# Research Papers — 2026-09 · bundle page 183 of 266 > Full-text markdown of papers #9101–9150 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/183 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/182.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/184.md) ### Task-Aware Federated Fine-Tuning for MoE-based Large Language Models Authors: Tingqi Wang, Hongyu Ke, Haoxin Wang, Rafal Angryk, Zhipeng Cai Published: 2026-09-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.13395v1 Mixture-of-Experts (MoE) has become a widely adopted architecture for Large Language Models (LLMs), as it improves model capacity while limiting computational overhead through sparse expert activation. This property makes MoE-based LLMs particularly attractive for resource-constrained distributed environments. However, federated fine-tuning of MoE-based LLMs remains challenging under heterogeneous client data. Since clients often correspond to different task preferences, directly aggregating their local updates may weaken expert specialization and introduce conflicting update directions on shared experts. To address these challenges, we propose FedTAR, a task-aware federated fine-tuning method for MoE-based LLMs. FedTAR establishes the association between local updates and task preference via routing outputs. Specifically, we apply Singular Value Decomposition (SVD) to both routing features and local updates to extract low-dimensional task coordinates and update directions. Based on the task coordinates, FedTAR performs intra-cluster aggregation among clients with similar task preferences and inter-cluster aggregation across different task groups. The aggregated update is then reconstructed through the learned task-to-update mapping, ensuring that the final update remains aligned with task-specific optimization directions. In this way, FedTAR preserves expert specialization and mitigates destructive interference among heterogeneous clients. We evaluate FedTAR on four benchmark tasks under different non-IID settings. Experimental results demonstrate that FedTAR consistently outperforms strong federated fine-tuning baselines and achieves state-of-the-art performance. --- ### Privacy-Preserving Deep Joint Source-Channel Coding with In-Loop Concept Erasure Authors: Rami Eid, Maria Slim, Mariette Awad, Hadi Sarieddeen Published: 2026-09-11 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.13393v1 Deep joint source-channel coding (DeepJSCC) transmits learned semantic features efficiently but can leak sensitive attributes such as gender, race, or speaker identity. We propose LEAPSC (LEACE-in-the-loop privacy for semantic communication), whose core contribution is the integration of in-loop least-squares concept erasure (LEACE) within a variational information bottleneck (VIB) encoder. By periodically refitting the projection operator during training, LEAPSC couples the encoder dynamics to the erasure mechanism, driving attribute-conditional mean differences toward zero within each task-label group on the fitting sample. Additional components, namely conditional value-at-risk (CVaR) tail-sensitive privacy, feature-wise linear modulation (FiLM) signal-to-noise ratio conditioning, and Lagrangian dual ascent, improve robustness across channel conditions and over the high-leakage tail of samples. On CelebA, FairFace, and Google Speech Commands, LEAPSC reaches task accuracy of 0.862, 0.755, and 0.925 respectively, with attacker accuracy at or below the label-only floor on CelebA (0.548 vs. floor 0.580) and within 2 percentage points (pp) of chance elsewhere, improving over an information-bottleneck adversarial baseline (IBAL) at a matched 52-epoch budget by +3.6, +2.5, and +1.3 pp (Welch's t-test, p=0.019 on CelebA). --- ### RFCLLM: Evaluating LLMs' Reasoning Ability of Network Protocol State Machines Authors: Anqi Chen, Dan Goldwasser, Cristina Nita-Rotaru Published: 2026-09-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13389v1 Mapping textual specifications into formal representations is essential for ensuring the correctness of protocol designs and implementations. LLM-generated mappings, used for networking security or testing, are assumed to capture a perfect understanding of the specification, which may not hold in practice. The goal of this paper is to assess the extent to which LLMs can interpret the specification correctly. We examine the degree to which an LLM's implicit representation of a finite-state transition system-defined via natural language descriptions-aligns with a manually generated ground-truth model. We designed 4 tasks and 1482 task queries for 16 protocols. We evaluated different judge biases, observed the inherent difficulty gaps between tasks, looked into the effect of 4 context types, and the influence of protocol characteristics. Our work contributes to a step toward verifying whether LLMs can really be trusted in FSM (Finite State Machine) reasoning of protocol specifications. --- ### ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Authors: Jiyan He, Guang Liang, Hao Liu, Haoxiang Guan, Jinbo Sun, Junyi Guo, Wenjun Feng, Yantai Xie, Yifei Shen, Bin Shao, Chuyang Wei, Kai Chen et al. Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13356v2 In this work, we present ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, system, and algorithmic efficiency. ZGCM-1 is founded on a core premise: compact models cannot passively memorize the open web, but can overcome parametric capacity limits by coupling deliberate internal thinking with active external tool use. To support this paradigm across a 256K context, we develop an end-to-end, high-efficiency open training recipe: Architecture & System Co-design: interleaved gated sliding-window and full attention, and a stable FP8 Muon optimizer; Progressive Curriculum & MDP Mid-Training: context scaling across 16K, 64K, and 256K, and the reformulation of interaction traces into Markov Decision Processes. Furthermore, we establish an AI-native R&D workflow where agent swarms autonomously manage cluster operations, data curation, and rapid diagnostic evaluation. Extensive evaluations show that ZGCM-1-7B is competitive across 7B model family on general benchmarks. On several challenging mathematical reasoning and agentic search suites, it remains competitive with frontier models orders of magnitude larger, such as Qwen3-235B-A22B and GLM-5.1. We also show that our pre-training design offers a ~4.2x efficiency improvement in 16K pre-training time-to-loss. Across the full development lifecycle, we distill eight actionable empirical findings-spanning architectural scaling, SFT quality pruning, long-context generalization, and agentic co-training dynamics. To facilitate community research, we open-source model weights from the pre-training, mid-training, and post-training stages, intermediate checkpoints, training code, per-stage data and data recipes, and W&B logs. --- ### SkillAtlas: An Attack Trace Library for Agent Skills Authors: Yuxin Tian, Zenghao Duan, Liang Pang, Zhiyi Yin, Xueqi Cheng Published: 2026-09-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.13353v3 Agent skills are reusable units for language-model agents, but their risks emerge through model decisions, user context, tool calls, and execution feedback rather than through stable signatures or a single sandbox run. Existing static, dynamic, and benchmark-style evaluations rarely preserve public evidence that can be inspected, searched, and reused. We present SkillAtlas, a hosted attack trace library that converts private agent-skill security report bundles into reviewed, redacted, and searchable public cases. The library contains 3,014 cases, 6,589 traces, 151,131 steps, 233 affected skills, and 8 risk categories; 42.5% of successful cases first become successful after a non-success initial round, and trajectory-grounded labels improve pre-execution guard accuracy to 0.770. --- ### Real-time Learning and Evolution in Robotic Art Installations Authors: Sofian Audry, Stephen Kelly Published: 2026-09-11 Categories: cs.HC, cs.LG, cs.NE, cs.RO arXiv: https://arxiv.org/abs/2609.13352v1 We present three robotic art installations which explore the aesthetics of adaptive behavior. Through embodied machine leaning and digital evolution, these works draw viewers into an artificial ecosystem in which open-ended novelty, trial-and-error learning, competition, and cooperation emerge in real time. Research-creation practices are examined in relation to these works, focusing on how they redefine the role of artists within a human-machine collective while examining points of convergence and divergence between artistic and engineering approaches to adaptive robotics. The systems in question use learning and evolutionary processes not as a means to optimize a specific solution, but as an aesthetic experience on its own, suggesting new modes of interdisciplinary art-science research. Finally, we discuss strategies and practices to elevate the aesthetic experience for audiences, including contexts of presentation as well as temporal and material considerations for artworks based on embodied adaptive systems. --- ### Beyond Point Forecasts: A Survey on Probabilistic Forecasting for Time Series and Spatiotemporal Data Authors: Donia Besher, Rajdeep Pathak, Madhurima Panja, Tanujit Chakraborty Published: 2026-09-11 Categories: stat.ML, cs.LG, econ.EM, stat.AP arXiv: https://arxiv.org/abs/2609.13345v1 Probabilistic forecasting is central to decision-making under uncertainty, yet its methodological landscape has become increasingly fragmented across temporal and spatiotemporal forecasting, statistical modeling, machine learning, and deep generative modeling. This survey develops a unified perspective by organizing probabilistic forecasting methods according to where and how uncertainty is introduced into the forecasting pipeline. Our taxonomy connects model-agnostic approaches including ensembles and distribution-free calibration, with model-intrinsic approaches spanning Bayesian modeling, parametric predictive distributions, distributional regression, and modern generative models, and further examines the emerging role of time series foundation models. Beyond methodological synthesis, we identify the assumptions, computational demands, and forms of uncertainty represented by different paradigms, and translate these distinctions into data-driven and domain-specific guidance for method selection. We complement the survey with a cross-paradigm empirical study on univariate, multivariate, and spatiotemporal forecasting tasks. The results reveal that no single uncertainty-quantification paradigm dominates across settings. Calibration, sharpness, predictive accuracy, and computational efficiency can lead to substantially different model preferences, while expressive generative models and zero-shot foundation models exhibit markedly different accuracy-efficiency trade-offs. Lastly, we identify unresolved challenges surrounding uncertainty in evolving dependency structures, physics-informed predictive distributions, forecasting extreme events, handling count-valued, directional, and continuous-time series, and the development of unified software resources. Our survey provides both a conceptual framework and a practical roadmap for probabilistic forecasting research. --- ### Stochastic Gradient Descent over P2 Authors: Maria Oprea, Qin Li, Yunan Yang Published: 2026-09-11 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2609.13343v2 Stochastic gradient descent (SGD) admits diffusion approximations that replace the complicated randomness of stochastic gradients by Gaussian noise, providing a powerful tool for understanding its dynamics and long-time behavior. We investigate whether an analogous approximation principle holds for optimization over probability measures, where the objective is a functional defined on the Wasserstein space P2. The nonlinear geometry and infinite-dimensional nature of P2 prevent a direct extension of the classical Euclidean theory. Using Lions differentiability, we lift the problem to a linear Hilbert space, where higher-order differential calculus becomes available. We then construct a Gaussian random-field approximation whose velocity field matches the mean and covariance of the original stochastic gradient. By exploiting this moment matching through higher-order Taylor expansions, we show that the Gaussian approximation captures the SGD dynamics with second-order weak accuracy. Our result provides a rigorous foundation for replacing sample-driven randomness by analytically tractable Gaussian fluctuations in stochastic optimization over probability measures. --- ### ProtoCAM: Interpretable Few-Shot Mask-Guided Prototypical Learning for Breast Lesion Classification in Ultrasound Imaging Authors: Ashkan Ebadi Published: 2026-09-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.13340v1 Breast ultrasound imaging plays an important role in the early detection and diagnosis of breast cancer, particularly for patients with dense breast tissue. However, developing reliable deep learning models for ultrasound analysis is challenging due to limited annotated medical data and the need for interpretable predictions. To address these challenges, this paper proposes ProtoCAM, an explainable few-shot learning framework for breast lesion classification that integrates mask-guided feature encoding, prototypical metric learning, and gradient-based visual explanations. The proposed approach leverages lesion masks to guide feature extraction and constructs class prototypes within an embedding space to enable robust classification under limited training samples. The framework was evaluated on the BUSI dataset using a stratified group k-fold cross-validation protocol to prevent patient-level data leakage. Experimental results demonstrate ProtoCAM's high performance in low-data scenarios. In a 3-way 5-shot setting, the proposed method achieves a macro F1-score of 0.910, representing a substantial improvement over standard supervised CNN models. Among the evaluated backbone networks, ResNet18 achieved the best performance, reaching a macro F1-score of 91.65% under a 15-shot configuration, providing interpretable insights into the classification decisions. These results highlight the potential of explainable few-shot learning frameworks for reliable computer-aided breast cancer diagnosis in data-scarce medical imaging environments. --- ### Bridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework Authors: Kazi Abrar Mahmud, Nilotpaul Kundu Dhurubo, Tamal Kirttonia, Sabbir Hossain Ujjal, Mohammad Ariful Haque Published: 2026-09-11 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.13335v1 Large Language Models (LLMs) have enabled more natural human-robot interaction, but open-source models often exhibit unstable long-horizon reasoning and inefficient action execution when deployed in agentic robotic frameworks. This paper presents an enhanced ROS-Agent based architecture that improves task reliability and execution efficiency for agentic robotic systems using open-source LLMs. The proposed system introduces a novel intermediate mechanism, termed the MetaTool, which enforces structured planning prior to action execution. Given a natural-language command, the MetaTool induces the LLM to generate a pseudo-code plan of intended tool invocations, which is stored in the ROS-Agent's scratchpad and persists throughout execution. By explicitly separating planning from execution, the proposed approach reduces execution loops and improves deterministic behavior. The architecture is validated on a custom mobile robotic platform with multimodal perception and motion control capabilities. Experimental results on real-world interactive tasks demonstrate improved task completion and contextual consistency, with up to ~24% gains on complex tasks compared to the baseline framework. --- ### The Agentic Company OS: Substrate Inversion for Sustained Enterprise Agent Deployment Authors: Oliver Aleksander Larsen, Mahyar T. Moghaddam Published: 2026-09-11 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.13334v1 Enterprise AI agents often succeed in a demonstration and then stall once they must operate day after day. An industry report estimates that most pilots never reach production and that deployed systems rarely retain feedback or improve over time, while agent benchmarks show single-run successes masking unreliable repetition. We argue that these failure modes share a common architectural root: agents reason over data structured for human operators and traditional applications, not for the language models that power them. This position paper proposes that companies deploying agents in sustained operation should rebuild their cognitive substrate, the shared environment agents read as working context, around representations matched to that reasoning surface, isolating schema translation to the action boundary. Markdown is the instantiation available today, not a proven agent-native primitive. Two mechanisms ground the argument: context-bandwidth asymmetry, the gap between one-pass reading of connected prose and field-by-field typed access that strips relations; and cross-loop coupling, the claim that action, skill, and policy loops compound only if they share one substrate. A four-layer framework (Data, Knowledge, Intelligence, Governance) operationalizes the position, with a Sync Agent enforcing the action boundary and a per-skill trust gradient, making governance and auditability structural properties of the substrate. The position revives the shared-substrate tradition of classical multi-agent systems under LLM-era economics. We analyze the main objections and risks, including indirect prompt injection on the compile path, and outline a research agenda for evaluating substrates directly. --- ### Global-Local Contextual Progressive Expansion Network for Martian Landslide Segmentation in Multimodal Remote Sensing Imagery Authors: Leo Thomas Ramos, Sidike Paheding, Abel A. Reyes-Angulo, Rajaneesh A., Sajinkumar K. S., Angel D. Sappa, Thomas Oommen Published: 2026-09-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13332v1 Automated landslide segmentation on Mars is one of the important tasks for understanding its surface processes, and all will aid in future space exploration. However, it remains a relatively underexplored open challenge because landslide morphology is highly variable, foreground regions are often sparse or irregular, and orbital observations combine heterogeneous spectral and topographic cues. In this context, this work investigates the capability of deep learning to address Martian landslide segmentation through an extensive assessment of modern neural segmentation models. To the best of our knowledge, this is the first study to provide such a comprehensive exploration in this domain. We further propose TransCPLES, a U-shaped network that couples Contextual Progressive Layer Expansion feature extraction with Transformer-based contextual reasoning, enabling the model to capture local geomorphic patterns and broader spatial dependencies for more reliable landslide delineation. Experiments on MMLSv2, a seven-band multimodal Martian landslide dataset, show that TransCPLES achieves the best overall performance when evaluated on geographically distinct samples, with consistent delineation across different landslide extents, stable foreground discrimination, and a favorable balance between accuracy and computational cost compared with several state-of-the-art convolutional, attention-based, and Transformer-based segmentation models. With this work, we hope to provide a useful reference and encourage further research and development in deep learning for planetary remote sensing. Code will be available after publication. --- ### Pedestrian Crossing Intent Classification From Event-Based Vision Using Convolutional Spiking Neural Networks With Temporal Augmentation Authors: Henok Teklu, Mustafa Sakhai, Maciej Wielgosz, Matej Mertik Published: 2026-09-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.13328v1 Anticipating whether a pedestrian will cross the road is safety-critical for autonomous vehicles, requiring real-time inference under challenging conditions including motion blur, high dynamic range, and class imbalance. Conventional frame-based deep networks process redundant RGB data at fixed frame rates, limiting their temporal resolution and energy efficiency. In this work we present an end-to-end pipeline that (i) converts real-world driving footage from the Joint Attention in Autonomous Driving (JAAD) dataset into synthetic dynamic vision sensor (DVS) event streams using the v2e simulator, (ii) augments training with the CARLA-simulated DVS sequences of the DVS-PedX dataset under both normal and adverse weather conditions, and (iii) trains a novel convolutional spiking neural network (Conv-SNN) with clip-consistent DVS augmentation to classify pedestrian crossing intent as binary: crossing or non-crossing. We detail all architectural decisions, the exact leaky-integrate-and-fire neuron dynamics with surrogate-gradient learning, the class-balanced loss formulation, JAAD oversampling at 6x, and a 70/15/15 stratified splitting protocol. The trained model achieves 95.83% accuracy and F1 = 0.9695 on the JAAD DVS test set, 97.79% accuracy and F1 = 0.9478 on normal CARLA DVS, and 94.78% accuracy and F1 = 0.8369 on adverse-weather CARLA DVS, all from a 1.07M-parameter architecture trained on CPU. Compared to prior frame-based approaches on JAAD, our method closes or surpasses the reported accuracy while operating natively on sparse temporal representations. We include a thorough analysis of the convergence behaviour across all 15 training epochs, domain transfer characteristics, and a quantitative comparison with representative related work. --- ### SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image Authors: Yu-Rou Tuan, Hao-Tang Tsui, Nicolas Ugrinovic, Kris Kitani, Xiaoxuan Ma Published: 2026-09-11 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2609.13146v1 Part-aware 3D asset generation enables applications such as editing, articulation, simulation, and fabrication, yet existing methods can generate visually complete individual parts without ensuring that they form a valid physical assembly. Consequently, generated neighboring parts may interpenetrate, lack valid connections, or collapse under gravity. We propose a physics-guided framework for improving single-image part-aware 3D generation with physically compatible geometry and stable connections. Our method resolves inter-part penetration, recovers a contact graph between neighboring parts, and introduces parameterized connectors at their contact surfaces. Using feedback from physical simulation, we refine connector placement, orientation, and dimensions to improve assembly stability while preserving the generated geometry. We further introduce a physics-based evaluation protocol that complements conventional geometric metrics by directly testing assembly validity and stability under gravity. Experiments comparing against multiple part-aware 3D generators show substantial improvements in physical realizability and stability while maintaining geometric quality. We additionally validate the resulting parts through 3D printing and real-world assembly. --- ### Type Diversity Enables Transformers to Generalise Compositionally Authors: Anssi Moisio, Mathias Creutz, Mikko Kurimo Published: 2026-09-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13144v1 Compositional generalisation has been divided into lexical and structural generalisation. Previous work has found that structural generalisation is harder than lexical for Transformers. We propose that this difference is not inherent to Transformers, but due to the high diversity of lexical types and low diversity of structural types in the specific datasets of these previous works. By type diversity we mean the number of different constructors of that type, instead of, for example, the specific word combinations that might populate the structure. To test this, we vary the amounts of type diversity of lexical and structural types in previously published datasets. We create linguistically diverse variants of the COGS and SLOG datasets using Grammatical Framework. We find that type diversity correlates with compositional generalisation equally in lexical and structural test cases, supporting our hypothesis. We note a contradiction with the proposition in previous work that compound divergence explains the difficulty in compositional generalisation tasks. We further investigate the effects of other dataset properties on compositional generalisation, such as the diversity of types other than the novel test structure, and surface properties of the logical semantics format. --- ### SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking Authors: Zhiwei Li, Lei Zhu, Hao Gu, Xiang Hu, Yan Wang, Haitao Mi, Sirui Han, Leo Liang, Zhijiang Guo Published: 2026-09-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13141v1 Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context units (tokens or blocks) for each query. Existing trainable methods usually use a lightweight selector to score context units, followed by hard Top-K selection that blocks gradients from the language modeling loss. Consequently, these methods commonly distill layer-wise dense attention distributions. Although this encourages the selector to rank context units by dense attention weights in the original model, the ranking is not directly aligned with their impact on predictions under a fixed attention budget (i.e., the number of attended context units per query), potentially wasting the limited budget on less useful units. To address this misalignment, we propose Simple Attention Sparsification (SAS), a gated sparse attention mechanism that optimizes context ranking end-to-end with the language modeling loss. The key idea is to inject the selector's continuous scores into attention logits during training, allowing the loss to update the selector through standard backpropagation. We identify several choices crucial for this simple design to work well in practice: placing the gate inside the attention softmax in log form, using normalized softmax gates to calibrate historical context against the always-retained current block, and preserving continuous selector scores so the model learns relative priorities rather than only hard selections. To support long-sequence training, we implement a memory-efficient Triton kernel that integrates SAS into FlashAttention-style computation. Across reasoning, long-context understanding, and agentic tasks, SAS consistently outperforms trainable sparse attention baselines across attention budgets, with especially large gains under tight budgets, demonstrating more effective context ranking for downstream tasks. --- ### Recurrent Dynamic Range Extension Authors: Sebastian Dille, Keru Fu, S. Mahdi H. Miangoleh, Yağız Aksoy Published: 2026-09-11 Categories: eess.IV, cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.13135v1 We present an approach to progressively extend the highlights of an image. Instead of reconstructing the full dynamic range of a complex scene directly, we learn a simpler task first: We extend the dynamic range of an input image by a single exposure value. Once this is mastered, we retrieve the full HDR image for the scene by executing our network recurrently, progressively increasing the dynamic range of the input. Our formulation is agnostic to the input dynamic range and targets a bounded output domain. This enables us to use widely available RAW images for the reconstruction task and adapt adversarial losses to construct realistic images. By incorporating Memory Replay for backpropagation, we can train our network recurrently over multiple inference stages and reduce reconstruction errors. As a consequence, our system reconstructs challenging long-tailed HDR scenes robustly and shows powerful recovery of bright light sources and highlights. --- ### Rethinking Heterogeneous System Disaggregation for Subquadratic Attention Authors: Arya Tschand, Yaosheng Fu, Vikram Sharma Mailthody, Nicolai Oswald, Po-An Tsai, Ritchie Zhao, Oreste Villa, Vijay Janapa Reddi, Karu Sankaralingam Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13134v1 Frontier language models are more aggressively using subquadratic attention to reduce the memory footprint and compute requirements during inference while still delivering frontier accuracy. While existing systems make dense attention-centric disaggregated serving decisions, we show that disaggregating inference around the unique arithmetic intensity and memory footprint of subquadratic attention LLMs can achieve significant throughput and energy efficiency gains on emerging DRAM-based and SRAM-only heterogeneous systems. We introduce SQD (SubQuadratic Disaggregation), a fine-grained heterogeneous disaggregation scheme that splits decode by quadratic and subquadratic attention rather than by operator type, and that applies across subquadratic attention variants. For sparse attention LLMs, we disaggregate decode into top-k selection, which must index through the full KV, and top-k attention plus FFN, which have static memory footprints. For linear and sliding-window attention LLMs, we disaggregate decode into dense attention layers and subquadratic attention layers plus FFN. In an adjusted 8xB200 heterogeneous system proxy, we observe average tokens/J improvements of 53% on GLM 5.2, 31% on Nemotron 3 Ultra, and 56% on Gemma 4 31B over the strongest GPU-only baselines. In an analytical model of a Rubin plus LPX system with fixed power budgets, we observe 1.2x to 1.5x tighter achievable latencies and up to 3.6x higher throughput over the best baseline of attention-FFN disaggregation. Our experiments also reveal architectural insights on chip and interconnect provisioning for next-generation heterogeneous systems serving subquadratic attention. --- ### A Hybrid LSTM-XGBoost Framework for Multi-Horizon Stock Return Prediction Across Diversified Equity Portfolios Authors: Seif ElDein Mostafa, Yahia Ahmed, Farah Datwish, Marwa Solayman Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13125v1 Accurate prediction of equity returns remains a major challenge in computational finance due to the non-stationary, nonlinear, and low signal-to-noise ratio nature of financial time series. This paper proposes a hybrid two-stage architecture that combines a long short-term memory (LSTM) network with an XGBoost gradient-boosted regressor for multi-horizon stock return prediction across a diversified panel of 14 U.S. equities spanning six industry sectors. The LSTM component, comprising two stacked layers with 64 hidden units, processes 60-day sliding windows of five sequential market features to produce 64-dimensional temporal embeddings that encode learned sequential market dynamics. These embeddings are concatenated with 14 hand-crafted technical indicators to form a 78-dimensional hybrid feature vector, which is subsequently passed to an XGBoost regressor tuned via 3-fold cross-validation grid search. The framework is trained on a multi-stock pooled corpus using strict chronological splits and per-stock MinMaxScaling to prevent look-ahead bias, and evaluated across four prediction horizons of 30, 90, 252, and 365 trading days. Experimental results demonstrate that the hybrid model achieves a test RMSE of 0.0949 on the 30-day horizon, roughly one-third that of the standalone LSTM baseline, while marginally matching or surpassing the XGBoost-Only baseline across the majority of stocks. Directional accuracy rises with horizon length, reaching 97.6% at 365 days; we show, however, that this largely tracks the high base rate of positive long-horizon returns in the sample, and we therefore benchmark directional accuracy against a naive always-positive predictor and treat the above-base-rate gap at short horizons as the more informative signal. A composite investment scoring framework derived from multi-horizon predictions is further proposed to support portfolio ranking and decision support. --- ### CMA-OT: Hierarchical Expert Supervision for Dance-to-Music Generation Authors: Jinting Wang, Chenxing Li, Dong Yu, Li Liu Published: 2026-09-11 Categories: cs.AI, cs.SD arXiv: https://arxiv.org/abs/2609.13118v1 Dance-to-music (D2M) generation aims to synthesize music that is rhythmically and stylistically aligned with dance videos. A key challenge arises from the semantic mismatch between sparse dance cues, such as rhythm and style, and the dense information required for music composition, including structure, instrumentation, and expressive dynamics. Existing methods typically rely on these sparse cues and supervise only the final audio output, resulting in poorly learned music representations and generated music with limited musicality and structural coherence. To address these issues, we propose Curriculum-guided Multi-scale representation Alignment with scale-aware Optimal Transport (CMA-OT), a novel paradigm that leverages an external music expert to provide hierarchical supervision for the generator's latent features, bridging the semantic gap and enhancing representation learning. To effectively incorporate hierarchical supervision, we introduce a curriculum-guided multi-scale learning strategy that progressively transfers musical knowledge from the expert to the music generator, enabling stable and effective representation learning. Moreover, to accommodate the semantic and structural variations across different expert scales and achieve fine-grained alignment under temporal mismatch, we propose a scale-aware optimal transport alignment mechanism, which models soft correspondences between hierarchical expert representations and the generator's latent features. Extensive experiments on two datasets demonstrate that CMA-OT achieves state-of-the-art performance in rhythmic synchronization, perceptual quality, and overall music generation. --- ### Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents Authors: Yunqi Lu, Tyler Baumgartner, Nikhil Johri, Brandon Tai, Candice Fan, Luc Debaupte, Ruben Aguilar, Bill Wang, Yi Zhong Published: 2026-09-11 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.13117v1 Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: continuing to speak while incorporating what the listener just contributed. The contribution may be a missing word, a correction or a clarification. We introduce Duplex Cue, an evaluation of this \emph{in-turn adaptation} in full-duplex voice agents. Duplex Cue separates listener intent (backchannel, collaboration, or interruption) from speaker behavior: continuing unchanged, adapting within the turn, or yielding. Adaptation includes acknowledgment as well as content revision. In a single-model case study using 300 human-confirmed cues from unscripted English conversations, we compare recorded human responses with PersonaPlex continuations generated while replaying the listener's audio. We retain 208 pairs with the ongoing speaker active at cue onset and a scorable response in each condition. On the 66 collaborative pairs, recorded speakers adapt in 68.2\% of cases, compared with 34.8\% for PersonaPlex. The model otherwise continues unchanged (42.4\%) or yields (22.7\%). These findings show why evaluating natural voice interaction requires measuring how an agent responds to a listener's contribution as well as whether it keeps speaking. --- ### A Ranking Approach for Measuring Calibration Authors: Anirban Chatterjee, Rina Foygel Barber Published: 2026-09-11 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.13100v1 When providing forecasted probabilities with a predictive model, the ideal model offers perfect calibration: the true probability of the outcome (i.e., the probability that $Y=1$) exactly matches the forecasted probability $f(X)$. In practice, models inevitably exhibit calibration error, and it is therefore important to be able to measure this miscalibration to assess a model's reliability. The Expected Calibration Error (ECE) is the most widely used measure of miscalibration, but is known to be impossible to estimate the ECE with guaranteed accuracy in an assumption-free setting. In this work, we propose an alternative measure, the rankECE, that is based on comparing points with neighboring values of the predicted probability $f(X)$. Our theoretical guarantees and empirical results establish that rankECE provides a better proxy for ECE as compared to binned approximations to ECE, which are the most commonly-used approximations in practice. --- ### Language-Guided Terrain-Adaptive Neural MPC for Autonomous Traversal of Articulated Tracked Robots Authors: Zhenfeng Gan, Yanbo Chen, Lirong Che, Yongyi Ma, Rongkai Zhu, Xueqian Wang Published: 2026-09-11 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.13083v3 In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and cluttered building interiors. Reliable autonomy remains challenging because robot-terrain interaction (RTI) is hybrid and discontinuous, and effective flipper-track coordination is difficult to model analytically. We present ASTRIL-MPC, a language-guided neural kinematics model predictive control (MPC) framework for autonomous traversal. A learned kinematics model predicts short-horizon task-state increments from a height sequence and recent trajectories; NMPC plans with multi-objective costs and strict feasibility constraints; and a large language model (LLM) proposes bounded updates to selected weights and bounds through a safety-checked interface with range clipping, rate limiting, and consistency checks. The compiled predictor enables a full control cycle within 100 ms. Across three traversal tasks and a multi-height generalization setting, ASTRIL-MPC improves an aggregate traversal-quality score by up to 71% over a non-adaptive NMPC and by 67% over a PPO baseline, while eliminating measurable collision impacts during descent. These results indicate that combining terrain-conditioned neural kinematics, optimization-based planning, and language-guided adaptation yields data-efficient and robust autonomy for articulated tracked robots. Real-robot trials over four indoor obstacles further demonstrate transfer to contact-rich physical traversal. --- ### Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction Authors: Baoyang Jiang, Fengchun Zhang, Leyuan Wang, Haotian Li, Yida Wang, Zhe Ji, Jinshan Lai, Xi Ren, Danyang Li, Zheng Yang, Jianwei Hu, Qiang Ma Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13082v1 Agentic systems offer a promising way to automate embodied benchmark construction, but existing approaches typically cover isolated stages or remain specialized to predefined environments and task families. More importantly, multi-step construction produces dependent intermediate artifacts that are often passed downstream without artifact-specific verification, allowing local defects to propagate into the final benchmark. We present Embodied-BenchForge, an agentic framework that transforms user-specified evaluation intents into complete embodied benchmark artifacts. It formulates construction as Closed-Loop Benchmark Synthesis, integrating forward artifact synthesis with backward verification and repair. Skill-Orchestrated Artifact Synthesis composes typed and reusable skills into executable workflows, while an artifact dependency graph records intermediate outputs and their dependencies. Requirement-Guided Verification and Repair applies artifact-specific contracts throughout construction and uses provenance to trigger local re-execution or upstream rollback when verification fails. Embodied-BenchForge constructs six benchmarks covering diverse embodied scenarios in the Offline EQA Track, together with one interactive benchmark containing 220 executable tasks in the Interactive Embodied Track. Evaluations of representative MLLMs and embodied agents show that the benchmarks distinguish model capabilities in both observation-based understanding and closed-loop execution. Quality assessment and ablations validate benchmark quality and the effectiveness of verification and repair, while repair and skill-reuse analyses demonstrate efficient localized recovery and cross-benchmark reusability. --- ### MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant Authors: Yi-Jen Shih, Shih-Yun Shan Kuan, Guan-Ting Lin, Kai-Wei Chang, Siddhant Arora, Shu-wen Yang, Abdelrahman Mohamed, Shinji Watanabe, Hung-yi Lee, David Harwath Published: 2026-09-11 Categories: eess.AS, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.13076v1 Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-end architectures. However, while recent benchmarks extensively evaluate dyadic interactions and passive audio comprehension, they largely overlook a prevalent real-world scenario: multi-party conversations. Evaluating agents in these settings is fundamentally more challenging than in dyadic interactions due to the exponentially greater conversational complexity. For voice agents to integrate seamlessly into human group dynamics, they must not only generate contextually appropriate responses but also demonstrate a nuanced understanding of open turn-taking. To address this gap, we introduce Multiparty Bench (MP-Bench), the first benchmark specifically designed to objectively evaluate conversational speech systems as active participants within multi-party contexts. MP-Bench assesses agent behavior along two primary dimensions: turn-taking awareness and response appropriateness. Additionally, we incorporate comprehension-based question-answering tasks as a complementary evaluation. By benchmarking 12 voice agents, we find that real-time voice agents stay at or below 22% on multiparty comprehension and remain near chance on multiparty turn-taking, exposing an open challenge for real-time voice agents under multiparty scenario. --- ### Autonomous Research for Open-Ended Problems: A Case Study on Telecom Ticket Retrieval Authors: Junghyun Min, Huseyin Uzunalioglu, Mohamed Trabelsi Published: 2026-09-11 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.13073v1 Recent breakthroughs in LLM-based systems and their abilities in problem solving and coding have allowed progress in the AI for Science paradigm, potentially replacing human roles in machine learning (ML) research. However, while several frameworks of fully autonomous end-to-end ML research have been proposed, successful implementations of them are often limited to problems with narrow search spaces, like language modeling or biomedical ML benchmarks. In this paper, we explore how autonomous research can be adapted to solve open-ended, industry-grade ML problems, by considering a case study: telecom ticket retrieval, an open-ended task with degrees of freedom in representation, architecture, and training data generation. We discover that autonomous research for open-ended problems with commercial and open-source agents shows both promise and limitations: while autonomous research can excel in narrow hyperparameter optimization, it lacks human-like intuition and creativity and requires operational overhead. Even with minimal human supervision, autonomous research can reach $90\%$ of state-of-the-art performance (0.34 vs. 0.38 Recall@1) in a much shorter time period (10 weeks vs. 10 months of human work) at a modest cost (up to \$200 per Cursor campaign). Our empirical evidence recommends that human researchers and autonomous research frameworks work together for best results in ML research. --- ### MAxBench: A Multinomial Concept Recovery Benchmark Authors: Divya Appapogu, Freya Behrens, Yonatan Belinkov, Aaron Mueller Published: 2026-09-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.13072v1 Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary concepts such as refusal, a single direction in activation space often suffices for steering. However, many concepts are not binary: Animals and Countries contain many subcategories, each with multiple instances. For these concepts, the search space over possible representation geometries is far larger than for binary concepts; it is thus not clear what geometries are most appropriate, nor what methods are most effective at recovering them. In this work, we introduce MAxBench, a geometry-agnostic evaluation framework for multinomial concept representations based on sampling from the recovered concept representation. We use MAxBench to compare 10 localization methods (covering 5 geometry types) across 6 concepts and 4 models. Using this framework, we find that (i) affine subspaces steer more reliably and have greater recall than rank-one or linear subspaces; (ii) much of this advantage is due to better non-zero offsets rather than the choice of bases; (iii) manifold steering is competitive with the best methods when applicable; and (iv) no method consistently outperforms prompting, in alignment with prior findings on binary concepts. These findings underscore the importance of expanding the scope of interpretability research and meta-evaluation to concepts with more varied structure. --- ### Involving before Evolving: A Vision for Trustworthy Enterprise Digital Twin Engineering Authors: Kérian Fiter, Adil Lagrou, Franck Dervault, Bentley Oakes Published: 2026-09-11 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2609.13071v1 Enterprise Digital Twins (EDTs) promise data-driven decision support at organizational scale, but realizing them requires navigating siloed departments, tacit knowledge, and high-stakes decisions with long-horizon consequences. Existing approaches involve domain experts during model development but focus less on early organizational buy-in in EDTs. We present a vision for trustworthy EDT engineering grounded in an `involving before evolving' paradigm: rapidly involving stakeholders through a working prototype before evolving toward federation and full interoperability. Our three-stage approach combines foundation models for rapid prototyping, an ontological backbone for federated interoperability, and observability tooling for stakeholder trust. We ground our vision in an ongoing collaboration with Michelin, a multinational manufacturer, where an initial prototype has helped support stakeholder buy-in. --- ### Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication Authors: Sayantan Kumar, Nicolas Grimaldi, Jack Cummins, Jeremy C. Weiss Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13062v1 Clinical timelines support treatment-window analysis and leakage-free modeling, but discharge summaries often obscure chronology and structured EHR tables describe only part of the patient course. We present a UID-preserving framework that links each narrative event occurrence to its source span and retains that identity through text-only estimation, structured-evidence retrieval, timestamped source-row grounding, and joint revision. We also present GAVEL, an LLM judge that compares two UID-aligned timelines against the narrative and structured record, to augment prior matching and temporal assessments. Across six open-weight models and 40 mixed-critical-care summaries, the GLM 5.2 multimodal revision, as compared to its text-only variant, improved temporal agreement without reducing event recovery and performed competitively with clinician annotations, while other model revisions showed smaller gains and lower overall performance. Ablations showed that UIDs primarily preserve event retention, whereas source-row linkage supports temporal placement. Blinded human review upheld most GAVEL findings, and controlled adjudication favored multimodal over text-only GLM 5.2 but did not for DeepSeek V3.2. In developing the UID and judge pipeline, we are able to demonstrate 43\% increased event recovery, a framework competitive with clinician annotations, and a system with occurrence-level provenance for both reconstruction and evaluation. --- ### CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models Authors: Blake Olson, Yuhang Song, Emmett McQuinn, Yuan Shangguan Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.13060v1 Diffusion Language Models (DLMs) offer promising parallel generation capabilities but lag behind autoregressive models in complex reasoning and tool-use tasks. While Reinforcement Learning (RL) has recently been applied to enhance DLMs, standard RL approaches suffer from an exploration bottleneck. To address this, we inject reasoning priors from a stronger teacher model to guide RL exploration. In this paper, we introduce CanvasAnneal, a curriculum-guided diffusion RL framework. During the initial RL phase, we warm-start exploration by injecting teacher-generated reasoning traces into the initial diffusion canvas. As training progresses, we gradually remove this guidance and require the model to generate more of the reasoning trajectory independently. Across mathematical reasoning and tool-use benchmarks, CanvasAnneal improves over standard diffu-GRPO on MATH500, Countdown, and Tau2 and substantially accelerates reward improvement on several tasks, while gains are task-dependent. Our results suggest that structured training-time guidance can alleviate exploration bottlenecks in diffusion RL and speed up convergence on harder tasks. --- ### Expert-Space Exploration in MoE Reinforcement Learning Authors: Hongyi He, Zhenghao Lin, Xiao Liu, Peng Cheng, Yan Lu, Yeyun Gong Published: 2026-09-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13058v1 Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models have primarily focused on improving optimization stability and training efficiency, while treating the expert selection as a fixed component. Since routing determines the sparse computation paths that induce output distributions, expert selection offers an additional source of rollout diversity. Through empirical analysis, we find that perturbing expert routing effectively alters model output and increases rollout diversity, which is similar to increasing the decoding temperature. However, direct perturbation can activate unsuitable experts and substantially degrade rollout quality. Motivated by these observations, we introduce Expert-Space Exploration Reinforcement Learning (ESRL), an architecture-aware framework that explicitly explores the expert-routing space of MoE models. ESRL preserves high-confidence experts as anchors, and restricts stochastic routing to a plausible candidate pool, thereby retaining reliable computation paths. The perturbation strength is further adapted according to router entropy to avoid over-perturbation. To mitigate the routing mismatch introduced by perturbation, ESRL records the expert paths used during rollout and replays them during policy optimization. Experiments demonstrate that ESRL achieves the best performance across MoE backbones with top-K, top-1, and shared-expert routing, as well as across mathematics, science, and code tasks without additional sampling or computational cost. Specifically, ESRL on Qwen3-30B-A3B achieves the best among all compared methods, improving average Pass@1 and Pass@8 over GRPO by 3.2 and 4.5 percentage points, respectively. Further analyses of expert utilization and training dynamics provide insights into how exploiting MoE-specific routing structure benefits RL training. --- ### Benign Loss Landscapes Can Coexist with Worst-Case Hardness Authors: Zach Furman, Stephan Wäldchen, Yangda Bei, Liam Hodgkinson Published: 2026-09-11 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.13057v1 Deep neural networks are expressive enough to contain worst-case targets that can be evaluated in polynomial time but cannot be learned in polynomial time by gradient descent. For practical tasks they nonetheless learn well, raising the question of what non-generic structure of real-world targets enables this. Existing surrogate models cannot pose this question because they either lack hard-to-learn targets entirely (deep linear networks) or cannot evaluate such targets efficiently (kernel methods, infinite-width limits). We study tree tensor networks (TTNs), a model class that generalizes deep linear networks and Tucker decompositions. We show they embed arbitrary read-once Boolean formulas, and thus contain polynomial-size targets that cannot be learned by gradient descent in polynomial time under the same mechanism as neural networks. Despite this, we prove that their loss landscapes are conditionally benign for every realizable target: every local minimum that is minimum-norm is global. Thus, surprisingly, bad local minima are not what distinguishes between typical and worst-case problems in TTNs. Instead, learning difficulty in TTNs can arise from high-order degenerate saddle points, which we show are caused by rank-deficiency. This is explored through a case study of the parity function, illustrating the potential for TTNs to relate landscape geometry to computational hardness. --- ### Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model Authors: Hoeun Lee, Jaeik Kim, Jusang Oh, Jinhyeok Kim, Geon Choi, Hyeonggeun Kim, Jaeyoung Do Published: 2026-09-11 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.13053v1 Visual goal and dynamics prediction can provide language-conditioned robot policies with both a target outcome and a representation of action-dependent scene changes. We bring these predictions into action generation and selection through a shared trajectory model. Dynin-Robotics implements this formulation on Dynin-Omni, an omnimodal masked-diffusion backbone, representing language, visual observations, goals, and actions as discrete tokens. By varying conditioning and target spans, the same model learns action prediction, action-conditioned next-observation prediction, terminal goal-state prediction, and trajectory-to-instruction reconstruction. These interfaces support test-time scaling through goal prediction, action-candidate evaluation, and joint refinement of action and future-state predictions. We continually pretrain the model on approximately 1.33 million trajectories from 48 Open X-Embodiment datasets and adapt it separately to downstream domains. On two VLABench tasks, robot pretraining improves adaptation within a fixed Stage-2 step budget, and the full objective mixture improves shifted-instruction success over Policy-only post-training under the same coupled decoder. Combining goal guidance with joint action-next-state denoising further improves shifted-instruction success over action-only decoding; the benefit depends on how the predictions are composed. Dynin-Robotics achieves competitive performance on LIBERO and zero-shot LIBERO-Plus, together with a 78.4% average success rate across four manipulation conditions on a Franka Research 3 robot. An optimized block-parallel implementation accelerates model-side action decoding by up to 29.2x relative to the base implementation under the reported profiling setup. These results support shared trajectory modeling as a common interface for learning complementary robot objectives and composing their predictions during control. --- ### A Unified and Constrained View of Regularization-Based Robust Reinforcement Learning Authors: Amine Andam, Jamal Bentahar, Mustapha Hedabou Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.13050v1 Regularization-based methods have become a standard approach for training Deep Reinforcement Learning policies against adversarial input perturbations. In this paper, we unify these methods by deriving new upper bounds on the performance gap between the nominal and worst-case policies. Each upper bound is expressed as an existing regularization objective plus a KL-divergence penalty between the nominal and worst-case policies, which further explains why adding a KL penalty improves robustness in practice. Building on these bounds, we formulate robust training as a constrained optimization problem, showing that existing methods correspond to the special case of a fixed Lagrange multiplier. We instead update the multiplier jointly with the policy to automatically tune the regularization weight. Finally, we conduct extensive adversarial evaluations across several continuous control tasks to validate our theoretical analysis. --- ### MCRL2: Multi-resource Cross-attention-based Representation Learning-augmented Reinforcement Learning for Cloud Microservice Scheduling Authors: Tiangang Li, Shi Ying, Xiangbo Tian, Chuan Shi, Ding Xiao Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.13048v1 Efficient microservice scheduling is crucial for maintaining load balance across nodes in data centers and ensuring high quality of service. However, achieving this in practice remains challenging due to dynamic resource imbalance under fluctuating workloads, nonlinear coupling across multiple resource dimensions, and the heterogeneity of microservice resource demands. While reinforcement learning-based approaches have shown promise, they struggle to capture the complex interdependencies among heterogeneous resources and neglect the importance of learning informative system representations. To address these limitations, we propose MCRL2, a novel reinforcement learning approach augmented with multi-resource cross-attention-based representation learning for microservice scheduling. Specifically, we first propose MCRL, a novel representation learning approach that captures structured and informative interactions among nodes, resources, and microservices via a multi-resource cross-attention mechanism. Then, MCRL2 augments reinforcement learning through MCRL-enhanced actor-critic architecture combined with a maximum entropy objective, improving system state expressiveness and leading to more stable and effective scheduling decisions. Extensive experiments on real production cluster traces demonstrate that MCRL2 significantly outperforms existing baselines in load balancing, scheduling success rate and average completion time across diverse workload patterns. --- ### Diffusion Models and Concept Formation Authors: Zekun Wang, Karthik Singaravadivelan, Christopher J. MacLellan Published: 2026-09-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.13047v2 Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a \emph{basic level} at which people recognize and name objects with the least cognitive effort. Cobweb is a classic cognitive account of this ability, an incremental learner that builds a probabilistic concept hierarchy by maximizing category utility. We argue that diffusion models, although designed for image synthesis, implicitly perform the same computation. The noisy marginals of a diffusion model are Gaussian smoothings of the data distribution, and the modes of these marginals form a hierarchy that corresponds to a Cobweb tree of probabilistic prototypes in four respects. Both are hierarchical density models, both are hierarchical-Bayesian models with Gaussian prototypes, both treat categorization as score-following that reduces uncertainty, and in both a basic level emerges. We locate this basic level for a diffusion model at an intermediate noise level, where recent analyses show that the reverse process commits to the class identity of a sample. The two models differ mainly in how they represent and learn the taxonomy. Cobweb learns a discrete tree incrementally, whereas a diffusion model encodes a continuous, interpolable hierarchy in a single learned score field fit to the data distribution. We test the correspondence on MNIST and Fashion-MNIST by recovering the diffusion hierarchy through mode-finding and comparing the basic levels of the two models. This reframes diffusion as a cognitive model of concept formation and offers Cobweb a continuous, scalable instantiation. --- ### Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning Authors: Hayato Futami, Hassan Shahmohammadi, Tushar Dhyani, Alkis Koudounas, Raphaël Lafargue, Yosuke Kashiwagi, Quentin Jodelet, Emiru Tsunoo Published: 2026-09-11 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.13045v1 Speech-to-speech translation (S2ST) has advanced significantly with speech LLMs, offering the potential for joint optimization and preserving non-linguistic information. However, these models struggle with predicting high-bitrate speech tokens in LLMs, and face the challenge of relying on S2ST training data with ideally aligned speaker identity and prosody. We propose using low-bitrate tokens based on single-layer vector quantization, trained to reconstruct self-supervised learning (SSL) features. We also employ a separate token-to-waveform decoder named Autowave-X, which is also conditioned on the source speech to improve non-linguistic transfer, thereby relaxing the training data constraints. With the integration of these techniques, we propose an S2ST model named Kraken, which augments a pre-trained LLM with speech feature inputs and the low-bitrate token outputs, followed by Autowave-X vocoder. We built the model upon Qwen3-8B and trained it using 150k hours of multilingual and multitask speech data. We demonstrated that our model exhibited better translation quality than SeamlessM4T-Large v2 and Qwen2.5-Omni, along with improved speaker and prosody transfer capabilities. --- ### Robust Policy Optimization via Adversarial Importance Sampling Authors: Amine Andam, Jamal Bentahar, Mustapha Hedabou Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.13044v1 Significant progress has been made in safeguarding deep reinforcement learning (DRL) policies against input perturbations. Developing robust DRL involves three main stages: algorithm design, implementation, and evaluation. In this work, we identify and address a key limitation at each stage. First, we introduce Adversarial Importance Sampling (Advis), a method that uses importance sampling over trajectories from standard training to estimate and optimize verifiable worst-case returns. Advis satisfies three desirable criteria not jointly achieved by prior work: it requires no additional environment interactions, no auxiliary networks, and captures long-term robustness. Second, we introduce advrl, a modular PyTorch library that provides clean, single-file implementations of existing robustness methods and adversarial attacks, facilitating rapid prototyping and enabling reproducible and traceable evaluations. Third, we revisit evaluation under learned adversaries and show that optimal adversarial hyperparameters do not transfer across agents, which can lead to an overestimation of robustness when using a limited set of attacker configurations. Accordingly, we evaluate policies against a large and diverse set of attackers, using 6-14x more configurations than prior work. Finally, we evaluate our approach on continuous control environments, demonstrating its effectiveness relative to existing baselines. The code is available at: https://github.com/AmineAndam04/advrl --- ### Unified CT and MRI Pancreas Segmentation for Label-Efficient Cross-Modality Subregion Transfer Authors: Ziliang Hong, Hongyi Pan, Halil Ertugrul Aktas, Andrea Bejar, Elif Keles, Frank H. Miller, Michael B. Wallace, Rajesh N. Keswani, Gorkem Durak, Ulas Bagci Published: 2026-09-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.13043v1 Robust medical image segmentation across imaging modalities is challenging because of large differences in appearance and intensity distributions. Models trained on a single modality often show substantial performance drops when applied to unseen domains. In this work, we develop a unified 3D pancreas segmentation framework that applies domain-adversarial learning to 4,604 heterogeneous CT and MRI scans to learn anatomical representations. A shared nnU-Net encoder-decoder is trained for whole-pancreas segmentation, with a latent domain discriminator encouraging CT-MRI feature alignment. The learned encoder is subsequently transferred to pancreatic head-body-tail segmentation using limited MRI-only subregion annotations. An average Dice score of 87.31% on the in-distribution test set and Dice scores ranging from 84.20% to 88.09% across external OOD datasets were achieved in whole pancreas segmentation. Dice scores of 80.53% on MRI and 83.05% on CT were achieved for downstream subregion segmentation, without using CT subregion annotations. These results demonstrate that a unified anatomical representation can support both cross-modality pancreas segmentation and label-efficient downstream transfer. --- ### DynSHAP: Towards Explainable Dynamic Survival Analysis Authors: Nastasya Anokhina, Jonas Jürß, Pietro Liò Published: 2026-09-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.13042v1 Deep learning models for dynamic survival analysis (DSA) achieve strong predictive performance by incorporating longitudinal patient data, but their black box nature limits clinical trust and adoption. Existing explainability methods cannot handle longitudinal, irregular inputs and functional survival outputs simultaneously, which limits their usability in DSA. We propose DynSHAP, a SHAP framework suited specifically for dynamic survival analysis. It extends common marginal SHAP estimators to this setting by treating time--feature pairs as players in the Shapley game. We further introduce Temporal DynSHAP, which learns linear dependencies in features over time and uses conditional sampling to address them in explanations. When applied to synthetic data with known ground-truth attributions, Temporal DynSHAP recovers temporally dependent features more accurately than marginal estimators for a given state-of-the-art model. Applied to two real-world clinical datasets and two DSA architectures, DynSHAP produces attributions faithful to model learning, allowing medical experts to see which patient information drove the prediction and when. --- ### Quantile-based Loss Filtering for Outlier-Robust Stochastic Gradient Descent Authors: Jamie Haddock, Anna Ma, Elizaveta Rebrova Published: 2026-09-11 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2609.13040v1 We study loss-based filtering for finite-sum optimization with a subset of corrupted component functions whose gradients may be highly unreliable. Motivated by minimum-loss-based SGD (min-$k$-loss) and quantile-based methods for corrupted linear systems, we propose and analyze a general loss-filtering framework -- Quantile-\(k\)-Loss SGD (Q\(k\)L-SGD) -- that samples \(k\) component losses at each iteration and updates using an index chosen uniformly from the lower empirical \(q\)-quantile. We prove linear convergence of this family of methods under standard convexity assumptions, requiring the sample size to scale with the number of corruptions and a subset strong-convexity threshold. For the cases when large enough sampling is impossible or undesirable, we give a complementary small-sample probabilistic analysis that covers any sample size $k$ and the convergence behavior depends on the probability of selecting an outlier and on the curvature of the selected good step. Experiments on polynomial regression, regularized logistic regression, and regularized hinge loss show that intermediate quantiles often outperform both standard SGD and min-\(k\)-loss SGD. In particular, min-\(k\) often stalls by repeatedly selecting nearly solved components, while intermediate quantiles retain robustness and produce more informative updates. --- ### Transfer Learning for Evolving Domains Authors: Ricardo Ribeiro Pereira, Jacopo Bono, Hugo Ferreira, Pedro Ribeiro, Pedro Saleiro, Pedro Bizarro, Carlos Soares Published: 2026-09-11 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.13039v1 Transfer learning explores how to leverage knowledge from various tasks or domains (sources) to enhance predictive performance in related tasks or domains (targets). Typically, transfer learning research is segmented into several isolated sub-areas (such as domain generalisation, domain adaptation, or multi-domain learning), each making distinct assumptions about target data availability, namely how much data and how many labels are available at training time. However, in many real-world applications, data availability is not fixed but evolves over time, as instances and labels are progressively collected from a new domain. Each of the classical settings then describes only a snapshot of a trajectory that a deployed system must traverse in full. We formalise this trajectory as a transfer learning problem in its own right, Transfer Learning for Evolving Domains (TrED), specified by a data availability process fixed by the environment, a learning protocol that the method is free to choose, and an evaluation criterion that scores the whole trajectory of models rather than a single one. Within this formalism, the classical settings are recovered as regimes that a learner may pass through, rather than as separate problems that TrED concatenates. We then examine the transfer learning literature to identify mechanisms that are promising building blocks for a solution, and find that most methods are tailored to a single regime and that even the strongest existing candidates do not yet optimise the whole trajectory. We argue that TrED is a well-posed and unsolved problem, and an important direction for future research. --- ### Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries Authors: Ben Opperman, Eduardo Alonso, Esther Mondragón Published: 2026-09-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.13035v1 Symmetries play a central role in reducing the complexity of reinforcement learning problems, yet most existing approaches rely on fixed group actions or predefined state abstractions. Classical reinforcement learning algorithms typically assume a globally structured Markov decision process with uniformly applicable actions and transitions, an assumption that limits their ability to exploit modularity and local, context-dependent regularities present in many realistic environments. We propose a reinforcement learning framework using groupoids to capture local, state-dependent symmetries and support the dy- namic discovery of equivalence structures during interaction. The agent maintains orbit representatives together with transporters that map raw states to canonical forms, enabling learning and decision-making to be performed in a symmetry-reduced space while preserving local distinctions. Empirical results demonstrate that the proposed groupoid-based approach improves sample efficiency and convergence in dense and large-scale environments exhibiting strong partial symmetries, yielding substantial performance gains over standard Q-learning. These findings show that dynamically exploiting local symmetry provides a practical and mathematically principled route to scalable and generalisable reinforcement learning. --- ### Attention Quantization for Tabular Foundation Models Authors: Jonas M. Kübler, Benjamin Jäger, Klemens Flöge, Noah Hollmann, Frank Hutter Published: 2026-09-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.13031v1 With the recent rise and adoption of tabular foundation models, optimizing their inference performance becomes an emerging field for efficiency research. While the models are architecturally similar to transformer-based large language models (LLMs), the size and serving patterns differ significantly. We show that the focus should be on the attention calculation and less on weight or KV cache quantization, which are more popular in LLMs. We develop a quantization strategy for queries, keys, and values to FP8 and use explicit FP8 matrix multiplication instructions to speed up the attention calculation. We find that it is crucial to align the quantization error in the test rows with the quantization error in the training rows, as otherwise the accuracy drops drastically. Our Triton kernel achieves a speedup up to 1.7x over regular 16-bit kernels, and we show that on TabPFN-v3 and TabICLv2 there is no relevant accuracy loss across TabArena and BeyondArena. --- ### Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition Authors: Yanjiang Shi, Peng Zhao, Nan Qi, Guiqin Wang Published: 2026-09-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.13024v1 As a key model compression technique, knowledge distillation aims to transfer knowledge from a high-capacity teacher model to a lightweight student model for enhancing the latter's performance. In this work, we reviewed the feature knowledge distillation for 3D-CNNs and observed that most feature distillation methods in video analysis are simple adaptations of those used in image analysis, often neglecting the differences of video features in the temporal dimension. To address this issue, we proposed Label-Guided Knowledge Distillation (LGKD) to guide the distillation of student model features using ground truth labels. Our method entails two components: sample-wise distillation and class-wise distillation, enabling the student model to learn feature representation of the teacher model at two levels. Sample-wise distillation utilizes label information and the teacher's probability distribution to guide the learning of features that significantly impact temporal accuracy while mitigating noise. Meanwhile, class-wise feature distillation employs a prototype network to further capture the relational knowledge among samples within the same category, enhancing the student's ability to learn higher-dimensional semantic information and improving model generalization. To demonstrate the effectiveness and superiority of our method, we conducted comprehensive experiments on two benchmark action recognition datasets, UCF101 and HMDB51, achieving competitive results. --- ### TileNet: Tile-Based CNN-SVM Architecture for Autonomous Unmanned Aerial Systems Inspection of Flat Roofs Authors: Samuel Dunthorne, Hashim A. Hashim Published: 2026-09-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.13013v1 Flat roofs are among the most influential components of the building envelope, governing both structural performance and thermal efficiency, and thereby contributing directly to household energy consumption, carbon emissions, and long-term environmental sustainability. Timely detection of roof defects is essential for reducing heating and cooling losses, preventing moisture-driven degradation such as mold growth, and supporting national climate-change mitigation goals. This paper presents a real-time, Unmanned Aerial System (UAS)-based deep learning framework that autonomously detects defects using live imagery captured during dual-altitude aerial passes. The multi-resolution flight strategy is designed to aid the identification of both small, fine-scale defects and larger structural issues, enabling more comprehensive assessments. To meet the strict computational and power constraints of embedded UAS hardware, the proposed framework integrates a tile-based architecture with a lightweight Convolution Neural Network-Support Vector Machine (CNN-SVM) classifier designed for low-latency onboard inference. The final model-comprising five convolutional layers and four dense layers, the last a linear SVM head, achieved a mean test accuracy of $94.4\%$ ($95\%$ confidence interval $\pm0.4\%$ over three seeds) on a photo-level split ($43,383$ training, $3,869$ validation, and $2,540$ test tiled and augmented images), outperforming GoogLeNet ($89.2\%$) and AlexNet ($79.8\%$). Experimental evaluations using real UAS imagery collected by onsite visits with DJI Matrice 350 RTK drone demonstrate that the system supports rapid, repeatable, and safe roof inspections while reducing human risk, lowering operational costs, and enabling more sustainable building maintenance. --- ### Comfort by Construction: Adaptive, Comfort-Bounded Action Spaces for Learned Driving Policies Authors: Anna Rothenhäusler, Daniel Jost, Raghu Rajan, Faris Janjos, Oliver Scheel, Andreas Look, Joschka Boedecker Published: 2026-09-11 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.13011v1 Data-driven driving simulators command accelerations and steering rates from a fixed grid without constraining the realized accelerations and jerks. As a result, reinforcement-learning policies inflate safety metrics through abrupt, last-second maneuvers that lie far outside the range of human driving and would be unacceptable to occupants of a real vehicle, so the metrics measure simulator permissiveness rather than policy quality. Enforcing comfort bounds naively is not enough: lateral limits shrink quadratically with speed, so clamping a static grid saturates it and destroys fine-grained control ("grid collapse"). We propose an adaptive action parameterization that rediscretizes the grid at every step to span exactly the per-step feasible control set, via closed-form inversion of the lateral-jerk constraint. We further present PufferDrive-Editor, a browser-based tool to audit realized kinematics and author kinematically challenging scenes. On the Waymo Open Motion Dataset and a hand-authored slalom, our adaptive model holds comfort violations below 1% while outperforming clipped-grid and direct-jerk baselines in navigability. --- ### Dual-guided Hierarchical Edge Localization for Large-scale Optimal Transport Across Dimensions Authors: Wenzhou Xia, Qiaoqiao Ding, Jingwei Liang, Xiaoqun Zhang Published: 2026-09-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.13010v1 Optimal transport (OT) compares distributions and aligns datasets in machine learning, yet unregularized discrete OT requires a linear program with quadratically many transport variables. We propose HELLO, a hierarchical solver that casts large-scale discrete OT as edge localization and uses dual potentials to guide both coarse-to-fine initialization and within-level refinement. Initialization propagates coarse dual potentials across a recursive subsampling hierarchy to assign candidate edges. Refinement then iteratively inserts the largest dual violators in each row and column until the relative KKT residual meets a prescribed tolerance, while budgeted pruning ensures linear memory complexity. For exact-arithmetic refinement, we prove finite termination at a global optimum under a symbolic lexicographic rule. At the million-point scale, HELLO attains lower transport objectives with order-of-magnitude runtime improvements over strong baselines across feature dimensions from single digits to thousands. It further scales to 1.28 million samples per marginal in 8192 dimensions on a single H100, using 41.6 GiB peak GPU memory while satisfying a full relative KKT residual below $10^{-6}$. Beyond standard discrete OT, the framework supports general pairwise costs and serves as a scalable balanced-OT oracle for semi-discrete OT, Gromov--Wasserstein, unbalanced OT, and OT-based Flow Matching. --- ### How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks Authors: Ali Ansari, Haoran Sun, Andy Zeyi Liu, Mark Jabbour, Yongshan Ding, Steven Girvin, Yu He, Sohrab Ismail-Beigi, Aleksander Kubica, Owen D. Miller, Corey O'Hern, Vidvuds Ozolins et al. Published: 2026-09-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.13009v1 Low reported scores on leading physics benchmarks, including those featured in the Artificial Analysis Intelligence Index (2026), suggest that frontier language models still struggle with advanced physics, a demanding test of their scientific reasoning and quantitative problem-solving abilities. Yet this impression does not always align with domain experts' experiences using these models in their work. We revisit these reported findings by evaluating frontier models on six widely used physics benchmarks and auditing them with experts, focusing on text-only problems with verifiable final answers. For each subfield of physics, faculty and graduate researchers with relevant expertise carefully review problem statements, reference solutions, and model responses to distinguish genuine model errors from grader errors, incorrect reference solutions, and ambiguous or underspecified questions. Most audited cases initially evaluated as incorrect reflect these benchmarking issues rather than errors in the models' physics reasoning. We then ask experts to address these benchmarking issues by correcting erroneous reference solutions and repairing or excluding flawed questions. We find that GPT-5.6-Sol's measured mean@4 rises from 47.3% to 78.7% on HLE-Physics and from 61.0% to 87.2% on CMT-Benchmark, while its corrected pass@4 reaches 94.4% on the 54 retained CritPt challenges. Corrected scores are computed on the retained evaluation subsets following expert review. Scores on the audited subsets of UGPhysics, PRISM-Physics, and PHYBench also rise substantially after correction. These findings suggest that current benchmarks substantially understate frontier models' ability to solve well-posed physics problems. Near-saturation on these closed-ended tasks highlights the need for more demanding, expert-validated evaluations. --- ### Tasks over Application Manuals: Revealing Gaps in Long-Horizon Procedural Reasoning for Language Models Authors: Utkarsh Soni, Syed Shariyar Murtaza, Yifan Nie, Sachin Chandrasekhar, Eugene Wen Published: 2026-09-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.13005v1 Large language models (LLMs) have achieved strong performance on a wide range of natural language tasks, and recent benchmarks suggest that they are increasingly adept at multi-hop reasoning. However, these benchmarks are typically short-horizon, requiring only a small number of retrieval or inference steps, and provide limited evidence of reliability on real-world tasks that involve following manuals spanning hundreds of pages with complex, interdependent guidelines. In this paper, we introduce Tasks over Application Manuals (TAM), a benchmark for evaluating long-horizon procedural reasoning. We construct TAM by curating real-world tasks from two domains: ICD-10-CM clinical coding (mapping medical conditions to diagnostic codes) and U.S. federal sentencing (computing crime sentencing guideline outcomes, specifically offense levels), with human-validated labels. Each task requires following an authoritative manual with tens of thousands of rules and executing a sequence of interdependent steps across different sections to produce an exact answer. We evaluate general-purpose prompting approaches, including retrieval-augmented generation, ReAct-style prompting, and an agent-harness baseline on GPT-5, and find that the best exact-match performance remains extremely low: 1% on ICD-10-CM coding and 15.5% on sentencing tasks. These results show that current benchmarks may overestimate LLM reasoning ability and miss a key challenge: reliably following long, rule-based procedures. The complete TAM data and code are publicly available. ---