# Research Papers — 2026-09 · bundle page 98 of 266 > Full-text markdown of papers #4851–4900 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/98 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/97.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/99.md) ### Curriculum Learning with GNN-based Reinforcement Learning for Job Shop Scheduling Authors: Jayakrishnan K. Vasudevan, Jonathan Hoss, Noah Klarmann Published: 2026-09-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.28085v1 The job shop scheduling problem is a challenging combinatorial optimization problem, and recent reinforcement learning approaches using graph neural networks have shown promise for learning scheduling policies directly from problem instances. However, training on large instances remains computationally expensive, and generalization across instance sizes remains challenging. This paper studies curriculum learning for graph neural network-based reinforcement learning in the job shop scheduling problem by comparing it with single-size training across three target sizes: 20 x 20, 25 x 25, and 30 x 30. In the curriculum setting, the policy is first trained on smaller instances and then progressively adapted to larger target sizes, allowing scheduling behavior learned in earlier stages to support learning on larger instances. Models are evaluated on unseen instances from 8 x 8 to 30 x 30 using the optimality gap, considering both generalization across all evaluation sizes and specialization on the target size. Results show that curriculum learning consistently reduces wall-clock training time, with larger benefits as the target size increases. The strongest advantage is observed at 30 x 30, where curriculum learning reduces the mean optimality gap across all evaluation sizes by approximately 8.1 percentage points, reduces the target-size mean optimality gap by approximately 8.6 percentage points, and saves approximately 50 hours of training time. --- ### ZoomDiff: A High-Fidelity Diffusion Model for Dual-Camera Smooth Zooming Authors: Jiayi Zhang, Renlong Wu, Yukang Ding, Sibin Deng, Wangmeng Zuo Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28083v1 Digital zoom transitions between dual cameras often exhibit conspicuous discontinuities in geometric structure and chromatic consistency, degrading the user experience. While recent dual-camera smooth zoom (DCSZ) methods attempt to mitigate this by fine-tuning frame interpolation (FI) models on DCSZ data, they struggle with the large cross-view disparities and complex geometric transformations. Considering that the generative prior of diffusion models is suitable for addressing this problem, we explore their application to DCSZ. However, naively applying existing diffusion-based FI models still yields low-fidelity transitions due to insufficient conditional guidance, high-frequency information loss during VAE encoding, as well as inadequate temporal consistency. To address this, we propose ZoomDiff, a high-fidelity diffusion model that leverages dual-camera inputs in both latent and pixel spaces for photo-realistic transitions. Specifically, we first strengthen dual-image conditional guidance during the multi-step denoising process to improve geometric consistency. Then we inject flow-aligned multi-scale features from the VAE encoder into the VAE decoder to recover high-frequency details, where flow-guided temporal consistency supervision are introduced to produce more smooth transitions. Extensive experiments on both synthetic and real-world datasets demonstrate that ZoomDiff outperforms state-of-the-art methods quantitatively and qualitatively. Project page: https://jiayi-hit.github.io/ZoomDiff.github.io/. --- ### Recursive Uncertainty-Gated Image Registration for Learning-based Algorithms Authors: Clara Rodrigo González, Oscar Bates, Fu Siong Ng, Meng-Xing Tang Published: 2026-09-23 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.28081v1 Conventional image registration algorithms are robust to domain shifts and achieve low errors, but they are slow and computationally expensive. Deep-learning methods are efficient at inference-time, but face challenges in out-of-domain samples. We propose Recursive Uncertainty-Gated Image Registration (RUGI), an algorithm for iteratively refining deformation fields predicted by learning-based registration models. At each iteration, the registration model predicts an incremental deformation, and a gating map modulates the update. Refinements are hence concentrated in regions that remain difficult to register. We explore two gating strategies: a learned uncertainty-based approach and an image residual error approach. We evaluate RUGI on cardiac MRI and echocardiography datasets and show consistent improvements over single-step inference. Ablation experiments demonstrate that iterative refinement alone improves registration, but informative spatial gating provides a significant additional benefit. The error-gated variant of RUGI can also be applied directly to existing pretrained models; applied to VoxelMorph, TransMorph, and CycleMorph, it yields MSE reductions of 27-37% with no modification to the original training procedure. The improvements in registration performance are reflected in decreased errors in ejection fraction estimation relative to ground truths. These results demonstrate that spatially selective iterative refinement provides an effective strategy to improve registration accuracy at inference-time. --- ### Reference-Based Analysis of Coherence and Diversity in Open-Ended Text Generation Authors: Esteban Garcés Arias Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.28080v1 Evaluating open-ended text generation involves understanding how different properties of a continuation relate to its perceived quality. We present a reference-based framework for examining coherence and diversity through three perspectives: aligning their evolution with human trajectories, comparing their summaries with a human continuation of the same prompt, and estimating their likelihood under a human reference distribution. Experiments with human quality ratings suggest that diversity-based alignment and mean-based comparisons capture quality-related variation, although the comparisons do not establish a predictive advantage for temporal alignment over simpler baselines. Reference likelihood also shows positive associations with ratings, with results varying across reference configurations and scoring horizons. Together, these analyses provide a structured way to examine how measured coherence and diversity relate to human judgments, while distinguishing similarity to human references from quality itself. Code and analysis resources are available at https://github.com/EstebanGarces/likely_human. --- ### LiAM-SAM: Lifecycle-Aware Memory for Robust SAM2-Based MOT Authors: Grégoire Francisco, Alessandro D'Amico, Samuele Costantini, Gianpiero Francesca, Lorenzo Garattoni Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28078v1 Segmentation-based multi-object tracking (MOT) with foundation video models such as SAM2 offers strong localization quality, yet remains fragile in crowded, real-world scenes. In detector-prompted SAM2 pipelines, failures typically arise at three stages of the object lifecycle: (i) erroneous or duplicate track initiation, (ii) memory drift during close interactions, and (iii) unreliable re-identification after long occlusions or re-entry. These errors corrupt object memory and accumulate over time, making long-horizon tracking unstable. In this paper, we reframe MOT as a lifecycle memory integrity problem. We present LiAM-SAM, a Lifecycle-Aware Memory (LiAM) framework with targeted mechanisms for each of the three failure modes. At track birth, to prevent faulty or duplicate initiations, we apply contrastive track initiation, which conditions each prompt on existing nearby tracked instances. To preserve memory integrity during strong interactions, we introduce motion- and geometry-grounded memory correction that resolves interaction confusions and suppresses drift. For reliable re-identification after disappearance, we maintain an adaptive context memory that promotes diverse and trustworthy references as long-term identity anchors. Finally, similarity aware spatial pruning optionally selects the memory tokens to retain at cross-attention time, improving efficiency with minimal accuracy loss. LiAM-SAM represents a modular, detector-agnostic, SAM2-based MOT system that achieves state-of-the-art HOTA and IDF1 on the evaluated benchmarks. In association-challenging environments, our ablations show that LiAM improves a detector+SAM2 baseline by +10.5 HOTA, +17.4 AssA, and reduces identity switches by 96%. --- ### TEEP-RCNN: Texture-Enhanced Edge-aware Perception for Steel Surface Defect Detection via Improved Convolutional Block Attention in Faster R-CNN Authors: Kirtan Rajesh Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28077v1 Steel surface defect detection is critical for automated industrial quality control but remains challenging due to subtle inter-class texture differences and pronounced class imbalance. We introduce TEEP-RCNN (Texture-Enhanced Edge-aware Perception Region-based CNN), a two-stage detector built on Faster R-CNN with a Feature Pyramid Network backbone and an improved Convolutional Block Attention Module (CBAM). Our CBAM adds dropout regularization in the channel attention MLP and batch normalization on the spatial attention branch, reducing co-adaptation and stabilizing gating logits. Training uses a differential learning rate protocol with cosine annealing warm-up, separating update rates for the pre-trained ResNet-101 backbone and the detection head. At inference, predictions are refined via Test-Time Augmentation fused with Weighted Box Fusion (WBF), improving localization stability on elongated and boundary-adjacent defects. On the NEU-DET benchmark across six defect categories, TEEP-RCNN achieves 73.3\% mAP@50 and 37.9\% mAP@50-95 in only 10 training epochs on a single GPU, competitive with YOLOv11m (76.2\% mAP@50, 100 epochs) while outperforming it on the rolled-in-scale category under the COCO metric. Per-class analysis shows the spatial attention branch is most effective on elongated texture defects such as patches and scratches, while crazing remains an open challenge across both paradigms due to its distributed non-local texture structure. --- ### SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference Authors: Xiaohuan Pei, Hengguang Zhou, Yuanhao Ban, Justin Cui, Jiaqi Feng, Haoyu Xie, Tao Huang, Pichao Wang, Yanchao Yang, Cho-Jui Hsieh Published: 2026-09-23 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.28064v1 Driving world-action models improve planning by coupling multimodal reasoning with future prediction, but their growing inference cost increasingly conflicts with the real-time latency requirements of vehicle control. Existing acceleration methods reduce tokens, layers, or sampling steps with policies selected prior to deployment, yet leave residual runtime variation largely unexploited after offline profiling and static scheduling on shared onboard compute. We observe that the largest admissible compute budget varies systematically with the residual runtime state, while recent realized latency provides a direct signal of the available compute slack. Motivated by this observation, we propose \textbf{SlackDrive}, a pre-inference compute allocator that reuses realized latency to select the compute budget of each control step before model execution. SlackDrive profiles the latency and planning utility of a small discrete budget set once, estimates online compute state from completed forwards, and selects the highest-utility budget predicted to remain within the admissible latency envelope, complementing existing profiling and resource scheduling while preserving the driving backbone and its compute actuator. On NAVSIM v2 with DriveDreamer-Policy, SlackDrive improves latency-constrained EPDMS by $21.7\%$ over the strongest baseline under a stringent latency regime, while the full-budget model and preconfigured token-pruning baselines exceed the admissible latency envelope under runtime contention. --- ### AstraLOD3: Zero-shot multimodal agentic reconstruction of LOD3 building models Authors: Bryan G. Pantoja-Rosero Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28061v1 Automated LOD3 building modeling typically relies on purpose-built geometric or learning-based pipelines, limiting flexibility across heterogeneous buildings and input evidence conditions. This study investigates whether Astra, a general-purpose multimodal foundation model, can address these limitations through zero-shot reconstruction of LOD3 building models within an agentic framework under bounded autonomy. AstraLOD3 combines multi-view images, calibrated cameras, and a filtered sparse SfM point cloud with a natural-language reconstruction specification, while the Astra agent dynamically selects and executes computational procedures using Python and Blender. Across 35 runs, including 24 benchmark buildings, AstraLOD3 achieved a mean FRDS of 0.9647 and geometric agreement comparable to that of previous purpose-built methods. Controlled ablations further revealed the effects of reconstruction guidance, evidence modalities, model configuration, and run-to-run variability. The results demonstrate that structured LOD3 reconstruction can be formulated as a constrained agentic process rather than as a fixed pipeline. Future work will investigate adaptive refinement, user-guided correction, task-specific specialization, and damage-aware reconstruction. --- ### A Native-Reference Coordinate Geometry for L2 Pronunciation Deviation Using Self-Supervised Speech Models Authors: Tina Raissi, Nhan Phan, Mikko Kurimo Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.28060v1 Self-supervised speech models encode rich phonetic information, but it remains unclear how to transform this information into interpretable metrics for second-language (L2) pronunciation assessment in spontaneous speech. We propose a native-reference coordinate geometry in which phone-class averages from native speech define a low-dimensional reference subspace, and L2 speech is evaluated by its distance to matching native phone-class coordinates. Unlike prior distance-based approaches, our method does not require parallel recordings with matched linguistic content or dedicated pronunciation labels. Across different self-supervised encoders and modeling choices, the resulting native-reference distances show negative Spearman correlations up to -0.5 with speaking proficiency, indicating that higher-proficiency speakers tend to lie closer to the native-reference space. --- ### Exact Quantile Balancing and Load-Error Injection for Mixture-of-Experts Authors: Pit Neitemeier, Jiaze Li, Alessio Serra, Philipp Scholl, Sohir Maskey Published: 2026-09-23 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.28053v1 Mixture-of-Experts (MoE) training requires global load balance to prevent expert under-utilization and local balance for efficient expert-parallel execution. Existing distributed Quantile Balancing (QB) uses shard-dependent or approximate global quantiles, while token-independent expert biases cannot ensure microbatch-level balance. We introduce Exact Quantile Balancing (EQB), which computes exact global-batch BF16 quantiles with negligible communication, and Load-Error Injection (LEI), which injects local load errors directly into router-score gradients. On 7.5B-parameter MoEs trained for up to 500B tokens, EQB improves global balance and downstream performance over naive QB, while LEI improves local balance and outperforms the GShard loss at comparable quality. --- ### Prompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings Authors: Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill Published: 2026-09-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.28049v1 Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough for deployment. Amateur team sport is a useful, largely untested place to check that assumption: over eight million students played a school sport in the United States in 2024-25 alone, almost none of it filmed by more than a single fixed camera, with several candidate actors crowded into frame and no operator or second angle to fall back on. Using volleyball as a test case, we ask whether strong performance on general video and world-model benchmarks translates into reliable, per-player attribution once footage is this chaotic, turning footage into statistics through a chain of tasks from finding play boundaries to naming who did what. We evaluate four approaches (prompting and agentic reasoning over frontier vision-language models, classical computer vision with small trained specialists, self-supervised video world models, and manual annotation) at every stage, on 66 amateur matches with 46,648 human-labelled contacts, filmed under conditions no published benchmark uses. No single paradigm wins every stage, and static, single-frame computer vision is not competitive at any stage involving motion or identity. A prompted model segments matches well, yet a far smaller trained model beats it at spotting contacts for a fraction of the cost, and the sport's own rules recover rally outcomes the pixels cannot. Identity is where every automated approach struggles: a jersey number is a static fact temporal reasoning cannot recover if never visible, unlike sporting action, a repeated motor pattern a temporal model can exploit, which is why holistic reasoning improves event detection while identity stays unchanged. We close with where each approach earns its cost, and what transfers beyond volleyball to amateur sport. --- ### TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval Authors: Mourad Hassani, Julien Romero, Amel Bouzeghoub, Christian Jacquelinet Published: 2026-09-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.28048v1 Modern information retrieval (IR) systems rarely represent time, yet many information needs depend on it: in clinical, journalistic, and legal search, when an event occurred can decide whether a document is relevant. Dense retrievers and Retrieval-Augmented Generation (RAG) pipelines match queries to documents well on topic but poorly on time, so they surface content that is on-topic yet temporally wrong. We introduce Temporal Textual Similarity (TTS), a task that measures how well two anchored texts align in time, independent of their topical similarity. We then present TEMPS (Temporal Embedding Model for Precise Search), a modular temporal branch that attaches to a frozen semantic retriever and trains on that signal. It resolves anchored temporal expressions to intervals and moment-matches each one to a Gaussian; the resulting ordering supervises an anchor-date-conditioned encoder, whose score we fuse with the semantic score at inference. Grounding supplies the supervision, so training uses no hand-labeled temporal data. The temporal score itself is the Gaussian-KL inclusion measure from distributional embeddings; what TEMPS adds is the grounding and the moment-matched supervision. On three temporal benchmarks, TEMPS improves MRR for every semantic backbone tested and, on TS- Retriever, lifts R@1 from 19.92 to 25.39 over the prior temporal state of the art. --- ### How Much Were You Told? Measuring External Information in Peer Reviews Authors: Matthieu Dubois, Pablo Piantanida, François Yvon Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.28041v1 Conference policies distinguish using Large Language Models (LLMs) to polish one's own review from delegating the critique, but current Artificial Text Detection (ATD) methods largely measure surface form rather than the origin of its content. We instead measure the external information carried by a review: information not explained by the reviewed paper and a generic reviewing instruction. We propose Self-Conditioning, an unsupervised information-theoretic estimator that compares the likelihood of a review under its production context with its likelihood when that context is augmented with hints extracted from the review itself. On the IntelLabs peer-review benchmark, Self-Conditioning separates fully-delegated from machine-polished reviews with AUC up to $1.0$ while remaining largely insensitive to surface rewriting. Moreover, as generators receive increasing amounts of externally-provided information, their scores move monotonically towards the human regime, unlike standard ATD baselines. High-temperature sampling can evade the estimator, but at the cost of output quality. --- ### Tensor Decomposition of Transformer Key-Value Caches: Spectral Structure and Format Comparison Authors: Rahul Krishnan, Volker Schulz Published: 2026-09-23 Categories: math.NA, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.28029v1 The key-value (KV) cache of autoregressive transformers can be viewed as a fourth-order tensor spanning attention heads, tokens, features, and grouped layers. We measure the singular-value spectra of all four mode unfoldings on Mistral-7B-v0.3 and LLaMA-2-13B and compare four standard tensor decompositions: Tucker, CP, tensor train, and t-SVD, at matched storage. The spectra partition the four axes into two classes. The token and feature modes carry low-rank structure, particularly for keys. The head and layer modes are nearly full-rank and resist compression at any practical error level. Among the four decompositions, Tucker achieves the lowest reconstruction error at every compression ratio from $2\times$ to $5\times$, because it can leave the full-rank modes untouched. Comparisons with two-dimensional unfolding baselines show that the preferred representation differs between keys and values: 2D methods achieve lower key error, while four-way Tucker achieves lower value error at matched storage. A mode-pinning theorem certifies the full-rank preservation from the measured spectra alone. Two further spectral properties affect the compressible modes without touching the full-rank ones: values reach a higher error floor than keys at every ratio, and post-RoPE keys lose $41\%$ - $64\%$ of their pre-RoPE compressibility on both models. --- ### Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing Authors: Norah Almousa, Shayan Peyghambari Oskoui, Raquel Coelho, Gayle Rogers, Xiang Lorraine Li, Diane Litman Published: 2026-09-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.28026v1 We investigate whether state-of-the-art large language models (LLMs) generate feedback that reflects the pedagogical practices of expert teachers in terms of feedback focus and adaptivity. Previous evaluation efforts have examined feedback characteristics, its impact on learning, and its target, yet the focus of feedback and its adaptivity remains largely overlooked. To bridge this gap, we adopt and refine Narciss's taxonomy into seven feedback focus types to annotate teacher and LLM-generated feedback across three university writing courses. We release FeedType, a benchmark containing annotated teacher and LLM feedback from six LLMs under three prompting strategies. We assess the coverage and distribution of feedback focus types, and examine whether LLMs adapt their feedback across draft stages and student performance levels as an expert instructor does. Our findings show that while most LLMs cover most feedback focus types, they fail to reflect teacher feedback distributions and show varying levels of adaptivity, with none matching the teachers' adaptive behavior. We believe FeedType will support future research on pedagogical alignment in LLM feedback generation. --- ### PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning Authors: Kevin Lee, Alison J. March Published: 2026-09-23 Categories: cs.LG, astro-ph.SR, cs.AI, physics.space-ph arXiv: https://arxiv.org/abs/2609.28022v1 Space weather early warning depends on detecting solar wind transients in in-situ measurements at the first Sun-Earth Lagrange point (L1), before they reach Earth. Fixed thresholds can miss combined magnetic and plasma structure, and many learning methods provide a single anomaly score. We present the Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather (PISCES), a convolutional autoencoder trained without catalog labels on OMNI solar wind measurements under physics constraints. Its loss includes magnetic field consistency, an empirical relation between temperature and velocity, the Parker spiral angle, and penalties on changes between consecutive one-minute samples in derived quantities calculated from the reconstruction. At inference, PISCES separates the anomaly score into magnetic and plasma reconstruction errors, physics relations, and residual corrections, and reports the magnitude of each contribution. Attenuation of the skip connections, selected on validation data, improves average precision for the trained models, while the untrained scores remain nearly the same. The trained models also give a more consistent ordering of these physical contributions. After smoothing with a trailing median, the alarms can precede independently observed sudden commencements, including positive sudden impulses. --- ### Improving Ensemble Filters with Flow Matching Authors: Haoyuan Chen, Alexandre Thiéry Published: 2026-09-23 Categories: stat.ML, cs.LG, math.DS, stat.ME arXiv: https://arxiv.org/abs/2609.28015v1 Data assimilation estimates a dynamical state from partial and noisy observations. Classical ensemble filters are efficient but restrict analysis updates through finite sample covariance and affine Gaussian distribution. We introduce the Flow Ensemble Filter (FlowEF), which uses conditional flow matching to transport the forecast ensemble from a classical baseline filter to an analysis ensemble. FlowEF uses a localized Gaussian source during training, transports forecast ensemble members from a baseline filter at deployment, and conditions its velocity field on ensembles from that baseline filter and the observation. The proposed model therefore learns a nonlinear update while mapping each baseline ensemble independently. For sparsely observed dynamical systems, FlowEF improves both deterministic and probabilistic metrics over all four classical ensemble filters. It also achieves the best performance among the state-of-the-art generative data assimilation models. --- ### SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentials Authors: Jonas Busk, Emil J. P. Frost, Yogeshwaran Krishnan, Henrik H. Kristoffersen, August E. G. Mikkelsen, Xueping Qin, Xin Yang, Heine A. Hansen, Arghya Bhowmik, Tejs Vegge Published: 2026-09-23 Categories: cond-mat.mtrl-sci, cs.LG, physics.chem-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2609.28013v1 Machine-learned interatomic potentials (MLIPs) for solid-liquid interfaces in advanced materials applications, e.g., electrochemistry, catalysis and corrosion, require training data that samples both liquid environments, the solid and the interface itself. We present SoLiD26, a curated solid-liquid interface dataset, containing 15.4 million first-principles atomic structures with up to 576 atoms and 15 chemical elements for training and evaluating MLIPs. The structures were compiled from density functional theory (DFT) calculations performed in studies of solid-liquid interfaces, with most configurations originating from ab initio molecular dynamics (AIMD) simulations. Each record contains atomic species, positions, simulation cell, periodic boundary conditions, potential energy and atomic forces. SoLiD26 includes aqueous coinage metal interfaces, electrode-electrolyte systems, and selected bulk reference structures, calculated with VASP using the PBE functional and D3 dispersion corrections. We describe the data ingestion and preparation pipeline used to construct the dataset. The application of SoLiD26 for training and evaluating MLIPs is demonstrated with a suite of MACE models on a simple training, validation and test split. The dataset enables development and benchmarking of MLIPs for structurally and chemically heterogeneous solid-liquid interfaces. --- ### Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints Authors: Imtiaz Ul Hassan, Öykü Akbulut, Onur Kaya, Ardhendu Behera, Swagat Kumar, Peter Matthew, Yonghuai Liu Published: 2026-09-23 Categories: cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.28007v1 Most Turkish-capable large language models (LLMs) are evaluated using general-purpose benchmarks rather than long, structurally complex domain documents. This paper evaluates five open-weight 7B-8B models for Turkish document question answering under a resource-constrained local deployment setting. The primary benchmark contains 100 systematically validated questions derived from a 109-page industrial R&D report, and the evaluation protocol is replicated using a second 112-page public-sector report and an independently constructed 100-question set. All models are evaluated locally on an NVIDIA RTX 3050 laptop GPU with 6 GB VRAM using controlled prompting, decoding, and 4-bit quantisation. The principal methodological contribution is an evidence-annotated evaluation protocol that separates retrieval failure from downstream model reasoning failure without requiring additional model calls. On the primary benchmark, end-to-end accuracy ranges from 49% to 75%. Seven lexical, dense, and hybrid retrieval configurations are additionally compared using 95% Wilson intervals and exact paired McNemar tests; none significantly outperforms the character TF-IDF baseline on either document. Evidence recall saturates differently across the two reports, showing that retrieval and effective context capacity can be binding constraints for some documents but not others. These results demonstrate that model selection, retrieval behaviour, and hardware limits must be evaluated separately when deploying open-weight LLMs for Turkish domain documents. --- ### Shared Global KV with Layer-Specific Local History Authors: Xinglang Xian Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28006v1 Decoder-only Transformer language models cache keys and values (KV) to reuse past computation during generation. Sharing KV across layers saves storage but reduces the diversity of representations available across depth. We study what local memory should retain alongside shared global KV, separating historical content from the input source used to form it. At 126M parameters and 2K context, an eight-seed study finds about 1.4% lower held-out test perplexity with local history than with a current-token local branch. Capacity, entry-count and training-compute controls support the value of historical content. In a two-seed comparison, this value persists when adjacent layers share local inputs while retaining independent projections; source sharing also shortens exact cache-construction dependencies. Against GQA and adjacent-layer KV sharing, equal bounded learning-rate searches and new-seed confirmation yield better same-source likelihood with larger caches and higher long-request latency. The ordering against adjacent-layer sharing persists after equal-token adaptation to 8K, with a short-context cost. The eight-seed external-book history effect remains uncertain, and downstream outcomes vary by task. We derive a sufficient suffix schedule that reduces upper-layer construction work while preserving the complete cache in exact arithmetic. --- ### Controlled Attribute-Specific Summarization of Interrogative Dialogues Authors: A Aditya Bhardwaj, Arjit Singh Arora, Md Shad Akhtar Published: 2026-09-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.28004v1 Effective summarization of interrogative dialogues is a critical task in forensic and investigative settings, requiring high factual accuracy, coherence, and attribute-specific relevance. In this work, we introduce CASPER, a novel Chain-of-Thought Attribute-Specific Prompting for Evaluative Summarization framework that leverages structured prompting and iterative refinement to generate high-quality summaries of interrogator-witness interactions. We construct MINDSum, a dataset extending the MIND corpus, comprising 6,000 utterance pairs annotated with event details, factual statements, character descriptions, and fillers. CASPER employs RoleEval, a hierarchical evaluation mechanism where multiple roles (officer, inspector, senior inspector) iteratively assess summaries based on predefined criteria. By integrating entity extraction and structured feedback loops, CASPER significantly improves factual consistency and contextual completeness compared to existing baselines. Experimental results demonstrate that our framework outperforms standard summarization models on both lexical (ROUGE) and semantic (BERTScore) metrics, while human evaluation confirms its alignment with expert reasoning. Our findings underscore the potential of controlled summarization in high-stakes domains, paving the way for AI-driven forensic intelligence. --- ### Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents Authors: Jiaxing Li, Lei Song, Rui Dong, Youyong Kong Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28003v1 Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment. However, in long-horizon and stateful environments, they often make structural errors such as missing required observations, performing premature writes, repeating failed calls, and violating action preconditions. These errors can lead to incorrect state updates, policy violations, and costly or irreversible consequences, making reliable tool execution a critical deployment challenge. Existing fine-tuning approaches require substantial data and computation, while flat memory may retrieve failed actions without preserving their causal context or safety conditions. In this paper, we propose FRESH, a Failure-aware Retrieval framework over Experience-Structured Heterogeneous graphs, which transforms historical successes and failures into structured external experience for tool-using agents. By explicitly modeling the dependencies among tasks, actions, errors, repairs, and execution conditions, FRESH helps frozen language models reuse reliable strategies, avoid recurring failures, and make safer decisions in stateful tool interactions. Experiments on $τ$-Bench and AppWorld with multiple open-source models show that FRESH consistently improves task success and tool-use reliability over no-memory agents and representative memory-based baselines. --- ### Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated Finance Authors: Jose Manuel de la Chica Rodriguez, Juan Manuel Vera Diaz, Pablo Delgado Romero Published: 2026-09-23 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2609.27994v1 Financial institutions are beginning to deploy agentic workflows in credit, fraud, collections, compliance, and operational control. Governance remains largely component-centric: each model or agent is specified, tested, authorized, and monitored locally. That is insufficient when institutional risk arises from the joint behavior of many locally acceptable components. We call this gap constitutional non-compositionality: local compliance checks need not compose into acceptable collective outcomes such as bounded disparate impact, market integrity, or traceable accountability. We propose ARIA as a finance-specific reference architecture and falsifiable research agenda for agent-population governance. It organizes six capabilities across normative-accountability, execution-control, and assurance-learning planes: policy specification, population-level observed-versus-expected behavior monitoring (M2), bounded authority, runtime containment, adaptive policy change, and preserved human oversight competence. Two simulations illustrate shared-signal thin-file exclusion under local controls and earlier warning from observed-versus-expected distributional monitoring in a constructed drift regime. The contribution maps these controls to fair-lending, EU AI Act, model-risk, and conduct-supervision evidence needs, and closes with a validation agenda rather than a production-effectiveness claim. --- ### Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces Authors: Andrew Bond, Ege Erdem Özlü, Tuna Çimen, Ilkin Umut Melanlioglu, Tolga Birdal, Erkut Erdem, Aykut Erdem Published: 2026-09-23 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.27988v1 Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direction is equally meaningful, but there is no reason to believe the true task geometry has this property. The task-sensitive geometry of the feature space is given by the pullback metric $g(F) = J(F)^\top J(F)$, where $J$ is the Jacobian of the decoder's output fed to a task-specific distance, with respect to the features. Storing the full $g$ is infeasible at modern scales, and for dense outputs such as depth maps even forming $J$ is impractical. We show that whether a low-rank approximation of this metric can be learned depends on the model-decoder pair, and we characterize this with a matrix-free diagnostic $κ_{cap}(r)$ computable with a low number of Jacobian-vector products. For tractable pairs, we develop the Spectral Pullback Network (SPN), which learns a low-rank version of the metric from randomized power iteration, and we distill it into a $310$K-parameter importance head that predicts token importance directly from the features. When the Jacobian spectrum is too spread out for a low-rank approximation, passing the decoder's input features through a VAE bottleneck can restore tractability. Across DPT, DINOv2, CLIP, and VGGT backbones, $κ_{cap}(r)$ predicts which learned-metric architectures are viable. The importance head reaches Spearman $ρ= 0.998$ on DINOv2 CLS, and our geometric token pruning reduces the additional depth error of ToMe-based token selection by $25\%$ on DPT depth at prune ratio $0.5$, without fine-tuning the ViT. Project page: https://cyberiada.github.io/TaskInducedViTs/ --- ### PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue Authors: Chenxuan Li, Jiayi Wan, Xinrong Chen, Zhongyu Zhao, Xuecheng Shang, Peixing Wan Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27987v1 Large language models (LLMs) have made substantial progress on medical question-answering, yet effective medical dialogue also requires learning to ask questions that uncover relevant patient information. To train such dialogue policies, a common pipeline combines supervised fine-tuning with reinforcement learning (RL) based on final diagnostic correctness. However, this outcome-based supervision does not directly distinguish the contributions of individual questions and provides no question-level feedback for unexecuted alternatives. To address this gap, we introduce PCQC (Privileged Counterfactual Question Credit), which uses privileged patient information during training to learn from questions never asked. During training, PCQC makes alternative questions directly comparable at the same dialogue state by using privileged patient facts to construct their answers. A frozen diagnostic scorer evaluates the diagnostic utility of each resulting question-answer pair by how strongly it supports the correct diagnosis. PCQC turns these comparisons into relative question credit that teaches the policy which questions to favor, directly supervising both executed and unexecuted questions alongside outcome-based RL without requiring complete rollouts for the unexecuted alternatives. Extensive experiments across four medical benchmarks demonstrate that PCQC achieves 63.10% mean diagnostic accuracy, outperforming GRPO and ATPO by 4.38 and 4.21 percentage points, respectively. These gains are achieved with 33.1% fewer inquiry turns than GRPO. --- ### Relative Discharge Stage (RDS) Classification: A Practical Indicator of Battery Discharge Progress Authors: Khoa Tran, Tri Le, Hung-Cuong Trinh, Hung Tran-Nam Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27986v1 Accurate remaining discharge time (RDT) prediction is challenging in real-world battery applications because future load profiles are unknown and highly dynamic. To address the uncertainty of continuous RDT regression, this paper introduces Relative Discharge Stage (RDS), a battery-management indicator that represents the remaining discharge condition using five interpretable classes: Normal, Good, Moderate, Low, and Recharge Required. Unlike state of charge (SOC), which reflects the current charge level, RDS characterizes the remaining discharge process without requiring future-current information during inference. A physics-informed RDS classification framework is proposed, combining SOC estimation with lightweight temporal learning. The SOC-estimation component includes second-order ECM state and terminal-voltage prediction, hysteresis and OCV temperature correction, core-temperature estimation, and AEKF state correction, supported by OCV evaluation, online STC-ECM parameter adaptation, and pretrained neural residual-voltage correction. The measured current, terminal voltage, surface temperature, and estimated SOC are arranged into a sliding observation window and processed by a lightweight temporal convolutional network. Experiments on two public lithium-ion battery datasets demonstrate robust RDS classification, with accuracy exceeding 80% under varying load and thermal conditions. --- ### Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices Authors: Ali Aliev, Maxim Rakhuba Published: 2026-09-23 Categories: cs.LG, cs.AI, math.DG, math.NA arXiv: https://arxiv.org/abs/2609.27982v1 In this paper, we are concerned with matrices formed by block-diagonal factors interleaved with fixed permutations -- a flexible family of structured matrices. This class has recently drawn interest in deep learning architectures for its balanced expressivity-efficiency trade-off, yet efficient computational strategies for working with it remain to be found. We approach this problem through Riemannian geometry and examine under what conditions this class admits a smooth manifold structure. For the practically important case of orthogonal two-factor matrices, we derive the essential Riemannian tools and propose efficient algorithms for their implementation. The algorithms leverage automatic differentiation, support parameter sharing within each factor, and avoid explicit dense matrix construction. We test them within the Riemannian optimization framework on the best matrix approximation problem and for parameter-efficient fine-tuning of large language models. Beyond the two-factor setting, we study the geometric and matrix-theoretic properties of factorizations with a larger number of block-diagonal factors. --- ### Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets Authors: Beomgu Kang, SoJin Yun, Hojoon Kim, Hyunseok Seo Published: 2026-09-23 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.27981v1 KV-cache eviction is typically evaluated through average quality-memory trade-offs, yet a small average loss can hide requests whose utility degrades materially. We reformulate eviction as a deployment risk-control problem: a material degradation occurs when eviction lowers task utility by more than a deployment-specified tolerance relative to full-KV inference on the same request, and deployment risk is the population frequency of such events. Given a reliability contract specifying a target risk level and confidence requirement, we use a compressor-agnostic post-hoc certification procedure to select a retention policy from calibration data with a finite-sample guarantee, falling back to full KV when no compressed policy is certified. Across multiple eviction methods, Llama and Mistral models, and LongBench and RULER-32K, the same contract supports substantially different levels of eviction: on Llama, it certifies SnapKV at 75% retention on LongBench but no tested compressed policy on RULER-32K, triggering full-KV fallback. Policies with empirical degradation rates below the 5% target can still fail finite-sample certification; on Llama LongBench, empirical thresholding selects uncertified policies that retain 5-10 percentage points less cache across fixed-budget methods. The proposed framework converts a deployment-level reliability requirement into a KV-memory operating point. --- ### Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery Authors: Rasmus Aagaard, Nicki Skafte Detlefsen Published: 2026-09-23 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.27980v1 Pruning large pre-trained transformer-based ASR models such as OpenAI's Whisper has seen great adoption, as pruning the decoder led to significant end-to-end transcription speedups. For instance, the {\tt whisper-large-v3-turbo} variant reduced the decoder from 32 to 4 layers, while Distill-Whisper similarly reduced the decoder to only 2 layers. Although some attention has been put towards reducing the size of the encoder, no approach has seen wide adoption. This could be due to the need for custom inference implementations to take advantage of the compressed model. We present an approach that ranks encoder layers by the leave-one-layer-out change in Word Error Rate (WER). The six layers that cause the least change are removed, corresponding to $18.5\%$ of the encoder stack. The pruned model requires no custom inference code as it is simply a more shallow encoder with fewer layers. We further distill using unlabeled monolingual speech data to recover performance degradation caused by the zero-shot layer pruning. Mean WER across four languages increases to $20.1\%$ after distillation, compared to $21.9\%$ zero-shot, going from a baseline of $18.2\%$. We release all of our code (https://github.com/rasgaard/whisper-encoder-layer-prune) and the pruned model (https://huggingface.co/rasgaard/whisper-large-v3-turbo-encoder-pruned). --- ### All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation Authors: Ohad Rahamim, Dvir Samuel, Idan Schwartz, Gal Chechik Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27901v1 Video is a rich representation of a physical event, capturing appearance, geometry, motion, and temporal evolution. Other modalities, such as 3D body motion or audio, encode narrower aspects of the same event. We find that joint multimodal diffusion transformers exhibit a corresponding asymmetry in cross-modal correspondence: companion modalities develop strong correspondences to video, but the reciprocal correspondences through which they constrain video remain substantially weaker. We express both directions as comparable correspondence distributions over video tokens and define their disagreement as the reciprocal correspondence gap. We introduce RecCAR, standing for Reciprocal Cross-modal Attention Regularization, a KL regularizer that uses the well-established video-to-modality correspondence as a fixed reference and aligns the weaker modality-to-video correspondence toward it. Across joint video-motion and video-audio generation, RecCAR improves the Human Anatomy score from 0.69 to 0.75 and reduces audio-video desynchronization from 0.804 to 0.752, while improving overall generation --- ### Evaluation of pre-trained models for pedagogical assessment of novel AI-assisted educational questions Authors: Michael Lawrence Castanares, Princess Ventures, Allan Tan Published: 2026-09-23 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.27749v1 The surge in AI-assisted generation of educational materials has outpaced our capacity to validate their pedagogical quality. Automated evaluation using Bloom Classifier models is a promising approach to assess educational materials at scale. These models show high accuracy within-distribution dataset (IID Dataset). However, applying the same models to new out-of-distribution (OOD) datasets such as AI-assisted generated questions could show performance degradation. To identify robust classifiers under dataset shift, we evaluated traditional Machine Learning (ML), transformer, and Large Language models on the Bloom level classification task. We also explored feature-engineering strategies incorporating NLP metrics, appending the learning objectives as part of the input, and text splicing to stabilize OOD performance. Our baseline tests show that TFPOS-IDF ML models perform poorly on OOD (Macro F1-score 0.48) compared to BERT (0.55) and LLMs (0.79). Text splicing improved macro F1-score performance of ML and BERT models (0.59 and 0.62, respectively). Appending the learning objectives with the input increased model performance on specific dataset. Model retraining provided the largest improvement across models and datasets. Overall, these findings highlight the trade-off on the use of pre-trained models with novel AI-assisted educational questions and how strategic feature enhancements help address loss in performance. --- ### Less Language, More Latents: Annotation-Efficient VLAs for Driving Authors: Alexey Zakharov, Kemal Oksuz, Puneet K. Dokania Published: 2026-09-23 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.27747v1 Vision-language-action models (VLA) promise human-steerable autonomous driving, but their training is bottlenecked by the scarcity of frames paired with natural-language instructions: while camera streams and expert trajectories are logged at scale, language annotations (e.g., turn left at the intersection) remain scarce and expensive to acquire. To address this challenge, we introduce Latent Action Driving Annotations (LADA), a three-stage pipeline that transforms abundant unlabelled observation-trajectory pairs into a substrate for language-conditioned control. First, we train a latent action model with a vector-quantised bottleneck, producing a compact codebook of high-level vehicle intents. Second, a small language-annotated subset is used to train a vision-language translator to map observations and language instructions into this codebook. Third, we train a driving VLA on observation-latent-action pairs over the full unlabelled corpus. Using fewer than 5% of language annotations and without leveraging any auxiliary chain-of-thought reasoning or visual question answering streams, LADA achieves a Driving Score of 87.98 and a Success Rate of 70.46% on the closed-loop Bench2Drive benchmark, matching or surpassing fully supervised baselines. --- ### Categorical Internalisation of Environmental Groupoids for Generalisable POMDP Solving Authors: Ben Opperman, Eduardo Alonso, Esther Mondragón Published: 2026-09-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.27745v1 This paper advocates category theory as a practical framework for structuring and improving rein- forcement learning in high-dimensional, partially observable environments. We model symmetries between environmental states by partitioning the state space into equivalence classes induced by sym- metry orbits, and organise each such class as a groupoid with a designated canonical representative. This allows the agent to share what it learns across many similar environmental states simultaneously, rather than treating every orientation or position as an entirely new problem. Learning is thus carried out on a symmetry-reduced state space with each orbit represented once, preserving structure while eliminating redundancy and improving sample efficiency. We implement this framework within standard reinforcement learning pipelines and evaluate two different approaches on partially observable benchmarks, demonstrating that orbit-based partitioning yields consistent performance improvements in environments exhibiting latent symmetry. Beyond these empirical results, our approach illustrates how categorical structure provides a principled bridge between abstract reinforcement learning formulations and their computational application, thereby establishing a pathway toward more structured and scalable learning systems. --- ### Limiting-Kernel Q($λ$): Bridging Short and Long Horizons Authors: Tolga Ok, Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani, Mohamad Amin Sharifi Kolarijani Published: 2026-09-23 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.27741v1 In value-based reinforcement learning, improving the accuracy of policy evaluation has been shown to improve downstream policy optimization performance. The widely adopted family of approximations relying on $n$-step truncation yields computationally efficient value estimators but is inherently limited to a short evaluation horizon. In contrast, methods that exploit the global structure of the transition dynamics can accelerate policy evaluation, but their memory and computational requirements often limit scalability to large or continuous state spaces. To reconcile these limitations, we introduce Limiting-Kernel Q($λ$) (LKQL), an off-policy value estimator that combines $n$-step truncation with a long-horizon approximation based on the limiting kernel (LK). LKQL has the same order of complexity as $n$-step estimators and integrates directly into both on- and off-policy actor-critic algorithms. We prove that, under aperiodicity and in the near-on-policy regime, the operator underlying LKQL improves the policy evaluation convergence rate over its truncated counterpart for sufficiently large $n$, and that LKQL itself converges almost surely to the optimal values in finite Markov decision processes (MDPs) under a fixed behavior policy. On the MuJoCo continuous-control benchmark, we show that LKQL improves over $n$-step baselines in most settings, particularly on long-horizon tasks. --- ### MENO: Memory-Efficient Neural Operator Authors: Shengyang Xu, Weijun Zhang, Jun Hu, Pengzhan Jin Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27739v1 We propose the Memory-Efficient Neural Operator (MENO) as a high-performance PDE neural solver based on the Manifold Function Encoder (MFE). MENO features three primary advantages: (1) MENO has a significantly smaller memory footprint and much faster training speed than other popular architectures, with the memory footprint being independent of the data resolution, and therefore holds the potential for scaling up to large-scale models. (2) MENO can accept PDE inputs of arbitrary form, including arbitrary geometric domains and arbitrary discretizations. In particular, it is capable of handling cross-geometry scenarios, i.e., where the input functions and the output solutions are defined on different manifolds. (3) MENO exhibits strong generalization capability, and achieves the best accuracy on most of the benchmarks we tested, compared with the results reported in the literature. The code is available on GitHub at https://github.com/jpzxshi/MENO, and all numerical examples in this paper can be run with a single command to reproduce the reported results. --- ### NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers Authors: Xiaohe Jiang, Guoqiang Zhang, Tianjin Huang, Ronghui Mu Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27735v3 Newton-Schulz (NS) iteration has recently been used in the Muon optimizer to transform update matrices during the training of large language models. Motivated by its spectral effect, we investigate applying NS directly to Transformer attention representations. We introduce Newton-Schulz Attention (NS-Attn.), a parameter-free transformation applied to the output of each attention head. Each head output is arranged as a feature-by-token matrix and normalized by its Frobenius norm. We then apply a finite NS polynomial step and restore the original norm. The objective is to reduce spectral concentration and increase effective rank before standard head merging and output projection. Across ViT and Swin on CIFAR-10 and CIFAR-100, NS-Attn. improves final-epoch accuracy in all 12 matched-seed comparisons, with mean gains of 0.25--0.83 percentage points. ViT ablations show higher mean accuracy with one iteration than with two. Spectral analysis further shows reduced leading-eigenvalue concentration and increased effective rank. These gains incur additional inference latency. --- ### InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies Authors: Sai Puneeth Reddy Gottam, Elmar Rueckert, Vedant Dave Published: 2026-09-23 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.27734v1 Vision-Language-Action (VLA) policies often rely strongly on the camera viewpoints seen during training, causing substantial performance degradation when deployed from unseen perspectives. Collecting demonstrations from sufficiently diverse physical viewpoints is expensive and still provides only sparse coverage of the viewpoint space. We introduce InfiNoVA, a data-augmentation framework that converts synchronized multi-camera demonstrations into a dense distribution of geometrically consistent training views. InfiNoVA reconstructs each manipulation trajectory as a time-varying 3D Gaussian representation and renders novel observations from sampled camera poses while preserving the original state-action correspondence. This explicit scene representation improves frame-level fidelity and temporal consistency while reducing task-critical hallucinations observed in generative novel-view synthesis. Across four real-world manipulation tasks, policies trained with InfiNoVA achieve 5.4x higher average success under unseen randomized viewpoints than both VISTA-based augmentation and the unaugmented policy. InfiNoVA further achieves 1.7x higher success than training directly on all five physical camera views. These results show that dense, geometrically grounded viewpoint augmentation provides a practical route toward camera-robust robot policies without modifying the underlying policy architecture. --- ### AI-Driven Neural Surrogates for In Silico Design of Cognitive-Affective Neuromodulation Targets Authors: Marco Rothermel, Madleen Stenger, Soroush Daftarian, Svenja Jule Francke, Bita Shariatpanahi, José C. García Alanis, Mohammad-Ali Nikouei Mahani, Stefan G. Hofmann, Tim Hahn, Hamidreza Jamalabadi Published: 2026-09-23 Categories: q-bio.NC, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2609.27729v1 In neuropsychiatry, the primary goal is often not only to decode brain activity but to change it, for example to lessen a negative affective bias or an overly salient memory. Motivated by control theory, we develop an AI-driven neural-surrogate framework that proposes candidate representational changes and tests their predicted perceptual effects from snapshots of stimulus-evoked fMRI activity, without physical stimulation. The framework combines fMRI decoding, deep generative modeling, and constrained latent-space steering. Valence and memorability are used only as worked examples. Using more than 36,000 image-fMRI observations from four deeply sampled Natural Scenes Dataset participants, subject-specific models recovered coarse generative structure from visually responsive cortex (two-way identification, 0.79-0.88; chance, 0.5). Graded perturbations were reconstructed as images and evaluated with automated scorers and human ratings from 7,200 trials by 18 participants. In the primary VDVAE model, valence shifted from -0.61 to +1.03 SD and memorability from -1.34 to +1.45 SD; a later Versatile Diffusion refinement reduced or altered these effects. Across five perturbation levels, human valence ratings moved in the predicted direction under the linear time-correction model (mean slope, 0.038 SD per unit of alpha; 95 percent CI, 0.003-0.074; positive in 16 of 18 participants). Perceived memorability did not change reliably. Baseline agreement with the automated assessor was suggestive for valence (r = 0.30) and weak for memorability (r = 0.10). Extreme perturbations drifted from the original stimulus, so intended change must be weighed against loss of fidelity. These findings provide a falsifiable upstream method for designing and behaviorally testing candidate representational targets for future neuromodulation in psychiatry, while marking the limits of the present static approximation. --- ### NeuralSRNF: Neural Square Root Normal Fields for the Statistical Shape Analysis and Generation of Nonrigid 3D and 4D Objects Authors: Awais Nizamani, Hamid Laga, Guanjin Wang, Farid Boussaid, Mohammed Bennamoun, Anuj Srivastava Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27728v1 We introduce NeuralSRNF, a novel framework for the statistical shape analysis and generation of genus-zero 3D and 4D objects that undergo nonrigid deformations. Traditional methods rely on complex and computationally expensive nonlinear elastic metrics that measure bending and stretching. Recent advances in elastic shape analysis achieve computational efficiency by mapping input 3D shapes to the space of Square Root Normal Fields (SRNFs) where the L2 metric approximates the partial elastic metric, significantly facilitating the process of computing geodesics and summary statistics. SRNFs, however, are not invertible, and the numerical algorithms used to map SRNFs back to the original space of surfaces remain computationally very expensive and often lead to approximate results. This paper addresses this fundamental SRNF inversion problem using a novel neural representation, termed NeuralSRNF. Unlike the commonly used numerical SRNF, NeuralSRNF is (1) continuous, and thus resolution-agnostic, enabling full functional shape analysis, (2) more accurate, and (3) computationally more efficient as it can compute inverse SRNF maps along a geodesic path in less than 3 s compared to over 10 min for the numerical SRNF. We demonstrate, using various datasets, the utility and efficiency of the proposed NeuralSRNF in multiple elastic 3D and 4D shape analysis tasks such as geodesic computation, deformation transfer, statistical summaries computation, and 3D shape generation. We show that it outperforms competing methods on most evaluated datasets and metrics by a wide margin in both accuracy and computational efficiency. The source code and additional results are available at https://awaisnizamani16.github.io/awais/NeuralSRNF/. --- ### SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving Authors: Zhilong Ge, Yuting Shao, Yutao Yang, Yuxuan Cai, Jie Zhou, Kai Chen, Bo Zhang, Qin Chen, Liang He Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.27717v2 Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather than internalized as reusable model capabilities. We introduce \texttt{SkillGym}, a framework that transforms these skills into executable, verifiable training environments for large language model agents. Its skill-to-task pipeline instantiates concrete tasks, verifies outcomes with code-based checkers, and assesses empirical skill dependence through contrastive executions. We construct and release 2,756 environments across 12 categories and collect 8,364 successful trajectories from multiple models and harnesses, averaging 49 tool calls and over 60k logged text tokens. These resources support supervised fine-tuning on verified workflows and reinforcement learning with outcome-based rewards. Under Claude Code, supervised fine-tuning improves Qwen3.5-35B-A3B by 199 Elo on GDPval-AA v2, 19.10 percentage points on Terminal-Bench 2.1, and 28.13 and 12.38 points on SkillsBench v1.1 with and without skills, respectively. Our 35B \texttt{SkillGym-Agent} reaches 51.47\% on skill-assisted SkillsBench, exceeding reported scores for Claude Sonnet 4.6, GPT-5.4 Mini, and DeepSeek V4 Pro. Without skills, it also surpasses skill-assisted bases under Codex and Claude Code, suggesting reusable procedural competence. --- ### FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology Authors: Anh-Tien Nguyen, Trung DQ. Dang, Nghiem Tuong Diep, Bui Ngoc Han Nguyen, Tan-Ha Mai, Miriam Cindy Maurer, Phuong Hoa Nguyen, Thi Thuy Uyen Nguyen, Youngjun Park, Daniel Sonntag, Duy Minh Ho Nguyen, Anne-Christin Hauschild Published: 2026-09-23 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.27710v1 Pathology vision-language foundation models vary in performance across diseases and tasks, with no single model consistently performing best. The high cost of expert pathology annotation can also limit the labeled data available for task-specific adaptation. Combining complementary pretrained representations is a potential approach to these limitations, yet learning an effective fusion from few labeled examples remains challenging. We introduce Few-shot Fusion Foundation Models of Computational Pathology (FFM-CP), which is a framework that combines multiple pathology vision-language models in the few-shot learning setting. The framework first aligns heterogeneous representations using a closed-form Orthogonal Procrustes transformation estimated from corresponding support images. This alignment preserves within-model feature geometry without training an additional alignment network. Within the aligned space, a unified graph enables information exchange across backbones by jointly refining support-image features and visual and textual class prototypes. These refined representations support complementary text-prototype and case-retrieval branches that capture semantic class knowledge and within-class visual variation, respectively. Each branch learns to combine predictions from all ordered backbone pairs, allowing queries encoded by one model to draw on evidence represented by another. We evaluate three backbone combinations on six histopathology datasets at 4, 8, and 16 shots per class. FFM-CP achieves higher mean macro-F1 than the strongest individually adapted member of each fused set in 50 of 54 comparisons. These findings suggest that combining complementary pretrained representations can improve histopathological classification when annotations are limited. --- ### DAVIO: Dense Monocular-Inertial SLAM with Feed-Forward Initialization and Pose-Conditioned Mapping Authors: Jaafar Mahmoud, Arthur Movsesyan, Mikhail Iumanov, Sergey Kolyubin Published: 2026-09-23 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.27702v1 A camera and an IMU are the minimal sensor setup for metric localization and dense mapping, yet classical visual--inertial filters must wait for parallax before they start and then retain only sparse landmarks. Feed-forward geometry models, in contrast, predict dense structure from a few images but provide neither metric scale nor gravity. We present DAVIO, which uses a single multi-view depth model, Depth Anything~3, for both start-up and mapping. At start-up, a five-image window and preintegrated IMU measurements form a feature-free linear system. Its robust, conditioning-checked solution bootstraps a VIO filter through buffered replay. During tracking, the filter's metric poses condition the depth model. Residual scale is corrected only along viewing rays, which preserves the metric camera baselines, and a gravity-preserving submap graph with drift-gated revisits refines the map. On EuRoC, DAVIO starts markedly earlier, reduces the localization error, and maps more accurately than SOTA feed-forward mappers given identical poses. On building-scale ORI sequences, DAVIO is on bar or better than SOTA mappers on the same odometry, and degrades far less when GT poses are replaced by real odometry. We release the code of DAVIO, a real-time dense metric SLAM system, to the community. --- ### SynSeq: End-to-End SYNTAX Score Prediction from Coronary Angiography Videos Authors: Christoph Baumann, Ronny Schweitzer, Noemi Pavo, Ulrike Attenberger, Christian Loewe, Philipp Seeböck Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27696v1 The SYNTAX score is an established tool for assessing coronary artery disease and guiding revascularization treatment decisions. However, its manual estimation from coronary angiography videos by clinical experts is time-consuming and subject to inter-reader variability. While machine learning has shown promise in automating this process, prior work has primarily focused on lesion detection, characterization, or binary disease classification, leaving direct SYNTAX score prediction relatively unexplored. We propose SynSeq, a video-based method for direct SYNTAX score prediction. It combines targeted preprocessing with a tailored training strategy using a zero-inflation-aware loss and linear target scaling. Evaluated on the public CardioSyntax dataset, SynSeq significantly outperforms previous state-of-the-art methods, improving $R^2$ by 0.55, reducing prediction bias by 93.1% and achieving more consistent performance across annotations from three independent expert graders. In addition, SynSeq achieves a weighted $F_1$-score of 0.80 for revascularization treatment recommendations, slightly below inter-expert agreement. These results demonstrate the potential of SynSeq to provide consistent, automated SYNTAX score assessment and reliable decision support for coronary revascularization planning. --- ### Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research Authors: Florian Kutzner, Celina Kacperski, Laura de Molière, Edoardo Chidichimo, Min Jun Jung, Felix P. S. Wallis, James K. He Published: 2026-09-23 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.27690v2 Researchers in industry and academia use synthetic survey respondents powered by large language models as substitutes for human samples. These synthetic populations require validation against real-world data, so researchers often address them using ad hoc comparisons with human surveys. Inspired by the intention-behaviour gap in behavioural science, we argue that these validations test the wrong thing for most applied cases where decision makers commission synthetic research to anticipate consequential behaviour. To address this problem, we propose a validation framework with two requirements. First, every validity claim must state its level of correspondence with human data: does the sample predict what the represented people do, which of four diagnostics (location, dispersion, response process and structure) does the validation address, and does the validation compare against experimental effects? Second, researchers must report validity claims for subgroups, since these groups are often the most affected by consequential decisions and aggregate accuracy hides their misrepresentation. Our validation framework operationalises three justice dimensions (distributional, procedural, and recognition) as measurable quantities and defines within-persona counterfactual experiments as a validation requirement. We then apply the framework to electric vehicle charging tariffs, before closing with a reporting checklist that researchers can use to make convincing validity claims. --- ### Gender Bias in Vision-Language In-Context Learning Authors: Tong Xiang, Yuta Nakashima, Noa Garcia Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27682v2 In-context learning (ICL) enables large vision-language models (LVLMs) to perform tasks by following patterns from in-context examples, yet its potential to amplify societal biases remains underexplored. We systematically investigate how ICL influences gender bias in LVLMs through VL-BICLE, an evaluation framework comprising six ICL settings, three tasks, and four datasets. Our experiments on six LVLMs reveal that gendered ICL demonstrations act as a directional force, shifting model bias toward the demonstrated gender through a cross-gender mechanism that disproportionately degrades performance on the opposite gender. This effect appears in image captioning and pronoun prediction but not in visual question answering, indicating that gendered ICL influences bias only when the task output involves gendered language. Similarity-based retrieval methods inherit the training pool's gender imbalance and offer no debiasing advantage, while standard quality metrics remain blind to these bias shifts. To mitigate this bias, we replace real in-context images with synthetic ones from stable diffusion models while keeping captions unchanged. This simple intervention reduces gender bias without degrading caption quality. --- ### CasCVS-Net: A Staged Multi-Task Cascade for Critical View of Safety Assessment Authors: Bock-Zien Toh, Yuanchuan Ren, Tay Aw Yu, Ng Khee Ong, Zhehua Mao, Sophia Bano Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27681v1 Automated assessment of the Critical View of Safety (CVS) in laparoscopic cholecystectomy requires both recognition of the three CVS criteria and anatomical grounding in small, rare, and often occluded hepatocystic structures. Learning-based methods differ in the anatomical information they use, from image-level classification to detection, segmentation, or graph-based reasoning, yet grounding the safety-critical anatomy remains the main bottleneck. We propose CasCVS-Net, a staged multi-task cascade that jointly performs object detection, semantic segmentation, and CVS assessment, trained on the Endoscapes dataset. The model couples the tasks through predicted anatomy: predicted boxes guide segmentation, and predicted masks provide region-level features for CVS classification, so CVS assessment at inference uses only model predictions rather than ground-truth annotations. To reduce optimisation instability in this coupled setting, training progresses from detection to detection-segmentation and then to the full three-task cascade, followed by task-wise fine-tuning. Evaluation on the public unseen test set shows that CasCVS-Net improves over matched single-task baselines on all three tasks, achieving 32.0 detection mAP, 46.8 semantic mIoU, 15.3 rare-anatomy mIoU, and 67.2 CVS mAP. It outperforms the state-of-the-art LG-CVS and SV2LSTG by 6.3% and 4.5% relative CVS mAP, respectively, corresponding to 4.0 and 2.9 mAP points. These results show that staged task coupling through predicted boxes and masks improves anatomical grounding for CVS assessment, particularly for rare hepatocystic structures. --- ### What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates Authors: Tian Zhou, Beverly Jin, Linxiao Yang, Xue Wang, Wenwei Wang, Bingqing Peng, Mengni Ye, Jinjie Gu, Liang Sun Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.27679v2 A tabular foundation model must discover which distinctions matter for each new table without updating its parameters. We develop in-situ representation refinement: support labels guide changes to the episode's representations, improving the information available to later queries. A regularized leave-one-out objective yields a support correction and its query extension. The leading term separates attention-based reading from state-dependent scaling, motivating RefineICL: an attention-gated, FFN-free contextual stack with selected low-rank feature interaction and typed memory. A direct intervention tests the role of evolving support states: removing one intermediate support update while preserving the block's query output increases final query cross-entropy in all 72 tested episodes. RefineICL-L24 reaches 0.93836 OVR-AUC and 0.87173 accuracy on AMLB29. A benchmark-informed continuation reaches 1644.8 Elo on the 38-dataset TabArena snapshot, 31.4 Elo above TabPFN-3 under the same evaluation. It also improves all four reported metrics over TabPFN-v3 on both TabZilla views. In a matched 100K-update depth grid, an expanded FFN gives no consistent validation benefit and uses 60.2% more peak inference memory at L8. These results connect learning within a forward pass to representation refinement and show how this view guides a competitive, memory-efficient model. --- ### Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding Authors: Fan Zhang, Yankai Chen, Zhuohan Xie, Yixi Zhou, Sijia Peng, Lei Fan, Xinhua Ji, Cunyuan Zheng, Huangyong Shan, Philip S. Yu, Xue Liu, Yu Chen et al. Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.27678v1 Contract inference requires multiple judgments about a shared document, but aggregate accuracy can conceal changes in the individual decisions. Repeated agreement is also insufficient: a model may consistently return the wrong answer. In this paper, we compare Jev with nine language models on ContractNLI, evaluating inference cost, response time, average correctness, and correctness across repeated request conditions. Controlled comparisons vary hypothesis visibility, requested outputs, and output order while keeping the contract and target judgment fixed. Jev has the lowest cost and median response time among the evaluated configurations, while hosted language models achieve higher baseline accuracy. Rankings by baseline accuracy differ from rankings by correctness across every condition and repeat, although small differences in the latter do not establish a general stability advantage. Development diagnostics further reveal compensating corrections and regressions, as well as persistent errors. These findings motivate evaluating cost and response time alongside whether individual judgments remain correct as the request configuration changes. Code: https://github.com/ZF-Utokyo/Jev-Benchmark --- ### RoadOcc Learns When to Persist, Transport, or Refresh Memory for Roadside Occupancy Prediction Authors: Xiaokai Bai, Lei Yang, Songkai Wang, Lianqing Zheng, Si-Yuan Cao, Hui-liang Shen Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27677v2 Fixed roadside cameras repeatedly observe a stable scene overlaid by sparse moving traffic. Temporal memory can recover weak observations, but reusing moving evidence at stale locations can corrupt occupancy predictions. Motion compensation addresses displacement, while reliance on the resulting history remains a separate learning problem. We introduce RoadOcc, which learns soft routing among fixed-coordinate history (\emph{Persist}), velocity-addressed history (\emph{Transport}), and current evidence (\emph{Refresh}). Motion state and class-consistent historical support supervise these source choices. Dynamic-aware cross-attention (DCA) updates candidate locations, multi-scale voxel velocity estimation (VVE) constructs transport addresses from multi-scale current--history correspondence, and velocity-guided dynamic sparse fusion (VDSF) combines routed evidence under fixed sparse-token budgets. On InfraOcc, RoadOcc reaches 65.29 mIoU and 32.37 dynamic mIoU, gains of 4.44 and 4.71 over STCOcc. Controlled address experiments show that VVE raises dynamic mIoU by 0.87 over fixed-coordinate reading. Across three seeds, supervised P/T/R adds 1.40 dynamic points over motion-corrected retrieval, while removing Refresh costs 0.32 points. Results from two transfer models, Occ3D-nuScenes, and longer intervals provide additional support. Code will be released. --- ### Track2Art: Articulated Object Model Recovery with Visual-Geometric Track Representations Authors: Xiaotong Li, Yixiong Jing, Junsheng Ding, Weihang Li, Benjamin Busam, Guangming Wang, Brian Sheil Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.27675v2 Understanding articulated objects is fundamental for robotic interaction, requiring accurate rigid-part discovery and the recovery of their kinematic relations. Existing approaches often treat articulation as a by-product of reconstructed geometry or recover it through per-instance optimization. We instead build on the hypothesis that articulation is directly observable from persistent motion: points on the same rigid part move coherently, while relative motion between parts reveals their kinematic constraints. We present Track2Art, a motion-centric framework for recovering structured articulated objects from RGB-D interaction videos. Track2Art lifts tracked image points into persistent 3D trajectories and combines pretrained tracking features, visual descriptors, and explicit trajectory geometry. These representations are grouped into a variable number of rigid-part hypotheses and subsequently used to recover directed kinematic relations, joint types, and joint geometry through rotation-equivariant learned--analytic reasoning. On the aligned 20-object PartNet-Mobility suite, Track2Art achieves 0.695 Point IoU and 0.410 end-to-end J@20, while requiring neither ground-truth part counts nor test-time optimization. ---