded into factual and counterfactual questions, guiding the model to reason over case-specific evidence and potential violations. This process establishes a reasoning pipeline that proceeds from evidence identification, through rule application, to final decision-making, while a self-verification loop improves the logical consistency of the generated code and the traceability of outcomes. Experiments on privacy and data protection scenarios demonstrate that Code-as-Auditor delivers more accurate and evidence-backed evaluations, enabling automated compliance regulation checking grounded in explicit regulatory criteria. --- ### Objective vs. Search: Decomposing What Makes a Good Tokeniser Authors: Ahmetcan Yavuz, Clara Meister, Tiago Pimentel Published: 2026-09-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.19145v1 Two dominant tokenisation algorithms are used by modern language models: byte-pair encoding (BPE) and UnigramLM. These differ along two orthogonal axes: their optimisation objective (compression vs. log-likelihood) and their search procedure (bottom-up merging vs. top-down pruning). Existing comparisons confound these axes, making it unclear whether their observed differences stem from what is being optimised vs. how it is being optimised. We disentangle the two by introducing two new tokenisation algorithms that complete this 2x2 design space: BottomUpLL, a bottom-up likelihood-based tokeniser, and TopDownComp, a top-down compression-based tokeniser. We train language models with tokenisers produced by each algorithm, varying: model size, vocabulary sizes, and domain (English-only vs. multilingual). Evaluating models on bits-per-byte, we find that the search procedure -- not the objective -- is the dominant factor: bottom-up tokenisers consistently achieve lower bits-per-byte in most settings. Evaluating models on the BLiMP task, however, shows no consistent relationship between design choice and performance. Overall, our results disentangle the effect of tokeniser design choices on language modelling performance, offering concrete guidance for their more principled construction. --- ### A Zeroth-Order Paradigm for LLM Preference Alignment Authors: Peter Chen, Xi Chen, Wotao Yin, Tianyi Lin Published: 2026-09-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.19144v1 Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and memory efficiency. However, likelihood displacement motivates alternative ways to extract information from preference pairs with small likelihood margins. In this paper, we propose and analyze Comparison-based Preference Optimization (ComPO), a zeroth-order alignment method based on comparison oracles. ComPO extracts directional information from these pairs without directly optimizing a differentiable preference loss on them. We establish a convergence guarantee for its basic offline scheme under smoothness, gradient sparsity, and compatibility between the oracle and a latent objective. We further introduce online ComPO, which retains the offline comparison mechanism and uses unlabeled policy generations for reverse-KL control relative to a reference policy. Following the coverage perspective of preference fine-tuning, we establish a performance guarantee for a basic constrained scheme under local coverage and in-distribution pairwise reward accuracy. Experiments on Mistral, Llama, Gemma-2, Qwen3, and Gemma-3 models demonstrate improvements over existing direct alignment methods, including length-controlled win rates, with pair-level diagnostics providing evidence consistent with mitigating likelihood displacement. --- ### PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection Authors: Sara Pieri, Evangelos Kazakos, Shizhe Chen, Josef Sivic, Cordelia Schmid Published: 2026-09-16 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2609.19143v1 Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent and detailed image captions, but reliably associating them with image pixels remains challenging. Existing methods that combine dense captioning with pixel-level grounding often produce either incomplete descriptions or inaccurate segmentation masks. We study this problem through panoptic grounded captioning, a task that requires a VLM to describe both foreground objects and background regions while grounding each referring phrase with pixel-level masks. We make three contributions. First, we introduce PanoCaps, a human-annotated benchmark constructed from panoptic segmentation datasets. It provides dense captions with near-complete pixel coverage and image-text alignments at the entity level, supporting both training and evaluation. We further propose a phrase-mask matching protocol and a generalized Panoptic Quality (gPQ) metric that jointly evaluates textual and mask agreement. Second, we formulate phrase grounding as selection from a phrase-conditioned pool of mask proposals and introduce PANORAMA, a VLM that conditions a pretrained segmenter on contextualized phrase representations to obtain candidate masks and learns to select those corresponding to each phrase. Training this interface jointly with caption generation enables PANORAMA to produce high-quality masks while allowing each phrase to refer to a single region or multiple instances. Third, PANORAMA achieves the best overall grounding on PanoCaps and matches or exceeds specialized models across several pixel-level grounding tasks. Experiments show that our method produces precise entity-level segmentations while maintaining detailed, mask-consistent captions. Code, data and models are available at https://www.di.ens.fr/willow/research/panorama/. --- ### PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics Authors: Bardienus P. Duisterhof, Kaifeng Zhang, Adam Hung, Bowen Wen, Stan Birchfield, Yunzhu Li, Deva Ramanan, Jeffrey Ichnowski Published: 2026-09-16 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.19142v1 World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse volumes of data, to instill a rich prior into downstream applications. Existing methods typically require robot action labels to learn action-conditioned 3D dynamics, which excludes web video data from the training pool. We study 3D point track completion as a pre-training objective for learning transferable 3D dynamics without robot data. Given a single RGB-D observation and sparse partial 3D trajectories (tracks), we predict future 3D tracks of all observed points. We show this objective produces a rich 3D dynamics prior, without requiring robot action labels. We contribute a diverse dataset of 2.9 million synthetic frames spanning deformable, articulated, and rigid objects, and use it to train PointZero. We show that a flexible and expressive transformer, PointZero, outperforms prior methods on the same data. We demonstrate the utility of our pre-training objective by post-training PointZero for two downstream applications: (1) action-conditioned 3D dynamics prediction and (2) imitation learning. When fine-tuned to condition on end-effector pose, PointZero outperforms the baselines on the recent PGND 3D dynamics benchmark. When fine-tuned to predict robot actions and 3D tracks, PointZero outperforms or matches the baselines on 6/7 simulated and real-world robot manipulation tasks. We furthermore evaluate training PointZero from scratch to isolate the benefits of our proposed architecture from those of our proposed pre-training objective and dataset. We release the dataset, checkpoints, and full training recipe. --- ### In-Context Robot Learning with VLM Agents Authors: Dongzhou Cheng, Taoran Yi, Ye Fang, Xingwu Zhang, Fan Feng, Yixuan Li, Gengxiong Zhuang, Rongze Wang, Shuai Yang, Wei Song, Weizhi Xue, Minyan Wu et al. Published: 2026-09-16 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.19138v1 Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstrations can cover every task and situation a robot will encounter, making the ability to learn from context at deployment essential for generalization. Such in-context learning (ICL), however, remains largely beyond the reach of existing robotic policies. The broad agentic capabilities of commercial vision-language models (VLMs), such as GPT-6 Astra, raise a compelling question: can these models learn from demonstrations, examples, and interaction feedback, then translate that information into executable and verifiable robot behavior from a new initial state without gradient updates or persistent changes to task-specific parameters? We introduce GPT-Policy, a general-agent framework for in-context robot learning. GPT-Policy integrates a context compiler that preserves task-relevant visual transitions, a VLM that proposes robot-tool actions, and a constrained controller that verifies and executes each action and reports its outcome. We evaluate its reliability and limitations through task success and efficiency metrics, matched comparisons across models, and controlled context ablations. In real-robot trials, human video demonstrations improve task completion even without robot action labels, while aligned action references yield further gains on contact-sensitive tasks. These findings position GPT-Policy as a step toward robot adaptation through in-context learning, providing an empirical foundation for translating the general-purpose capabilities of VLMs into physical behavior and clarifying the challenges that must be overcome for reliable deployment. --- ### Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation Authors: Guanhua Ji, Tianyu Li, Dayoon Suh, Yuqian Zhang, Boyan Zhang, Nadia Figueroa Published: 2026-09-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.19137v2 Video generation models have advanced rapidly and can now synthesize plausible videos of robot manipulation from image and text prompts. Recent work extracts robot actions directly from such generated videos, but the result is purely kinematic and lacks force information, causing failures in contact-rich tasks where appropriate contact forces are essential for success. We present a pipeline that jointly leverages generated video and audio to derive motion trajectories and desired-force profiles. The force profile is shaped by the loudness of the generated contact sound, and we execute the resulting force-aware trajectories on a Franka robot using a closed-loop force regulator. We evaluate our pipeline on multiple tasks that require making contact and demonstrate successful zero-shot manipulation where a kinematic-only baseline fails. We also show that the pipeline can be used as a data generation engine to train policies that achieve the tasks in a closed-loop manner. Project website, videos, and dataset: https://dreamingcontactsound.github.io/ --- ### Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation Authors: Guanhua Ji, Tianyu Li, Dayoon Suh, Yuqian Zhang, Boyan Zhang, Nadia Figueroa Published: 2026-09-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.19137v1 Recent advances in video generation allow robots to learn manipulation trajectories from generated videos. However, these approaches produce purely kinematic trajectories that lack force information, causing failures in contact-rich tasks where appropriate contact forces are essential for success. In this work, we explore augmenting generated video with audio to shape a bounded, time-varying desired-force profile using the loudness of generated contact sounds. We present a pipeline that jointly leverages generated video and audio to derive motion trajectories and corresponding desired-force profiles from a structured natural-language task prompt. We execute these force-aware trajectories on a Franka Panda robot using a closed-loop force regulator that tracks the audio-shaped force profile during contact. We evaluate our pipeline on multiple tasks that require making contact and demonstrate successful manipulation where a kinematic-only baseline fails. We also use the pipeline as a data generation engine to train policies that achieve the tasks in a closed-loop manner. Project website, videos, and dataset: https://dreamingcontactsound.github.io/ --- ### Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging Authors: Pranaya Jajoo Published: 2026-09-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19135v1 Can a logged dataset visit every hidden state frequently and still be exponentially uninformative about a target policy's value? We show that it can when the logger depends on history. For every horizon $H \ge 3$, we construct two POMDPs with at most two latent states per stage, three actions, and a common logger with three memory states. Action coverage, belief coverage, and two behavior-marginal outcome-revealing conditions all have constants independent of $H$. Nevertheless, evaluating a known deterministic target policy to accuracy $1/8$ requires $Θ((3/2)^H \log(1/δ))$ logged episodes at confidence $1-δ$, for $0 < δ\le 1/4$, even when both candidate models are known. The mechanism is simple: a reset erases the unknown transition that determines the target value. We characterize the resulting statistical experiment exactly and obtain a matching optimal estimator. A directed two-lane gridworld realizes the construction, and trajectory simulations agree with its finite-sample prediction. The result establishes intractability for the history-dependent-logging, model-based case posed by Zhang and Jiang (2025, arXiv:2503.01134), under their behavior-marginal definition of revealing. --- ### ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments Authors: Hejia Geng, Zesen Huang, Haoyang Li, Wenbin Li, Koutian Wu, Zihan Zhou, Yuanbo Pang, Weihao Liu, Zigong Xu, Zhiping Li, Zongzheng Zhang, Chuanfei Dong et al. Published: 2026-09-16 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.19134v1 Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE --- ### Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments Authors: João Meneses dos Santos, Arlindo L. Oliveira Published: 2026-09-16 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.19128v1 Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery from failed steps. We extend SwiftSage, a dual-process agent that combines a fast action proposer with a slower planner, using two modular cognitive extensions: an Adaptive Memory Module (AMM) for salience-gated episodic storage and trigger-driven retrieval, and a Self-Reflection Module (SRM) for bounded execution-time validation and corrective intervention. Both modules are implemented as feature-flagged extensions over the same execution substrate, enabling controlled ablations on ScienceWorld. Across four configurations---baseline, baseline+AMM, baseline+SRM, and the full system---the full system achieves the best mean final score (64.62), success rate (43.17%), and successful-step efficiency (19.33 steps), while SRM is the strongest standalone contributor. The results suggest that execution-time control is the dominant bottleneck in this setting, while episodic memory becomes most useful once the runtime loop is stabilized. --- ### Affora: A Design System for Agent-Friendly Interfaces Authors: Jin Gao Published: 2026-09-16 Categories: cs.HC, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.19125v1 Computer-use agents increasingly operate software designed for people, but interfaces often leave actions or task state unclear to machine readers. We present Affora, a design system that supports both readers while preserving visual freedom and familiar human workflows. Three controlled studies examine component implementations, visual variation, and interaction-design principles. Their findings inform guidance from individual components to complete sites, supported by reusable implementations and executable checks. Agent performance depends on the interaction meaning available through its interface representation; substantial visual variation remains possible when that meaning is preserved. Evaluation on independently authored interfaces shows gains where Affora addresses existing deficits, but limited effects where those deficits are absent or outside its coverage. A workflow case provides preliminary evidence of reduced interaction cost. Affora connects user experience and agent experience through a shared interface rather than a separate agent-only surface. --- ### Flag Game: A Toy Model for Mechanistic Swarm Interpretability Authors: Elizabeth Pavlova, Hidenori Tanaka Published: 2026-09-16 Categories: cs.AI, cond-mat.dis-nn, cond-mat.stat-mech, cs.MA, physics.soc-ph arXiv: https://arxiv.org/abs/2609.19124v1 Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formation and spread of beliefs about the world, and mechanistic understanding is crucial for collective alignment. To this end, we introduce the Flag Game, a toy model for studying the mechanisms of collective belief formation. Concretely, a hidden country flag defines the ground truth, and each bounded agent directly observes only a private crop but can exchange beliefs and weigh social evidence from peers. Despite its simplicity, the Flag Game reproduces rich collective phenomenology: non-monotonic scaling of performance with population size, accuracy gains from social-awareness prompting and team diversity, and strong effects of organizational structure. In particular, we identify that collective belief collapse at small population sizes turns into collective belief polarization as the population grows. This polarization causes the performance decline at large population sizes, but creates diversity in collective beliefs. Finally, we dissect the mechanisms underlying collective belief collapse and polarization with two complementary approaches. We first introduce social circuit attribution, a technique to predict which agent, and what view, matters most to collective dynamics, and verify its predictions by causal interventions on agents, tracing how agent patching changes collective outcomes. However, the efficacy of causal interventions on agents decreases as the population grows. We therefore develop a statistical mechanical theory for larger populations and verify that it matches the empirical phase diagram. Together, these results take a first step toward mechanistic swarm interpretability, a science of how the properties of individual agents and their communication give rise to emergent collective behavior. --- ### Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation Authors: Meng'en Qin, Yinchen Liu, Mingxuan Cui, Youlu Xing Published: 2026-09-16 Categories: cs.CV, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.19122v3 Visual signals require compact yet sufficient representations for robust downstream prediction. Convolutional sparse coding (CSC) provides an explicit mechanism for suppressing redundant components while preserving signal content, but its sparsity coefficient is often manually selected during training. We propose a training-adaptive convolutional sparse coding framework for robust visual signal representation. Specifically, we unfold the CSC optimization with the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) and treat the sparsity coefficient as a differentiable variable jointly learned with the network parameters. From the information bottleneck perspective, this coefficient controls the trade-off between information retention and compression: the sparsity term promotes compact representations, while the reconstruction term together with task loss preserves task-relevant signal content. We further introduce a label-free post-training strategy that adjusts the compression strength for corrupted inputs with the main network parameters fixed. Experiments on CIFAR and ImageNet demonstrate competitive clean-data recognition and greatly improved robustness under different input perturbations. --- ### Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Signal Representation Authors: Meng'en Qin, Yinchen Liu, Mingxuan Cui, Youlu Xing Published: 2026-09-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19122v1 Visual signals require compact yet sufficient representations for robust downstream prediction. Convolutional sparse coding (CSC) provides an explicit mechanism for suppressing redundant components while preserving signal content, but its sparsity coefficient is typically fixed and manually selected. We propose an adaptive convolutional sparse coding framework for robust visual signal representation. Specifically, we unfold the CSC optimization with the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) and treat the sparsity coefficient as a differentiable variable jointly learned with the network parameters. From the information bottleneck perspective, this coefficient controls the trade-off between information retention and compression: the sparsity term promotes compact representations, while the reconstruction term together with task loss preserves task-relevant signal content. We further introduce a label-free post-training strategy that adjusts the compression strength for corrupted inputs with the main network parameters fixed. Experiments on CIFAR and ImageNet demonstrate competitive clean-data recognition and greatly improved robustness under different input perturbations. --- ### Track, Articulate, Act: Generating Articulation from Casual Human Videos Authors: Jiaming Zhang, Homanga Bharadhwaj Published: 2026-09-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.19119v1 Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes in object state. In this work, we study articulated objects such as doors, drawers, cabinets, laptops, ovens, and hinged containers that are ubiquitous in daily life and present unique challenges for embodied interaction. These objects cannot be represented by a single pose; their motion depends on the underlying parts and joints. We introduce a real-to-sim framework that reconstructs a simulation-ready articulated object and hand-object interaction from a casual monocular RGB video, without RGB-D or multi-view input, prior scans, manually specified joints, or robot demonstrations. Our key insight is that dense 3D point tracks provide an embodiment-agnostic articulation cue: points on the fixed link remain approximately stationary, while points on the moving link follow coherent revolute or prismatic motion. Our method segments the links, estimates the joint and its state trajectory, reconstructs an articulated asset, and aligns the recovered 3D hand motion with the object. Central to our approach is a modular recipe that repurposes powerful pretrained models for single-image 3D reconstruction, mesh segmentation, and 3D scene flow, connecting their predictions through explicit geometric reasoning to infer articulation. We use the reconstructed articulated object and the human hand trajectory to replay interactions through contact in MuJoCo. The framework shows how pretrained vision models and explicit motion reasoning can turn casual human videos into articulated object models suitable for downstream embodied interactions. https://track-articulate-act.github.io/ --- ### Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry Authors: Peter Potash Published: 2026-09-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.19113v3 We evaluate six frontier language models on the two-agent $\log_2 N$-Questions game (Potash et al., 2019) to measure self-communication across an information asymmetry. A questioner with access to $N$ candidate Wikipedia lead paragraphs ($N = 4$ to $1024$) must identify a secret target using exactly $\log_2 N$ binary questions answered by an agent from the same provider that sees only the target. Across 408 games, win rate decays cleanly as a geometric power of horizon length, $p^{\log_2 N}$ ($p \approx 0.93$). Per-round failure rates are flat across the horizon, indicating that errors compound because more rounds must succeed rather than because individual rounds grow harder. Adjudication across three independent judges shows that losses divide between single-agent answer errors and discrimination failures, which become undetectable and unrecoverable under the two-agent structure rather than from channel breakdown. Claude Opus 5 lags behind due to systematic false-negative answers (82% answer errors), whereas the five leading models (GLM-5.3, GPT-5.6 Sol, Grok 4.6, Gemini 3.8 Flash, and Kimi K3) are closely clustered. Maximizing information gain requires structural partitioning (e.g., splitting on document titles), and neither reasoning-token expenditure nor API cost correlates with success ($r = -0.05$), highlighting communicative reliability as a distinct bottleneck from inference compute. --- ### Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models Authors: Peter Potash Published: 2026-09-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.19113v1 We evaluate six frontier language models on the two-agent $\log(N)$-Questions game. A questioner sees $N$ Wikipedia lead paragraphs and must identify a secretly chosen target using exactly $\log_2 N$ yes/no questions. An answerer sees only the target and the question, and replies with one word. Both roles run on the same provider, so the game measures how well a model communicates with itself across an information asymmetry. We run 408 games over document sets of 4 to 1024 paragraphs at a total API cost of \$363. One model finishes well behind the others: Claude Opus 5 wins 28 of 68 games, against 45 to 56 for GLM-5.3, GPT-5.6 Sol, Grok 4.6, Gemini 3.8 Flash and Kimi K3. The leading five are only marginally separable. Pooling those five, win rate declines with set size at $r=-0.973$ and is fit by a single per-round reliability parameter. The form is $\text{win}=p^{\log_2 N}$ with $p=0.928$. Losses divide into answer errors and discrimination failures in roughly equal measure, and models almost never name a document their own evidence excludes. Every unanimous answer error from the weakest model was inspected: 32 of 34 are ``No'' answers, on properties stated in the document's first sentence, under an instruction that explicitly warns against defaulting to ``No''. Information per question, estimated from answer balance, correlates with win rate at $r=+0.88$. The only two models to extract a full bit per question are the only two that partition on document titles, a strategy absent below $N{=}32$ and used in a quarter of questions above it. Reasoning-token expenditure varies $4.5\times$ across models with little relation to success, and the trace grows as the candidate set shrinks without a matching gain in reliability. --- ### How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents Authors: Zixi Chen, Akshay Vegesna, Samip Dahal, Andrew Gordon Wilson Published: 2026-09-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19107v2 Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pre-training, leading to power-law improvements in performance as computation increases. As an anchoring point, we consider the architectural formulation of looped transformers. Although not typically used in this way, looping, also known as recursive depth, provides a mechanism for model growth, by increasing the number of loops during training. Model growth, with and without shared weights, provides the biggest changes to the scaling exponents. In particular, a 7.4B model growth architecture matches GPT-3 13B on CORE with roughly $20\times$ less compute, and has compute efficiency gains that increase with scale. Moreover, simply using a boundary operator in a vanilla transformer, which normalizes and injects an earlier block, also provides an exponent increase, although to a lesser extent. In the data-constrained, multi-epoch setting, standard looping has a useful regularizing effect, where we find it is compute-optimal to increase the number of loops with scale. These results can be understood through the lens of computational depth: for a given computational budget, we wish to increase the usable depth of the transformer, which can lead to efficiency gains that increase with scale. --- ### How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents Authors: Zixi Chen, Akshay Vegesna, Samip Dahal, Andrew Gordon Wilson Published: 2026-09-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19107v1 Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pre-training, leading to exponential improvements in performance with increases in computation. As an anchoring point, we consider the architectural formulation of looped transformers. Although not typically used in this way, looping, also known as recursive depth, provides a mechanism for model growth, by increasing the number of loops during training. Model growth, with and without shared weights, provides the biggest changes to the scaling exponents. In particular, a 7.4B model growth architecture matches GPT-3 13B on CORE with roughly $20\times$ less compute, and has compute efficiency gains that increase with scale. Moreover, simply using a boundary operator in a vanilla transformer, which normalizes and injects an earlier block, also provides increasing compute-efficiency gains, although to a lesser extent. In the data-constrained, multi-epoch setting, standard looping has a useful regularizing effect, where we find it is compute-optimal to increase the number of loops with scale. These results can be understood through the lens of computational depth: for a given computational budget, we wish to increase the usable depth of the transformer, which can lead to efficiency gains that increase with scale. --- ### rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference Authors: Kaijun Zhou, Zhiyang Li, Le Chen, Jinyu Gu Published: 2026-09-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.19104v1 Factory work is a promising early scenario for embodied AI: assigning repetitive manual jobs to robots has clear economic payoff, and a structured station keeps the jobs tractable for current policies. Vision-Language-Action (VLA) models now dominate as the policy paradigm for these robots. The inference latency of VLA models directly affects robot responsiveness and motion smoothness. However, existing VLA inference frameworks do not fully exploit the characteristics of embodied workloads or account for the distinct bottlenecks across different stages of VLA inference. In this paper, we first characterize embodied workloads and identify substantial task similarity across repeated robot executions. We further find that such similarity extends beyond observations and action trajectories to internal model states. Drawing on these observations, we present rMuscle, a real-time VLA inference framework inspired by human muscle memory. It exploits cross-execution similarity through a dual-phase muscle-memory cache. The Context Cache reuses visual-token outputs to reduce computation, while the Action Cache reuses neuron activation patterns to reduce weight accesses. We keep both the cache memory footprint and access overhead low through online cache recomputation, sliding-window cache retrieval, and mask sharing across consecutive denoising steps. rMuscle achieves 1.29-1.42X speedup on RTX 4090 and Jetson Thor across LIBERO, RoboTwin, and physical manipulation tasks, while maintaining the original success rates on real-world robots. --- ### Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations Authors: Leon Bergen, Usha Bhalla, Andrew Lee, Barak Widawsky, Linas Nasvytis, Connor Watts, Siddharth Boppana, Sidharth Baskaran, Dron Hazra, Michael Byun, Atticus Geiger, Owen Lewis et al. Published: 2026-09-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.19101v1 As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model representations? This work analyzes how reward hacking is represented internally in frontier open source LLMs, and how those representations can be used to understand and discover the range of hacking behaviors a model displays. In particular, we find that simple difference of means vectors coherently represent reward hacking in Kimi K3, GLM 5.2, and Qwen 3.8 Max across a variety of behaviors in common evaluations. Despite their simplicity, these vectors are both generalizable and interpretable, and we can use them to reliably detect reward hacking. We first evaluate reward hacking in commonly reported benchmarks like DeepSWE and SWE-bench, finding that models reward hack excessively in these environments; GLM 5.2 hacks in 57.2% of rollouts on DeepSWE and in 73% of rollouts on SWE-bench. Catching these requires monitors; LLM monitors are effective, but expensive detectors. We show that DoM vectors are similarly effective but virtually free, catching 3.1% more hacks in Kimi K3 and 7.9% fewer hacks in GLM 5.2 on DeepSWE at a monitor matched false positive rate. DoM vectors run on the chain-of-thought also predict reward hacks in the model's subsequent actions, meaning we can run them online and catch potential hacks before they occur. Finally, we analyze probe-hits that LLM monitors do not catch and discover other undesirable behaviors, as well as show transfer to finding hacks in non-SWE evaluations. Together, these results provide evidence that simple, white-box methods can be used to scalably study and monitor reward hacking behaviors in frontier open source models --- ### Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory Authors: Michael M. Craig, Riley J. Hickman, Yingshan Ma, Rémi Piché-Taillefer, Christine Allen, Pauric Bannigan Published: 2026-09-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19099v1 Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulations remains experimentally intensive. We present Andromeda 2, an agentic system that reasons over structured in-house experimental evidence and invokes computational and experimental tools to design and execute successive formulation batches. Using a miniaturized automated laboratory at a matched budget, we benchmark it against Andromeda 1, a probabilistic optimization model deployed across dozens of live development projects, and a wet-lab design-of-experiments (DoE) campaign. For paclitaxel, Andromeda 2 achieved a 50% high-performance hit rate versus 17% for Andromeda 1 and 2% for DoE, and identified 12 formulations meeting all four target product profile (TPP) objectives versus 6 and 0, respectively. Median $AUC_{10-240}$ was 70.1, 12.0, and 3.5 mg$\cdot$min/mL, while maximum AUC was comparable between Andromeda 2 and Andromeda 1. A selected full-TPP formulation achieved an apparent effective paclitaxel loading of $19 \pm 5\%$ w/w at the first FaSSIF measurement, approximately 3.3-fold higher than the 5.7% w/w loading reported for a published paclitaxel S-SEDDS. A controlled ablation showed that access to structured in-house experimental evidence increased mean AUC by 34%. --- ### Prepared Or Unprepared? Evaluating Healthcare Workforce Readiness for Clinical Adoption of Artificial Intelligence in Nigeria Authors: Abbas M. Rabiu, Abdulrazaq A. Zubair, Um-mulkhairi Ibrahim, Tolulope Olusuyi, Shaheeda Farouq, Safwan M. Dafi, Adaobi C. Emegoakor, Yewande Gbadamosi, Maruf Adewole Published: 2026-09-16 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2609.19096v1 Artificial intelligence (AI) is increasingly integrated into healthcare systems worldwide, yet its successful clinical adoption depends critically on workforce readiness, particularly in low- and middle-income countries (LMICs) where infrastructural and training gaps persist. This cross-sectional study evaluated awareness, attitudes, preparedness, and barriers to AI adoption among 761 healthcare professionals across multiple disciplines and practice settings in Nigeria. Data were collected between December 2025 and March 2026 using a structured, validated questionnaire. Overall awareness of AI in healthcare was high (92.6%); however, objective knowledge and self-reported preparedness remained limited, with 40.9% reporting low or very low knowledge and only 63.0% feeling adequately prepared. Willingness to adopt AI was high: 92.5% expressed interest in training, and 78.7% supported inclusion of AI education in undergraduate curricula. Key barriers included lack of training (84.7%), poor infrastructure (71.1%), high cost of AI tools (61.0%), fear of job displacement (60.6%), ethical concerns (52.9%), and data privacy concerns (52.7%). Significant differences in preparedness were observed across geopolitical zones (chi-square (5) = 24.28, p < 0.001), and awareness differed across professional groups (chi-square (6) = 68.38, p < 0.001). Attitudes toward AI differed significantly across professional groups (F = 3.32, p = 0.003), with professionals who felt prepared demonstrating more positive attitudes (mean = 3.74) compared to those who did not (mean = 3.46). These findings reveal a critical disconnect between high awareness and actual readiness, underscoring the need for targeted training, infrastructure investment, and clear implementation frameworks to bridge the gap between AI technological potential and clinical reality in resource-constrained settings. --- ### Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation Authors: Daniel P. Jeong, Charles Q. Li, Hossein Hosseiny, Nitya M. Bhalla, Fatma Uyar Morency, Pradeep Ravikumar, Zachary C. Lipton, Michael Oberst Published: 2026-09-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.19093v1 Radiologists follow heterogeneous reporting practices. Two radiologists examining the same image and identifying the same clinical findings might nevertheless compose superficially distinct reports, varying in terminology, shorthand, formatting, and level of detail. These variations in reporting norms represent an under-appreciated obstacle in efforts to evaluate AI-based radiology report generation (RRG) models, where machine-generated reports are typically assessed based on their concordance with human-generated references. In this paper, we quantify the sensitivity of established evaluation metrics to variations in reporting practices, revealing impacts large enough to alter the rankings of models. We introduce a radiologist-informed taxonomy of variations in radiology reporting practice and a method (ReRef) that rewrites reference reports along the axes of our taxonomy while preserving clinical interpretation. For instance, when comparing the performance of nine RRG models on MIMIC-CXR using RadCliQ-v1, condensing the discussion of normal findings in the reference reports causes Libra to drop from first to second place while CheXOne rises from third to first. Our results suggest that many current metrics fail to decouple clinical interpretation from conformity to reporting practices and that choosing the ``right'' references that accurately reflect the desired reporting practices can be important in practice. To support future research, we release MIMIC-CXR-Ext-ReRef, a radiologist-validated dataset of 120 (original, alternative) reference report pairs derived from MIMIC-CXR. --- ### Securing quantum error correction against misleading advice from AI agents Authors: A. Barış Özgüler Published: 2026-09-16 Categories: quant-ph, cs.AI, cs.CR, eess.SY arXiv: https://arxiv.org/abs/2609.19090v1 Can an attacker turn influence over an artificial intelligence (AI) adviser into a harmful quantum error-correction update? We identify an ambiguity in passive syndrome records that obstructs recovery selection, then show how additional calibration measurements support certified recovery updates under uncertainty and drift. In an odd-distance square toric code with error-free preparation, syndrome measurements, and recovery operations, opposite coherent $X$ rotations produce identical passive syndrome-history distributions. Yet a fixed phase correction can help at one sign and harm at the other. A terminal logical measurement on known encoded calibration states supplies the missing sign information. A separate evaluator accepts an update only when calibration uncertainty and a justified drift bound certify improvement over the current recovery, without assuming that the adviser recommends correctly. In simulated advice attacks, calibration-confidence checks reject harmful proposals while retaining beneficial updates under honest advice. We derive sufficient limits on calibration age that require improvement through deployment. In matched simulations, a validated channel-specific bound retains more beneficial updates than the general bound after accounting for evaluation time, while preventing the tested harmful activations under the stated drift assumption. A separate surface-code experiment includes stochastic circuit faults and noise changing during acquisition. Deterministic controllers achieve at least as many beneficial updates with the same observations. Violating the drift assumption permits harmful acceptance in the toric experiment. The results identify information required for recovery selection, establish conditional guarantees against harmful updates, and quantify the recovery improvements forgone through conservative acceptance. --- ### MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education Authors: Luyao Zhu, Xun Wei Yee, Wei Li, Mun Thye Mak, Wee Siong Ng Published: 2026-09-16 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.19088v1 Large vision-language models have achieved remarkable progress in multi-modal understanding, yet their capabilities in educational settings remain insufficiently evaluated. In AI-assisted language learning, models must interpret artistic imagery, understand its semantic, affective, and cultural content, and reason about visual context to support meaningful interaction. However, existing benchmarks primarily focus on real-world images or domain-specific educational reasoning, providing limited coverage of artistic educational content. To address this gap, we introduce MUSE, a benchmark for evaluating large vision-language models on artistic image understanding in situated educational applications. MUSE decouples image annotation from question generation, enabling diverse tasks with controllable difficulty while reducing annotation effort. It comprises twelve tasks spanning visual perception, semantic and affective interpretation, culture understanding, and compositional reasoning, together with diverse artistic images deliberately curated to center Singaporean and Southeast Asian multicultural contexts alongside Western art traditions, covering multiple themes and difficulty levels. Evaluation of open-source and proprietary models reveals substantial disparities across capability dimensions, particularly in affective interpretation and compositional reasoning. Our analysis further identifies common failure modes and key challenges for developing trustworthy multi-modal models for education. We hope MUSE will serve as a standardized benchmark for advancing multi-modal understanding in situated educational applications. --- ### A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings Authors: Marcus M. Noack, Maher B. Alghalayini, Mark D. Risser Published: 2026-09-16 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2609.19083v1 Kernel methods, and Gaussian Processes (GPs) in particular, require a Hilbertian distance measure---one whose square is conditionally negative definite (CND)---to guarantee positive semi-definiteness (PSD) of the kernel matrix; a condition that fails for many natural input spaces, including smooth manifolds and spaces of probability distributions. We propose the Sparse Landmark Embedding (SLE) kernel, which eliminates this requirement entirely. Each input is embedded into a sparse feature vector via compactly supported bump functions centered at all |D| training points; applying any standard PSD kernel in this embedding space yields a kernel that is provably PSD for arbitrary distance measures. The compact support automatically controls embedding sparsity, keeping kernel matrices well-conditioned and computationally tractable despite the high ambient dimension. We provide theoretical guarantees on PSD, sparsity, stability, and universal approximation, and demonstrate, using geodesic and Wasserstein distances, that the SLE kernel matches or substantially exceeds domain-specific baselines in both predictive accuracy and uncertainty quantification. --- ### Probabilistic Linear Explanations Authors: Frederic Koriche, Jean-Marie Lagniez, Chi Tran Published: 2026-09-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.19077v1 Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human cognitive limits by involving too many features, while probabilistic relaxations have remained largely limited to categorical classification. We present a unified framework for probabilistic explainability based on sparse, anchored linear models, applicable to both binary classification and continuous regression. By mapping instances to the Boolean hypercube, our linear explanations strictly generalize subset-based approaches: they capture both the magnitude and direction of feature contributions while enforcing a prescribed sparsity budget $k$. We show that minimizing the relevance error for such explanations is \ClassNPPP-hard when the underlying model is a neural network, and we relate this intractable objective to a tractable surrogate---the fidelity error. For a parameterized family of local distributions, the relevance error of any $k$-sparse explanation is bounded by its fidelity error up to a multiplicative factor that remains small locally. We address the resulting empirical problem using two complementary approaches: a Mixed Integer Programming (MIP) formulation that yields provably optimal empirical solutions while maintaining polynomial sample complexity, and a polynomial-time Iterative Hard Thresholding (IHT) algorithm with provable approximation guarantees. Empirical evaluations show that, unlike state-of-the-art baselines such as LIME and MAPLE, our explanations satisfy both the anchoring and sparsity constraints by construction, while consistently achieving lower relevance error. ---