# Research Papers — 2026-09 · bundle page 208 of 266 > Full-text markdown of papers #10351–10400 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/208 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/207.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/209.md) ### ONE CYLinder: A Benchmark for Graph-Based Surrogate Modeling of Unsteady Bluff-Body Flows Authors: Théodore Michel, Antoine Campos, Alban Dujardin, Henry Areiza, Philippe Meliga, Elie Hachem Published: 2026-09-08 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2609.08947v1 Graph-based surrogate models offer a promising route to accelerate computational fluid dynamics (CFD) simulations on unstructured meshes. However, their development is limited by the scarcity of benchmark datasets spanning multiple flow regimes and standardized protocols for long-horizon autoregressive prediction. We introduce ONECYL (ONE CYLinder), a new benchmark for unsteady flow past a circular cylinder across laminar, transitional, and high-Reynolds-number regimes. The benchmark comprises 450 high-fidelity Variational Multiscale finite-element simulations (270,000 flow snapshots) with randomized cylinder geometries, providing time-resolved velocity and pressure fields together with mesh connectivity, geometric descriptors, Reynolds numbers, and integrated aerodynamic quantities. Beyond the dataset, ONECYL establishes a unified evaluation framework combining full-field rollout errors, virtual probes, and drag and lift predictions to assess numerical accuracy and physical fidelity. To accompany the benchmark, we develop a Graph Transformer as a reference baseline predicting velocity and pressure fields autoregressively on unstructured meshes. Using ONECYL, we investigate geometric representations and physics-based regularization across the three Reynolds-number regimes. The results show that explicitly encoding the cylinder geometry through a level-set representation consistently improves long-horizon prediction accuracy and generalization to unseen geometries, while divergence-based regularization becomes increasingly beneficial as flow complexity increases. The ONECYL benchmark and its Graph Transformer baseline provide a reproducible framework for evaluating graph-based surrogate models and establish a foundation for future research on long-horizon prediction of unsteady bluff-body flows. --- ### SkillAdam: Stable and Efficient Skill Evolution for Agents Authors: Gaoyuan Li, Meihao Fan, Yizhe Liu, Shaolei Zhang, Ju Fan, Siyi Wang, Jiaheng Hou, Xudong Weng, Honghan Tian, Zang Li Published: 2026-09-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.08944v1 Agent skills provide a lightweight way to equip frozen language-model agents with domain knowledge and procedural guidance, yet obtaining high-quality skills remains costly and difficult to scale. Expert-written skills require substantial human effort. Recent skill self-evolution methods automate an iterative loop that uses execution feedback to revise skills, but their heuristic update strategies often yield unstable optimization and low iteration efficiency. We identify two challenges in realizing stable and efficient skill self-evolution. Direction Stability requires effective corrections to accumulate rather than be overwritten by iteration-local feedback. Update Adaptivity requires the scope of each revision to reflect the consistency of recent case-level improvements. We introduce SkillAdam, an Adam-inspired framework for optimizing discrete and non-differentiable skill documents. As a functional analogue of Adam's first moment, an optimization memory records identified problems and the outcomes of prior solution attempts to stabilize the update direction. As a functional analogue of Adam's second moment, a volatility-driven edit budget tracks the history-weighted variation of recent case-level improvements and adaptively controls the update magnitude. Across seven benchmarks that span short- and long-horizon tasks, SkillAdam achieves state-of-the-art performance with more stable optimization dynamics. It also obtains stronger skills with substantially fewer optimization iterations and lower cost than prior methods. Code repository: https://github.com/ruc-datalab/SkillAdam --- ### Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation Authors: Xingyu Deng, Mingzi Cao, Nikolaos Aletras, Xi Wang, Mark Stevenson Published: 2026-09-08 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.08943v1 Automatic fact-checking systems assess the veracity of claims given evidence from relevant documents. Large Language Models (LLMs) have demonstrated strong performance in fact-checking due to their general reasoning capabilities. However, it remains unclear whether they faithfully make use of the evidence provided to reach veracity judgments or rely on parametric knowledge. To investigate this, we introduce Fact-Ablated Evaluation (FAE), a new evaluation framework that iteratively ablates the cited evidence to assess whether LLMs revise their predictions accordingly. Our empirical results show that current off-the-shelf LLMs as fact-checking systems rely more on their parametric knowledge than on the evidence provided. To bridge this gap between prediction accuracy and evidence grounding, we propose REAL (Rigorous Evidence Ablation Learning), a training framework that promotes evidence-dependent verification through counterfactual evidence supervision for the LLM-as-verifier models. Experiments on four fact-checking datasets across different domains demonstrate that models trained with REAL obtain superior evidence-dependent capabilities compared to standard fine-tuned models. Our findings highlight that strong fact-checking performance can still coexist with weak evidence dependency, while REAL encourages veracity predictions to remain more closely tied to the availability of supporting evidence. --- ### EgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning Authors: Jingpu Yang, Fengxian Ji, Mingxuan Cui, Yilin Sun, Hang Zhang, Jianhua Zhu, Yufeng Wang Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08938v2 UAV video question answering requires separating camera motion from changes in the scene, but RGB-only multimodal models receive no explicit, stable reference for that separation. We present EgoSIS, a pose-free adapter that converts RGB-derived bidirectional flow into motion-canonical visual evidence in three stages. Factorized Visual Ego-Transitions (FVET) fits a robust image-plane transition and exposes motion, residual-support, and reliability factors. Reliability-Gated Ego-Transition Memory (ReTEM) uses reliability-weighted updates for a bounded history and re-anchors it at cuts or sustained uncertainty. Ego-Aligned Spatial Evidence (EASE) warps supported visual features into each segment's local anchor and injects four spatial evidence tokens per visual slice through zero-initialized residuals, without changing Qwen's visual-token count. On SIS-Bench, EgoSIS-8B obtains 89.9\% perception, 82.5\% perception-plus-memory, and 76.2\% overall accuracy, with the largest gains concentrated in self-awareness perception and memory. The adapter thus provides an interpretable interface between optical flow and spatial reasoning. --- ### EgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning Authors: Jingpu Yang, Fengxian Ji, Mingxuan Cui, Yilin Sun, Hang Zhang, Jianhua Zhu, Yufeng Wang Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08938v1 UAV video question answering requires separating camera motion from changes in the scene, but RGB-only multimodal models receive no explicit, stable reference for that separation. We present EgoSIS, a pose-free adapter that converts RGB-derived bidirectional flow into motion-canonical visual evidence in three stages. Factorized Visual Ego-Transitions (FVET) fits a robust image-plane transition and exposes motion, residual-support, and reliability factors. Reliability-Gated Ego-Transition Memory (ReTEM) uses reliability-weighted updates for a bounded history and re-anchors it at cuts or sustained uncertainty. Ego-Aligned Spatial Evidence (EASE) warps supported visual features into each segment's local anchor and injects four spatial evidence tokens per visual slice through zero-initialized residuals, without changing Qwen's visual-token count. On SIS-Bench, EgoSIS-8B obtains 89.9\% perception, 82.5\% perception-plus-memory, and 76.2\% overall accuracy, with the largest gains concentrated in self-awareness perception and memory. The adapter thus provides an interpretable interface between optical flow and spatial reasoning. --- ### AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing Authors: Ziyang Ma, Zhikang Niu, Wenming Tu, Tianrui Wang, Ruiqi Yan, Junxi Liu, Yanru Huo, Nickk Huang, Yang Liu, Qicong Xie, Zeyu Xie, Hui Wang et al. Published: 2026-09-08 Categories: cs.SD, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2609.08936v1 We introduce AuK, an open-source foundational model that unifies speech generation and editing through a common interface of natural-language instructions and audio context. To support this broad capability set, we construct approximately 3.03 billion instruction--audio instances and 1.95 million hours of effective supervision across five task families: speech generation, content editing, enhancement and separation, paralinguistic editing, and acoustic editing. AuK combines a multimodal large language model for semantic conditioning, an VAE jointly trained on speech, general audio, and music for acoustic conditioning, and a hybrid rectified-flow Transformer that performs dual-stream MMDiT blocks followed by unified single-stream DiT blocks for generation. Training begins with generation-only warm-up and proceeds to joint generation--editing pre-training. We then apply complementary post-training strategies: human-feedback preference optimization for open-ended editing and reward-based reinforcement learning for speech generation. To reduce inference cost, we further distill the model with consistency initialization and task-routed Decoupled DMD. The resulting AuK-Flash performs 4-step inference without classifier-free guidance and achieves a 4.5 wall-clock speedup over the full model under matched conditions. Experiments demonstrate leading performance on zero-shot and instruction-controlled speech generation and general instruction-guided editing, while remaining competitive on signal-level restoration tasks. We release both the source code and model weights to support reproducibility and further research. --- ### When Models Defer to Wrong Answers: A Robustness Audit of Source-Attributed Cues in Multiple-Choice QA Authors: Manikandan Ravikiran, Siddharth Vohra Published: 2026-09-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.08934v1 Language models often receive a question together with a claim about what another source answered. We audit whether such claims destabilize answers in multiple-choice question answering. For each item, we hold one wrong option fixed across misleading conditions and vary the cue template attached to it. We introduce \emph{neutral-conditioned misleading cue adoption rate} (NC-MCAR), which measures switches to that option only on valid cued trials where the same model first selected the gold answer under a neutral prompt. This is a measure of answer instability, not proof that the model knew the answer or that all deference is irrational. We evaluate four instruction-following models on MMLU-Pro and IndicMMLU-Pro in English, Hindi, Bengali, Tamil, and Telugu. Across 220{,}000 outputs, the expert template yields 41.1\% aggregate NC-MCAR, compared with 12.5\% for the majority template. These two conditions use the same wrong option and final instruction. Filler accuracy remains well above expert-wrong accuracy, while correct-cue prompts have high valid-response accuracy. The audit documents answer instability relevant to grounding under the tested forced-choice prompts: a bare, unverified source claim can outweigh an answer that was previously consistent with the task evidence. --- ### Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents Authors: Wenbo Gao, Zhaomou Song, Zhiyuan Ji, Renxi Liu, Xing Li, Xianzhi Yu, Xiaoguang Li, James Chung-wai Cheung, Weizhe Lin, Yaoyuan Wang Published: 2026-09-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.08919v1 Autonomous agents powered by large language models (LLMs) continuously accumulate experience through interaction, creating an opportunity to improve future behavior through self-evolution. A fundamental challenge is how to transform abundant, task-specific interaction experience into reusable model competence without sacrificing the ability to adapt rapidly to newly observed evidence. Explicit textual states, such as skills and agent harnesses, provide fast, human-readable and editable adaptation, but incur persistent dependence on external context; parametric policies provide compact and reusable competence, but are substantially slower to update. We present \textit{Experience Funnel}, a self-evolving framework that couples fast state adaptation with slow policy consolidation in an alternating loop. Interaction trajectories are first distilled into an explicit textual state, where newly acquired experience can be rapidly incorporated and validated. The framework then selectively identifies state-enabled behavior that remains useful across state revisions and consolidates it into the policy through transition-aware distillation. The updated state--policy pair subsequently generates new rollouts, providing fresh evidence for the next round of state adaptation and policy consolidation. Experiments across diverse agent benchmarks show that \textit{Experience Funnel} consistently improves agent capability over state-only evolution and policy-internalization approaches, while progressively converting useful explicit experience into autonomous policy competence. --- ### Data-Efficient Crosswalk Segmentation from Overhead CCTV via Confidence- and Geometry-Guided Pseudo-Labeling Authors: Abdirashid Omar, Jonghyuk Park Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08914v2 Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoint and appearance shift when applied to elevated CCTV. We investigate a data-efficient target-domain pipeline using 241 manually annotated CCTV images and 5,926 unlabeled CCTV frames. A source-domain experiment trains a 31.0M-parameter custom U-Net on 3,300 first-person-view (FPV) images and obtains 93.05% IoU on its 330-image FPV test split. This result is a source baseline, not transferred performance: the released CCTV notebook instantiates a 42.0M-parameter DeepLabV3-ResNet50 from torchvision weights, and no compatible mapping from the U-Net checkpoint is implemented. Training on 201 manual CCTV images and selecting on 40 held-out manual masks yields 88.91% IoU. The model then predicts all unlabeled frames; image-level certainty and a largest-component area prior rank the candidates, and the top 1,000 attain mean certainty 0.976 and mean combined score 0.988. A repository audit shows that the reported second-stage 98.52% IoU was measured on a 150-image split containing only teacher-generated pseudo-masks. Because of a directory-layout mismatch, the executed combined-data loader found zero manual samples and split 1,000 pseudo-labeled samples into 850 training and 150 evaluation samples. We therefore report 98.52% as internal pseudo-label agreement rather than human-ground-truth accuracy. The defensible target-domain result is 88.91% IoU on the 40 manual validation images. Batch-one FP32 inference at 512 x 512 requires 12.98 ms, corresponding to 77.03 FPS, on an NVIDIA RTX A6000 48 GB GPU. These findings support the practicality of confidence-and-geometry filtering while also showing why pseudo-label evaluation must remain isolated from the labels used for self-training. --- ### CoSA: Correlation-Guided Change A ttention with Learnable Residual Gating for Remote Sensing Change Detection Authors: Abdirashid Omar, Jonghyuk Park Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08914v1 Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoint and appearance shift when applied to elevated CCTV. We investigate a data-efficient target-domain pipeline using 241 manually annotated CCTV images and 5,926 unlabeled CCTV frames. A source-domain experiment trains a 31.0M-parameter custom U-Net on 3,300 first-person-view (FPV) images and obtains 93.05% IoU on its 330-image FPV test split. This result is a source baseline, not transferred performance: the released CCTV notebook instantiates a 42.0M-parameter DeepLabV3-ResNet50 from torchvision weights, and no compatible mapping from the U-Net checkpoint is implemented. Training on 201 manual CCTV images and selecting on 40 held-out manual masks yields 88.91% IoU. The model then predicts all unlabeled frames; image-level certainty and a largest-component area prior rank the candidates, and the top 1,000 attain mean certainty 0.976 and mean combined score 0.988. A repository audit shows that the reported second-stage 98.52% IoU was measured on a 150-image split containing only teacher-generated pseudo-masks. Because of a directory-layout mismatch, the executed combined-data loader found zero manual samples and split 1,000 pseudo-labeled samples into 850 training and 150 evaluation samples. We therefore report 98.52% as internal pseudo-label agreement rather than human-ground-truth accuracy. The defensible target-domain result is 88.91% IoU on the 40 manual validation images. Batch-one FP32 inference at 512 x 512 requires 12.98 ms, corresponding to 77.03 FPS, on an NVIDIA RTX A6000 48 GB GPU. These findings support the practicality of confidence-and-geometry filtering while also showing why pseudo-label evaluation must remain isolated from the labels used for self-training. --- ### The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation Authors: Aaryaman Kalani, Murari Mandal, Dhruv Kumar, Mohan Kankanhalli, Yash Sinha Published: 2026-09-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.08901v2 Approximate machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. We identify a previously undocumented confound in how unlearning is evaluated on BatchNorm-based architectures: a single forward pass over retain data, an operation that modifies no weight, can deterministically rewrite the model's normalization state and reverse the apparent surface-metric forgetting. We formalize this operation as a weight-preserving fixed-point operator and prove that any pre-versus-post gap it induces is provably attributable to BN running statistics rather than to any modification the unlearning method made to the weights. This attribution claim cleanly separates measurement failure (BN artifact) from encoder failure (residual weight-encoded information, recently documented in concurrent work), and the same operator framework yields a unique decomposition of linear-probe elevation into BN-measurement-bias and encoder-geometry components. Empirically, the artifact reverses headline forget accuracy by up to 78 pp across nine evaluated methods on standard benchmarks; an attacker with as few as 10 unlabeled images recovers most of the masked accuracy; and a strict GroupNorm control reduces the artifact to zero across all methods. The tested membership-inference attacks change little under recalibration, locating the observed evaluation failure in forget accuracy and linear probing. --- ### The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation Authors: Aaryaman Kalani, Murari Mandal, Dhruv Kumar, Mohan Kankanhalli, Yash Sinha Published: 2026-09-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.08901v1 Approximate machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. We identify a previously undocumented confound in how unlearning is evaluated on BatchNorm-based architectures: a single forward pass over retain data, an operation that modifies no weight, can deterministically rewrite the model's normalization state and reverse the apparent surface-metric forgetting. We formalize this operation as a weight-preserving fixed-point operator and prove that any pre-versus-post gap it induces is provably attributable to BN running statistics rather than to any modification the unlearning method made to the weights. This attribution claim cleanly separates measurement failure (BN artifact) from encoder failure (residual weight-encoded information, recently documented in concurrent work), and the same operator framework yields a unique decomposition of linear-probe elevation into BN-measurement-bias and encoder-geometry components. Empirically, the artifact reverses headline forget accuracy by up to 78 pp across nine evaluated methods on standard benchmarks; an attacker with as few as 10 unlabeled images recovers most of the masked accuracy; and a strict GroupNorm control reduces the artifact to zero across all methods. The tested membership-inference attacks change little under recalibration, locating the observed evaluation failure in forget accuracy and linear probing. --- ### From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection Authors: Mengzhe Geng, Yujia Lu, Manuela Kunz, Patrick Littell Published: 2026-09-08 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.08899v4 Speech deepfake detectors usually emit one score per utterance, but a borderline score does not reveal why two examples differ during retrospective error analysis. We ask whether a final score can be calibrated from component fields while keeping those fields visible for inspection. We build a decision record with a passive detector score and a score from a probe applied to a marked copy. It also includes retrieval support held out of the evaluated family, a margin from a support-set profile, and raw neighbor closeness. A cross-fit calibrator combines these fields and two differences between raw scores into one final score. On matched ASVspoof development data, the calibrated record reduces equal error rate (EER) by 3.48 percentage points relative to the fixed retrieval-augmented rule. It reaches 8.43% EER, whereas a passive WavLM baseline reaches 6.71% on the same subset. The record is therefore not the strongest detector in this comparison. Its value is to retain inspectable component fields while producing one scalar score for retrospective diagnosis. --- ### From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection Authors: Mengzhe Geng, Yujia Lu, Patrick Littell, Manuela Kunz, Xie Chen Published: 2026-09-08 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.08899v1 Speech deepfakes can mimic a speaker's voice convincingly enough to deceive listeners and automated systems. This has driven strong progress in speech deepfake detection, but most detectors still end with one score per utterance. That score is useful for ranking systems, yet it says little about why a borderline item should be trusted, deferred, or reviewed. Two utterances can fall in the same score band for different reasons, for example because passive and retrieval evidence disagree or because the keyed probe is unavailable. We ask whether the final decision can remain scalar without discarding that provenance. We answer this question with an auditable decision record that carries four aligned cues into a late calibration step: a passive detector score, a conditional keyed-probe score on a marked derivative, retrieval support, and a speaker-profile margin, together with explicit disagreement coordinates. On the 4,080-example ASVspoof 5 Track 1 matched subset, the fixed retrieval-augmented rule improves on retrieval-only evidence, from 15.84 percent to 11.91 percent EER, and late calibration over the full record reaches 8.43 percent EER. At a 33.75 percent review budget, the exposed cue union covers 82.85 percent of the calibrated model's errors. The best passive WavLM run still reaches 6.71 percent EER, so we do not present the decision record as a stronger standalone detector. Its contribution is to preserve the evidence behind each surfaced utterance while still producing one operating score for thresholding and review. --- ### Evolution of Multimodal Question Answering: From Modality-Adaptive Extraction to Unified Language Representation Authors: Abdullah Al Shafi Published: 2026-09-08 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.08896v1 The rapid growth of multimodal data has intensified the need for question answering (QA) systems capable of reasoning across heterogeneous sources such as text, tables, and images. In this paper, we present a comprehensive methodological comparison of three influential frameworks, namely Multimodal Adaptive Extraction (MAE), Solar, and UniMMQA, tracing the evolution of multimodal question answering from modality-adaptive pipelines to fully unified architectures. We examine how each approach models cross-modal interactions, transforms heterogeneous inputs, and performs reasoning, highlighting key design differences in modality representation, reasoning, and answer generation. Our analysis demonstrates a clear shift from explicit modality-specific processing toward unified text-centric formulations enabled by pre-trained language models (PLMs). Empirical comparisons across benchmark datasets show that this transition leads to substantial improvements in both Exact Match (EM) and F1-Scores, with UniMMQA achieving the most consistent and scalable performance. Despite these advances, we identify persistent challenges, including information loss during modality transformation, error propagation in multi-stage pipelines, and limitations in capturing fine-grained cross-modal dependencies. Overall, this study provides a deeper understanding of current design trends and offers insights into the future direction of unified multimodal reasoning systems. --- ### Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems Authors: Maximilian Schall, Sedigheh Eslami, Markus Krimmel, Antoine Chaffin, Louis Milliken, Bo Wang, Denis Bykov Published: 2026-09-08 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2609.08887v2 Evaluating first-stage retrievers in large-scale production RAG requires a benchmark that pairs a large-scale corpus with a large set of agent-reformulated search queries based on real user queries and their conversation threads, and that labels many relevant documents per query. No existing public benchmark evaluates this setting: large-scale collections typically provide only a small number of evaluation queries, whereas benchmarks with many queries generally contain only millions of documents. Moreover, most benchmarks assess human-written queries, while the first-stage retrievers in agentic RAG pipelines serve machine-written reformulations whose distribution differs from human search behavior. To overcome these evaluation gaps, we introduce Q2D-Web (Query2Doc-Web), a large-scale agentic retrieval benchmark consisting of a 190M-document web corpus and 70k agentic search queries in ten languages, reformulated from real-world user queries in production systems. Q2D-Web provides three sets of fixed relevance judgments: agent citations, production rankings, and a combined set that unions both signals and adds LLM-based judgments of unlabeled pooled documents to reduce false negatives. We benchmark 13 retrievers including lexical, dense, and late-interaction models and find that their relative ordering is largely insensitive to the choice of judgment set, while diverging substantially across topical domains, query languages, and query types. To enable fast evaluation, we also study subcorpus sampling as an approximation to full-corpus evaluations. Retaining a third of the corpus, selected by reciprocal rank fusion over pooled retriever runs, preserves the full-corpus model ranking under the combined judgments while raising absolute Recall@1000 only by 4 to 7 points. The public leaderboard is accessible under: https://huggingface.co/spaces/perplexity-ai/q2d-web-leaderboard --- ### Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems Authors: Maximilian Schall, Sedigheh Eslami, Markus Krimmel, Antoine Chaffin, Louis Milliken, Bo Wang, Denis Bykov Published: 2026-09-08 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2609.08887v1 Evaluating first-stage retrievers in large-scale production RAG requires a benchmark that pairs a large-scale corpus with a large set of agent-reformulated search queries based on real user queries and their conversation threads, and that labels many relevant documents per query. No existing public benchmark evaluates this setting: large-scale collections typically provide only a small number of evaluation queries, whereas benchmarks with many queries generally contain only millions of documents. Moreover, most benchmarks assess human-written queries, while the first-stage retrievers in agentic RAG pipelines serve machine-written reformulations whose distribution differs from human search behavior. To overcome these evaluation gaps, we introduce Q2D-Web (Query2Doc-Web), a large-scale agentic retrieval benchmark consisting of a 190M-document web corpus and 70k agentic search queries in ten languages, reformulated from real-world user queries in production systems. Q2D-Web provides three sets of fixed relevance judgments: agent citations, production rankings, and a combined set that unions both signals and adds LLM-based judgments of unlabeled pooled documents to reduce false negatives. We benchmark 13 retrievers including lexical, dense, and late-interaction models and find that their relative ordering is largely insensitive to the choice of judgment set, while diverging substantially across topical domains, query languages, and query types. To enable fast evaluation, we also study subcorpus sampling as an approximation to full-corpus evaluations. Retaining a third of the corpus, selected by reciprocal rank fusion over pooled retriever runs, preserves the full-corpus model ranking under the combined judgments while raising absolute Recall@1000 only by 3 to 7 points. The public leaderboard is accessible under: https://huggingface.co/spaces/perplexity-ai/q2d-web-leaderboard --- ### FRAME: Factored Retrieval via Attribute Readouts for Object-Centric Scene Memory Authors: Woosang Jeon, Sanghyeok Choi, Minwoo Kim, Taehyun Jung, Taehyeong Kim Published: 2026-09-08 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.08886v1 Language-guided robots need persistent scene memories to follow instructions, revisit objects, and resolve references to objects encountered over time. While much of language-guided scene-memory retrieval has emphasized spatial or relational references, many everyday object references specify objects by multiple persistent attributes, such as category, material, size, or surface appearance. We formalize this problem as attribute-compositional retrieval, where a fixed object-centric scene memory is queried with natural language to retrieve the object satisfying the requested attributes. To investigate this capability directly, we introduce a controlled evaluation protocol with fixed scene memories and attribute-defined targets, separating retrieval from perception and annotation ambiguities. We then propose FRAME, which turns language into query-relevant attribute weights, uses learned readouts to estimate per-attribute evidence from object embeddings, and ranks objects by aggregating this evidence according to the query. Across held-out scenes and object assets, FRAME outperforms representative scene-memory retrieval baselines while reducing post-decomposition object scoring to lightweight matrix-vector computation. These results position attribute-compositional retrieval as a complementary scene-memory capability for language-guided robots, showing that persistent object attributes can be exposed as composable evidence for accurate and efficient multi-attribute retrieval. --- ### Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Concepts Authors: Mengmeng Ma, Yunxiang Peng, Tang Li, Lu Lin, Binsheng Zhao, Oguz Akin, Xi Peng Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08879v1 Cancer segmentation models can fail silently, generating plausible but incorrect masks that risk missed findings or unnecessary biopsies. A critical question arises: Do AI models "know" when they are wrong, and if so, can we use the signal to predict their own failures? Humans do have a "Feeling of Error" (FOE): a spontaneous sense of unease that flags a potential error during thinking. We investigate whether cancer segmentation models exhibit an analogous internal signal. Unlike output-level cues (e.g., prediction confidence or uncertainty), which offer no insight into why a failure occurs and suffer from a sensitivity-quality tradeoff where high detection sensitivity could degrade overall segmentation quality. We instead propose to capture the model's FOE from its inner workings. Using mechanistic interpretability tools, specifically Sparse Autoencoders, we decompose internal neural activations into a dictionary of human-interpretable concepts and show that failure cases exhibit a distinct latent signature: fewer active concepts with lower activation magnitudes compared to successful segmentation. By training a classifier on these concept activations, we achieve accurate failure detection along with explanations for the model's mistakes. Experiments on prostate, pancreatic, and brain cancer segmentation demonstrate that our approach outperforms output-based methods in failure detection while preserving segmentation quality. --- ### High-Magnetization Sampling at Low Temperatures: Ising Models and Bayesian Sparse Linear Regression Authors: Syamantak Kumar, Purnamrita Sarkar, Kevin Tian, Yusong Zhu Published: 2026-09-08 Categories: cs.DS, cs.LG, math.PR, math.ST, stat.ML arXiv: https://arxiv.org/abs/2609.08873v1 Sparsity is a powerful structural resource in optimization and statistics. We develop frameworks for leveraging sparsity in sampling problems over the Hamming slice $\mathcal{X}_k^d:=\{\mathbf{x}\in\{\pm 1\}^d:|\{i:\mathbf{x}_i=1\}|=k\}$, in high-dimensional regimes where $k\ll d$ (i.e., where $\mathcal{X}_k^d$ is \emph{highly magnetized}). We use our frameworks to design improved samplers for canonical problems in the study of \emph{Ising models} and \emph{Bayesian sparse linear regression}. Our first main result considers the \emph{Sherrington--Kirkpatrick} (SK) model restricted to fixed-magnetization slices $\mathcal{X}_k^d$. We give a polynomial-time sampler for fixed-magnetization SK models at any inverse temperature $β>0$, under arbitrary external fields, provided that $k\le c_βd$ for an appropriate constant $c_β$. By combining this result with an annealing strategy for estimating normalizing constants, we obtain polynomial-time samplers for the SK model at arbitrarily low temperatures under a sufficiently strong external field of strength $h$. In the large-$β$ limit, our framework permits sampling at field strengths within constant factors of the \emph{Almeida--Thouless line} delineating the replica-symmetric and replica-symmetry-breaking regions ((dAT78)), improving polynomially over the field strength $h(β)$ required by the recent work of (BAR26). Our second main result concerns the measurement complexity of polynomial-time Bayesian sparse linear regression. Recent work by (KSTZ25) shows how to sample from the canonical \emph{Gaussian spike-and-slab posterior} with expected sparsity $k$, at any signal-to-noise ratio, given $n\gtrsim k^3\log^3 d$ Gaussian measurements. We improve this requirement to $n\gtrsim k^{3/2}\log^2 d+k\log^3 d$, using a common sparsity-aware framework underlying both our results. --- ### OntoKG-EQ: A provenance-grounded, competency-question-governed knowledge graph for auditable analyst querying Authors: Furqan Nasir, Muhammad Atif Saeed, Muhammad Ehsan, Sher Jeel Ahmad, Abdul Moiz Altaf Published: 2026-09-08 Categories: cs.ET, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2609.08869v1 Analysts in emerging equity markets keep answering the same questions. Did fundamentals match the market's response? How does the local currency co-move with returns? Which firms outperform sector and benchmark, and which disclosures coincide with abnormal trading? These answers come from ad-hoc spreadsheets that are hard to reproduce, audit, or trust. We present OntoKG-EQ, a knowledge-based system that makes such queries reproducible, evidence-linked, temporally explicit, valid, and inspectable. It couples a bounded, competency-question-governed core ontology with a provenance-aware knowledge graph in which every class, property, shape, and metric is justified by one of five frozen questions. The system materialises market data into the graph, computes the metrics, validates its structure against declarative shape constraints, answers each competency question with a graph query, derives typed findings, and generates an explanation tracing each result to its observations, evidence, sources, and provenance. We evaluate on curated datasets from three emerging markets (Pakistan, Malaysia, Indonesia). Once each market's data is mapped into the common schema, the ontology, shapes, queries, and rules are reused unchanged. A relational-database baseline shows the graph changes no analytics. Its value is governance, provenance, and self-explaining structure. Because answers are rendered deterministically from the validated graph, their consistency with it is guaranteed by construction. Used as a reference, the system measures how consistently eight open language models transcribe the same evidence (provenance coverage 0.00 to 1.00). A study with a 17-participant convenience panel finds the evidence bundle significantly increased perceived trust and completeness. Code and data are openly released. --- ### SeGDeP: Semantic- and Geometric-Aware Decoupled Prompts for Reasoning Segmentation Authors: Linnan Zhao, Xu Liu, Lingling Li, Licheng Jiao, Fang Liu, Wenping Ma Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08867v1 Reasoning segmentation converts an implicit linguistic conclusion into a precise mask, requiring both semantic identification and spatial grounding. Existing MLLM-segmenter interfaces either use a special trigger or compress both signals into one context, although they receive different supervision and fail differently. This coupling obscures whether a failure arises from target interpretation or from localization. We present SeGDeP, an explicit what-where interface. A semantic prompt branch and an independent geometric projection path transform resolved MLLM states into semantic features and a DETR-predicted box, which jointly condition a SAM 3 mask decoder. Training first aligns this executable interface, then uses group reward-decoupled policy optimization (GDPO) to balance format, box-IoU, and mask-IoU feedback. SeGDeP-4B reaches 82.7 average cIoU over eight RefCOCO-family splits and 66.0/59.6 gIoU on ReasonSeg val/test while adapting only 0.38% of Qwen3-VL parameters through LoRA. Controlled stage-wise ablations, gradient diagnostics, and prompt interventions further show that the two paths develop complementary semantic and geometric specialization rather than duplicating the same evidence. --- ### API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces Authors: Jennifer Wang, Joachim Baumann, Daniel E. Ho, Sanmi Koyejo Published: 2026-09-08 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.08861v2 Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assumption underlying benchmark scores is that the model performance measured through APIs faithfully reflects the behavior of deployed systems. We challenge this assumption by auditing ChatGPT, Claude, and Gemini across seven systems and nine benchmarks spanning general capability, social bias, and sycophancy. We find systematic API--interface differences in both accuracy and consistency. On average, API evaluations score 3.4 percentage points higher in accuracy and 2.1 percentage points higher in test--retest agreement than corresponding interface evaluations. For ChatGPT, the performance difference between API and interface access rivals the API-only difference between GPT 5.3 and GPT 5.4. Put differently, switching access surfaces can degrade performance as much as downgrading a full model generation. We further test whether exposed API controls can reproduce interface behavior by varying system prompts, sampling parameters, and reasoning settings. These controls shift behavior in some cases but do not reliably eliminate the gap. Our findings document a context-validity gap: measurements obtained through APIs do not necessarily generalize to corresponding deployed interfaces, complicating the use of API evaluations as proxies for deployed systems. --- ### API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces Authors: Jennifer Wang, Joachim Baumann, Daniel E. Ho, Sanmi Koyejo Published: 2026-09-08 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.08861v1 Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assumption underlying benchmark scores is that the model performance measured through APIs faithfully reflects the behavior of deployed systems. We challenge this assumption by auditing ChatGPT, Claude, and Gemini across seven systems and nine benchmarks spanning general capability, social bias, and sycophancy. We find systematic API--interface differences in both accuracy and consistency. On average, API evaluations score 3.4 percentage points higher in accuracy and 2.1 percentage points higher in test--retest agreement than corresponding interface evaluations. For ChatGPT, the performance difference between API and interface access exceeds the API-only difference between GPT 5.3 and GPT 5.4. Put differently, switching access surfaces can degrade performance as much as downgrading a full model generation. We further test whether exposed API controls can reproduce interface behavior by varying system prompts, sampling parameters, and reasoning settings. These controls shift behavior in some cases but do not reliably eliminate the gap. Our findings document a context-validity gap: measurements obtained through APIs do not necessarily generalize to corresponding deployed interfaces, complicating the use of API evaluations as proxies for deployed systems. --- ### Earth System World Model for What-If Simulations: A Case Study for Terrestrial Ecosystems Authors: Zhihao Wang, Ruichen Wang, Ruohan Li, Lei Ma, George Hurtt, Xiaowei Jia, Gengchen Mai, Shaowen Wang, Yiqun Xie Published: 2026-09-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.08855v1 Machine learning emulators have become essential for accelerating expensive Earth-system simulations, but most existing approaches remain passive forecasters: they reproduce simulator trajectories under prescribed forcings without an explicit interaction mechanism for user-specified interventions. This limits their use in interactive scientific workflows and Earth-system digital twins, where users often need to explore how a system would respond if selected state components were changed. We propose an action-conditioned world-modeling framework for Earth-system emulation that reformulates simulator trajectories as supervision for controllable state-transition learning. The key idea is transition-action pretraining: naturally observed state changes are treated as label-free action supervision, allowing the model to learn both prescribed dynamics and action-conditioned responses without manually annotated interventions. We further introduce masked response learning to infer unobserved variables under partial state edits and learn coupled system dependencies. We test this framework on ecosystem dynamics across six global regions and multiple stand ages. Experiments show that the model preserves competitive long-horizon emulation accuracy while enabling controllable structural interventions and coherent responses in coupled ecosystem-cycle variables. These results suggest a practical route from passive Earth-system emulators toward interactive, intervention-aware scientific surrogates. --- ### Length Generalization for Transformers via Compression Authors: Georg Zetzsche, Hongjian Jiang, Andy Yang, Pascal Bergsträßer, Marco Sälzer, David Chiang, Anthony W. Lin Published: 2026-09-08 Categories: cs.LG, cs.FL, cs.LO arXiv: https://arxiv.org/abs/2609.08851v1 Recent advancements in transformer length generalization theory enable us to reliably predict when a transformer can learn to solve a task. In particular, the C-RASP hypothesis (a formalized version of the so-called RASP-l conjecture) posits that transformers length-generalize on a task if and only if a solution is expressible in the C-RASP language. While this hypothesis has strong empirical validation, theoretical problems arise from the fact that no computable length generalization bounds exist for C-RASP, alongside the discovery of seemingly contradictory experiments. To address these problems, we refine the C-RASP hypothesis utilizing the recently-proposed fragments C-RASP+ and C-RASP1. These fragments have computable length generalization bounds, though in the worst case requiring an extremely large (double exponential) sample size. It is an open question whether these sample size bounds are tight. In this paper, we resolve this open question by providing an exponentially tighter bound. In doing so, we show a polynomial length generalization bound for transformers if we adopt compressed strings, via a novel connection to power words. As an application, we show how this yields a fine-grained analysis of the C-RASP conjecture that resolves contradicting experimental evidence against it. --- ### DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding Authors: Zhuo Cao, Bingqing Zhang, Sen Wang, Xue Li Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08850v1 Text-guided Video Temporal Grounding (VTG) aims to localize the relevant segments in an untrimmed video based on text queries, yet collecting dense temporal annotations and training task-specific models remain costly and brittle under distribution shift. Recent training-free VTG approaches mitigate this issue by directly matching pretrained vision-language representations, but they still face two fundamental information bottlenecks: frame-wise visual encoding overlooks temporal dynamics, while fixed query embeddings cannot resolve query ambiguity. To address these issues, we propose DSE-VTG, a \underline{D}ual-\underline{S}ide \underline{E}nhancement framework that addresses both without any task-specific training. On the visual side, Multi-scale Similarity Fusion (MSF) combines frame- and clip-level similarities into a unified, temporally aware similarity profile. On the textual side, Query-level Test-Time Adaptation (Q-TTA) optimizes a lightweight additive offset to adapt the query embedding to the video at test time, without finetuning the backbone or calling external large language models. Extensive experiments on three standard and two OOD benchmarks show that DSE-VTG achieves state-of-the-art performance among training-free methods. On Charades-STA, it improves mIoU over the strongest prior training-free method by 5.61 points. Under distribution shift, DSE-VTG reaches 50.86 mIoU on Charades-CG Novel-Word, surpassing the strongest supervised baseline by 2.76 mIoU. Our code will be released upon acceptance. --- ### FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute Authors: Hongchi Xia, Tianhang Cheng, Wei-Chiu Ma, Shenlong Wang Published: 2026-09-08 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.08848v1 We present FIRE3D, a unified framework that takes a single RGB image or casual RGB video and transforms it into simulation-ready 3D scene assets for games and interactive applications in under a minute. At the core of FIRE3D is a feed-forward, end-to-end network that predicts a compositional scene representation from posed RGB-D observations estimated from the RGB capture, including the 6-DoF pose, bounding box, mesh, and texture for every object. By modeling the scene as a collection of discrete entities, FIRE3D produces amodally complete and simulation-ready environments where objects are physically decoupled and ready for interaction. Our framework requires no test-time optimization, runs orders of magnitude faster than prior interaction-ready methods, and provides object-level completeness beyond existing feed-forward 3D approaches. We demonstrate competitive or state-of-the-art results across pose accuracy, geometry completeness, and texture quality across various datasets while being orders of magnitudes faster. Project page: https://xiahongchi.github.io/Fire3D/ --- ### Leveraging Visual and Geometric Priors for Metric-scale and Complete Vehicle Gaussian Reconstruction from Limited Views Authors: Jinyu Miao, Jiusi Li, Yifei He, Miao Long, Kun Jiang, Mengmeng Yang, Diange Yang Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08841v1 High-fidelity vehicle assets are essential for controllable traffic scene generation, particularly for synthesizing rare and safety-critical long-tail scenarios. However, reconstructing a reusable vehicle representation from in-the-wild onboard images remains challenging for two reasons. First, image-to-3D generation methods generally produce models without reliable metric scale. Second, onboard cameras usually observe only one side of a target vehicle, making conventional multi-view reconstruction incomplete on unobserved regions. To solve these problems, we propose a feed-forward vehicle asset reconstruction method, which leverages two complementary priors to reconstruct 3D Gaussian representations for vehicles using sparse one-sided observations. To achieve metric-scale reconstruction, a visual foundation model is first utilized to serve as a visual prior for Gaussian initialization. The Gaussian attributes are then estimated by a learnable encoder-decoder module. A symmetry-aware cloning strategy is presented to complete the unobserved side directly in Gaussian space, which exploits the bilateral structure of vehicles as a geometric prior. Experiments on the public dataset demonstrate that the proposed method significantly outperforms existing approaches in both vehicle asset completeness and geometric accuracy. --- ### Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course Authors: Evelyn Duesterwald, Benjamin Elder, Lilian Ngweta, Shashanka Ubaru, Malgorzata Zimon Published: 2026-09-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.08832v1 Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains largely unaddressed. When given the same task five times, a ReAct agent on the AppWorld benchmark using GPT-4.1 succeeds in all five runs only 53% of the time, even though its per-run pass rate averages 77%. We call this 24-point shortfall the consistency gap, and we argue that addressing it is a precondition for trustworthy AI agent deployment. We present a self-evolving agent framework that reduces this gap by identifying unstable, low-consistency steps in agent trajectories and converting them into episodic memory the agent can draw on in future runs. At its core is a Consistency Analyzer that pinpoints where and why a trajectory is likely to flip across executions, and a Guideline Generator that converts the diagnosis into targeted guidelines, committed to memory and injected into future agent executions on similar tasks. On AppWorld with ReAct/GPT-4.1, our framework raises the fraction of tasks that succeed in all five runs by +16 points on same-task evaluation and +13 points on similar-task generalization. --- ### A Closed-Form Estimator and Diagnostic Battery for Anchor-Judge Error Correlation, Under a Single-Common-Factor Model Authors: Veerendra Kumar Sunkavalli Published: 2026-09-08 Categories: stat.ME, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.08826v1 When an external reference set (an anchor) is used to decompose an LLM-judge panel's error into a quality signal and a shared common-mode error, standard practice assumes the anchor is uncontaminated: its error uncorrelated with the judges' shared error. We study when that assumption can be dropped and replaced by an estimate. Under a single-common-factor model, >=2 judges and >=2 anchors point-identify the quality variance, the common-mode variance, and each anchor's contamination correlation rho_k in closed form, with an exact per-anchor-pair failure boundary; a designated clean-anchor estimator, by contrast, reports a contaminated companion anchor as fully clean once its trusted anchor is itself contaminated. Because the single-common-factor assumption is itself untestable, the estimator ships gated behind a calibrated diagnostic battery (judge-covariance dispersion; over-identification; a family-block test from judge metadata, with a family-blocked estimator that removes family-level shared-residual bias exactly), bootstrap confidence intervals with measured coverage, and a weak-identification screen. A proposition maps which violations bias rho_k, in which direction, and which evade detection. For ordinal scores we show an identification hierarchy: with all variables ordinal, rho_k is not identified at any number of anchors; with ordinal judges and >=3 continuous anchors it is, and we give an estimator for that case. On real data the validation is asymmetric, and we say so plainly: the diagnostics are validated in the rejecting direction (both real panels we test are correctly rejected by the model-adequacy pre-test), while the estimator is validated in simulation and stress-tested semi-synthetically under oracle calibration; no real panel has yet passed the pre-test, and the pre-test exists precisely to say so. All results replay offline from shipped, checksummed artifacts. --- ### Beyond Gait: Person Identification from Millimeter-Wave Point Clouds Across Activities of Daily Living Authors: Xilai Wang, Zixiong Han, Saad Rhanmouni, Chenzhe Zhao, Yunze Lu, Miodrag Bolic Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08818v1 Person identification from millimeter-wave (mmWave) point clouds has mainly relied on gait. Indoor walking, however, is often brief and interrupted, while other activities of daily living (ADLs) may provide complementary identity information. We investigate identification across seven ADLs using mm-ADL, a new point-cloud dataset collected from 11 subjects under a controlled protocol. This extension introduces heterogeneous states and transitions whose spatial and temporal characteristics vary with activity. We therefore study whether activity can provide useful context for learning identity representations. We propose an activity-conditioned framework in which a human activity recognition router dispatches each clip to an activity-specific identity expert. The framework is implemented as a supervised mixture of experts, using a dual-stream static-dynamic PointNet (DS-SDPNet) to combine time-aggregated spatial structure with frame-to-frame information. We evaluate closed-set identification (ID) and subject-disjoint re-identification (ReID). With learned hard routing, ID accuracy increases from 62.1% to 68.0%. In a two-occupant ReID setting, hard routing increases mAP from 57.2% to 75.4% and Rank-1 accuracy from 59.1% to 82.1%. Under a matched gallery partition, activity-specific experts also outperform a shared embedding, showing that the gain extends beyond restricting the gallery. These results support the feasibility of using ADLs beyond gait for identification and the value of activity conditioning under controlled indoor conditions. --- ### Dynamic Latent Space Modeling of Inhomogeneous Poisson Network Processes with Applications to International Relations Authors: Jie Jian, Jiguo Cao, Owen G. Ward Published: 2026-09-08 Categories: stat.AP, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.08813v2 We study continuous-time relational event data, where time-stamped dyadic interactions reflect both individual node propensities and evolving relational proximity. We propose a dynamic latent space model for inhomogeneous Poisson processes, where event intensities depend on node-specific activity parameters and time-varying latent distances modeled via flexible B-splines. We prove model identifiability by decoupling baseline activity from latent position, ensuring high interaction volumes do not warp the spatial map. For scalability, we develop a minibatch stochastic gradient algorithm with stable initialization and geometric anchoring, alongside an effective-degrees-of-freedom BIC for tuning model complexity. Simulations confirm accurate parameter recovery and out-of-sample prediction. Applied to cooperative diplomatic events among 60 major economies (1995--2022), the model uncovers shifting patterns of international cooperation and isolates mobile geopolitical actors from stationary institutional anchors. --- ### Dynamic Latent Space Modeling of Inhomogeneous Poisson Network Processes with Applications to International Relations Authors: Jie Jian, Owen G. Ward, Jiguo Cao Published: 2026-09-08 Categories: stat.AP, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.08813v1 We study continuous-time relational event data, where time-stamped dyadic interactions reflect both individual node propensities and evolving relational proximity. We propose a dynamic latent space model for inhomogeneous Poisson processes, where event intensities depend on node-specific activity parameters and time-varying latent distances modeled via flexible B-splines. We prove model identifiability by decoupling baseline activity from latent position, ensuring high interaction volumes do not warp the spatial map. For scalability, we develop a minibatch stochastic gradient algorithm with stable initialization and geometric anchoring, alongside an effective-degrees-of-freedom BIC for tuning model complexity. Simulations confirm accurate parameter recovery and out-of-sample prediction. Applied to cooperative diplomatic events among 60 major economies (1995--2022), the model uncovers shifting patterns of international cooperation and isolates mobile geopolitical actors from stationary institutional anchors. --- ### ArmPoser: Real-Time, Calibration-Free Arm Pose Estimation from Smartwatch IMU Authors: Bishnu Dev, Vasco Xu, Xi-Aan Loh, Chenfeng Gao, Henry Hoffmann, Karan Ahuja Published: 2026-09-08 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2609.08806v1 Arm pose estimation enables applications in fitness, extended reality input, rehabilitation, and life logging. Prior smartwatch-based approaches rely on calibration poses and preprocessing pipelines that transform raw IMU measurements into standardized training formats. These steps hinder deployment in everyday settings and introduce errors due to imperfect calibration and sensor drift. We present ArmPoser, a calibration-free arm pose estimation system using a single smartwatch IMU. Our central contribution is training models directly in the reference frame native to consumer smartwatches, aligning learning with how IMU data is produced by deployed devices. By operating on device-native axes, ArmPoser removes the need for coordinate transformations, explicit alignment, and bone-offset calibration used in prior work. We further augment training with physically grounded variations in watch placement and arm morphology to account for user-specific variability. ArmPoser also includes a wear-configuration module that infers anterior or posterior forearm placement and crown orientation. We evaluate pose estimation on public benchmarks and on a 10-participant, 30-activity study using watchOS and Android smartwatches, where ArmPoser matches or exceeds calibrated baselines without any user calibration. --- ### Evaluation Principles for MRI-MRA Registration in Trigeminal Neuralgia: An ROI-Centered Neurovascular Benchmark Authors: Xupeng Zhang, Xihang Wang, Michael Xie, Haoyuan Liang, Hau Ern Lien, Oishika Das, James Feghali, Risheng Xu, Peirong Liu Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08805v1 Preoperative evaluation of trigeminal neuralgia (TN) often requires joint interpretation of structural MRI, which depicts the trigeminal nerve and surrounding cisternal anatomy, and time-of-flight MRA, which highlights vascular structures. Although MRI-MRA fusion is clinically attractive for visualizing neurovascular compression, this task is poorly captured by conventional whole-brain registration evaluation because the clinically relevant target is a small trigeminal ROI, vessel annotations are partial and clinically focused, local TOF-MRA contrast is variable, and field-of-view mismatch can limit deformable alignment. We formulate TN MRI-MRA fusion as an ROI-centered neurovascular registration-evaluation problem and construct a benchmark from 149 patients with clinician-annotated bilateral trigeminal ROIs. Six representative registration pipelines were evaluated using local image-based metrics, segmentation-derived vessel-localization metrics, prediction-volume analysis, and contrast- and FOV-stratified comparisons. Conventional evaluation summaries were often misleading: local image similarity, vessel-background separability, and downstream vessel localization did not co-rank methods; one-sided vessel distances were strongly affected by predicted vessel extent under partial annotations; and local MRA contrast determined when vessel-separability metrics were informative. Deformable refinement provided only a small, FOV-dependent benefit over affine alignment, while reader review showed that locally favorable vessel distances could coexist with globally implausible registrations. These findings indicate that TN MRI-MRA registration should be evaluated as a local, vessel-aware, contrast-sensitive, and FOV-aware visualization task rather than as generic multimodal brain registration. Our code is publicly available at https://github.com/jhuldr/TN-Reg-Benchmark. --- ### Ostrich: Taking Large Strides Through Stiff Contact in Differentiable Dynamics Authors: Aleš Kučera, Karel Zimmermann Published: 2026-09-08 Categories: cs.RO, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2609.08800v1 Three properties determine whether a differentiable simulator can drive gradient-based optimization through contact: simulation accuracy, gradient reliability, and per-iteration cost. Tape-based engines such as MJX and Newton Semi-Implicit require timesteps small enough to keep contacts numerically tractable, and their backpropagation memory grows linearly with the number of timesteps T. Surrogate models bound memory by approximating contact away, but the resulting gradients lose the geometry the optimization depends on. We present Ostrich, a GPU-accelerated rigid-body simulator that resolves hard contacts and friction with non-smooth Newton iteration at large timesteps (h ~ 0.1 s), and differentiates the converged residual via the implicit function theorem, reusing the forward Schur complement to compute the adjoint at O(1) memory per timestep. On real-robot trajectories over a pallet obstacle, Ostrich holds MuJoCo's sim-to-real accuracy up to a 50x larger timestep. Its gradients converge from random initializations where MJX descends slowly and Newton Semi-Implicit stalls; a warm iteration runs 211x faster than MJX's and 4.7x faster than Semi-Implicit's. On the same scene Ostrich differentiates 8,192 parallel worlds on a single 24 GB GPU, sustaining 29x checkpointed MJX's optimization throughput; without checkpointing both baselines exhaust memory at far fewer worlds. We close with a gradient-based trajectory optimization demonstration over triangle-mesh terrain across a 10 s horizon, a setting where prior engines either restrict to primitive geometry or face the convergence and memory limits shown above. --- ### Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation Authors: Youngrok Park, Sangmin Bae, Hojung Jung, Jongwoo Ko, Yunseon Choi, Young Jin Kim, Pashmina Cameron, Aaron Courville, Se-Young Yun Published: 2026-09-08 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.08798v1 Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This question is particularly important for successive model generations and multi-domain consolidation, where repeating frontier-scale post-training from scratch can be prohibitively expensive. Yet conventional distillation treats the weak teacher as an optimization target, potentially imposing its capacity ceiling on the student. We introduce On-Policy Reverse Distillation (OPRD), which evaluates the teacher's policy shift relative to its reference policy on student rollouts and amplifies the component of the student's verifier-driven policy gradient along that direction. By rescaling only verifier-supported updates, OPRD preserves the stationary points of policy optimization while accelerating learning beyond the teacher. In both successive model transfer and multi-teacher distillation, OPRD achieves higher performance with fewer student updates than existing RL and distillation approaches. Response-style analysis shows that OPRD students remain closer to models trained with verifier-based RL alone than to their weak teachers, suggesting that teacher guidance accelerates rather than redirects the student's own optimization. Results in conventional strong-to-weak distillation further demonstrate that OPRD effectively combines verifier-driven policy optimization with teacher guidance regardless of capacity ordering. --- ### Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights Authors: Matthias von Davier Published: 2026-09-08 Categories: stat.AP, cs.CL arXiv: https://arxiv.org/abs/2609.08797v2 The Potts model extends the Ising model to multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pairs of ratings and category labels, with weights derived from LLM embeddings. The model does not presuppose ordered category thresholds or equidistant scoring; instead, it focuses on pairwise agreement among ratings and assigns category-specific positive weights, making it suited for multi-category scoring reliability. We evaluate the model on three constructed-response datasets spanning a corpus of K=14,466 short answers on a three-level rubric and two AERA essay prompts of roughly 1,200-1,400 responses on four-point rubrics. We compare three strategies for sharpening the similarity signal: top-K pruning, min-max normalization with a power transformation, and ColBERT late-interaction similarities. Top-K pruning, which replaces the dense similarity graph with a sparse local network of strongest semantic neighbors, consistently yields the highest accuracy and Cohen's kappa, and the selected neighborhoods are always a small fraction of the corpus. Power tuning consistently ranks second, while ColBERT is competitive on longer essay prompts and adds little on short answers. Across all settings, most misclassifications occur between adjacent score levels, confirming that the model preserves the ordinal structure of scoring rubrics without imposing rigid assumptions. These findings suggest that LLM-derived similarities, combined with a parsimonious Potts formulation and a sparse local graph, offer a robust and interpretable framework for reliability auditing in educational assessment. We discuss extensions to multiple raters and hierarchical rating designs. --- ### The Rater Ising-Potts Model with LLM-Derived Weights: An Application to Multi-Category Scoring Reliability Authors: Matthias von Davier Published: 2026-09-08 Categories: stat.AP, cs.CL arXiv: https://arxiv.org/abs/2609.08797v1 The Ising model is extended to the Potts model for multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pairs of raters and category labels, with weights derived from LLM embeddings. The model does not presuppose ordered category thresholds or equidistant scoring; instead, it focuses directly on pairwise agreement among raters and assigns category-specific positive weights, making it particularly suited for multi-category scoring reliability when raters evaluate responses using a scoring guide. We demonstrate the model's effectiveness on diverse constructed-response tasks, including balanced short-answer items and more challenging, imbalanced essay prompts from the AERA dataset. Across these settings, the model achieves strong agreement with human scores, with the vast majority of misclassifications occurring between adjacent score levels, confirming its ability to preserve the ordinal structure of scoring rubrics without imposing rigid assumptions. A practical similarity normalization and optional power transformation is introduced as a tunable preprocessing step that sharpens semantic distinctions and can be adapted to different datasets. These findings suggest that LLM-derived semantic similarities, combined with this parsimonious Potts-type formulation and flexible similarity scaling, offer a robust and interpretable framework for reliability auditing in educational assessment contexts. Extensions to multiple raters and hierarchical rating processes are discussed. --- ### Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling Authors: Rx Fan, Z Han Published: 2026-09-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.08796v2 Multi-agent traffic simulation seeks diverse, coordinated, and physically realistic futures from maps and observed history. Long-horizon closed-loop generation must reconcile multiple decision time scales while its context evolves with generated states. Existing methods often unfold long futures from an initial scene and resolve intent, interaction, and motion monolithically, weakening cross-scale consistency and adaptation. Multimodal rollout poses a further consistency problem: independently reselecting modes across agents or commits can stitch together incompatible futures instead of preserving a coherent joint branch. We present Hi-FLoop, a branch-consistent multi-timescale state-feedback framework. Eight scene-level Worlds represent joint hypotheses; all agents share one selected World identity throughout all 16 commits of an 8-second rollout, while Goal, Preview, and Control states adapt within that branch. An 8-second Goal anchors intent, a 2-second Preview coordinates interactions, and 1-second Control produces physical motion. Every 0.5-second commit feeds back only its executed prefix as new facts, while unexecuted hypotheses never enter factual memory. Joint Preview Interaction induces a sparse directed future graph and uses conflict probabilities and signed arrival-time differences to refine interaction-aware motion. For generated-state recovery, a prefix-frozen A-to-B cascade transfers typed physical state and the branch index--but no latent state--from a frozen prefix model to an independently parameterized recovery model. On the full H-D public-validation split of 955 scenarios, the S2.1 cascade obtains an 8-second scene-joint ADE-at-joint-minFDE@8/joint-minFDE@8 of 2.048/6.384 m when one World must explain all evaluated agents. Agent-centric oracle-minADE@8 is 0.526 m at 6 seconds and 0.875 m at 8 seconds. --- ### Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling Authors: Rx Fan, Zhan H Published: 2026-09-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.08796v1 Multi-agent traffic simulation seeks diverse, coordinated, and physically realistic futures from maps and observed history. Long-horizon closed-loop generation must reconcile multiple decision time scales while its context evolves with generated states. Existing methods often unfold long futures from the initial scene and resolve intent, interaction, and motion monolithically, weakening cross-scale consistency and adaptation. We present HI-FLOOP, a branch-consistent multi-timescale state-feedback framework. Eight scene-level Worlds represent joint hypotheses, and all agents share the selected World identity throughout an 8-second rollout. Within the branch, an 8-second Goal anchors intent, a 2-second Preview coordinates interactions, and 1-second Control produces physical motion. Every 0.5-second commit feeds back only its executed prefix as new facts, while unexecuted hypotheses never enter factual memory. Joint Preview Interaction (JPI) induces a sparse directed future graph from Preview and uses conflict probabilities and signed arrival-time differences to gate interaction refinement. For generated-state recovery, a prefix-frozen A-to-B cascade lets frozen Model A generate 0-1 seconds, then transfers typed physical state, admissible context, and the branch index, but no latent state, to an independent Model B for re-encoding and 1-2-second recovery. On the full H-D public-validation split of 955 scenarios, one complete S1 run yields an Overall score of 0.689987 with the official evaluator. Under agent-centric oracle evaluation, HI-FLOOP achieves oracle-minADE@8 of 1.196636 m over the 8-second horizon and 0.526 m over the 6-second horizon. --- ### Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports Authors: Akash Prakash, Boubakr Nour, Makan Pourzandi, Chadi Assi, Mourad Debbabi Published: 2026-09-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.08790v1 Threat hunting increasingly depends on converting unstructured knowledge (e.g., Cyber Threat Intelligence reports) into actionable hunt leads: concise, investigable hypotheses grounded in observable artifacts and adversary techniques. Producing such leads manually is a tedious and hard-to-scale task. Existing automated approaches stop at the entity layer, ignore the defender's operational environment, and analyze each report in isolation. To address these gaps, we introduce AHLERT, a system that automatically extracts relevant, environment-aware, and hunt leads from threat reports through (i) a hybrid retriever that combines dense vector search with multi-hop traversal over a knowledge graph seeded with MITRE ATT&CK; (ii) an ontology-grounding retrieval-augmented generation method that constrains each lead to the defender's own assets and controls; and (iii) an LLM-agnostic framework that emits structured, directly actionable leads rather than loose indicators of compromise. We evaluate AHLERT on public CTI reports for well-known APTs across multiple proprietary and open-weight models. Hybrid evidence retrieval with ontology grounding raises mean F1 by ~2x (0.44 to 0.85) over a single-route flat-RAG baseline, and AHLERT attains the highest effectiveness score (~86.95%) compared with off-the-shelf LLM models. --- ### Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers Authors: Louis Yiven Zhu Published: 2026-09-08 Categories: cs.CY, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.08789v1 Frontier AI developers publish safety frameworks that commit them to evidencing whether their models are dangerous. The European Union and California now treat these documents as instruments of accountability, and both already impose duties on their revision. Neither requires the revision to be legible, in the sense that a reader could learn from the developer's own account what changed. We introduce the silent revision rate, the share of material changes to a framework's commitments that the developer's published account does not identify, and we release the versioned, hash-pinned corpus needed to compute it. The corpus contains every public version of the safety frameworks of the twelve developers that have published one, together with each provider's changelog, redline or announcement. We trace 710 commitment instances across twelve consecutive version pairs, code them against a frozen codebook, and adjudicate 244 individually. Three findings follow. First, 67% of material changes (95% CI 62 to 72) are silent under a strict standard and 53% under a lenient one, falling to 49% at section granularity. Second, silence appears to track the form of the account, since narrative announcements run at 74% against 63% for itemised changelogs, whereas account length in words barely matters; on the test that respects nesting the difference is suggestive. Third, 77% of traced changes weaken or remove a commitment, and in seven of eight pairs weakenings are more often silent than strengthenings. The statutory remedy therefore exists and specifies the wrong artefact. A justification explains why a framework changed, an enumeration states what changed, and only the latter makes revision auditable. We argue that publication duties should carry an enumeration duty, which one provider already meets, voluntarily and incompletely. --- ### Adaptive Anisotropic Attention for Axis-Structured Signals Authors: Mahir Jain, Parshva Runwal, Aditya Ray Mishra, Arvasu Kulkarni, Jeet Bandhu Lahiri, Sandeep Singh, Siddharth Panwar Published: 2026-09-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.08788v3 Dense self-attention treats all token pairs as equally plausible before learning, an interaction-isotropic prior that can be mismatched to structured signals. For structured, low signal-to-noise ratio (SNR) signals such as EEG, dependencies are organized along the electrode and time axes, and this uniform prior exposes each token to many irrelevant interactions. We introduce Adaptive Anisotropic Attention (AAA), which splits attention into two paths: a temporal path, where each token attends to the tokens of its own electrode across time, and a spatial path, where it attends to the tokens of the other electrodes at the same time step. A small gate predicts, for every token, a convex combination of the two path outputs: two non-negative weights that sum to one. On six EEG downstream tasks, the resulting model, AXON (AXis-factorized Operator Network), improves mean balanced accuracy over a dense baseline under both linear probing and full fine-tuning. We show that both paths (temporal and spatial) are necessary and that the weighted sum beats a hard choice of one path; most of the benefit comes from the gate learning a different temporal/spatial balance at each layer of the network. Controlled audio spectrogram experiments show that axis factorization transfers beyond EEG. These results suggest that aligning attention with the natural axes of structured signals provides a useful inductive bias. --- ### Adaptive Anisotropic Attention for Axis-Structured Signals Authors: Mahir Jain, Parshva Runwal, Aditya Ray Mishra, Arvasu Kulkarni, Sandeep Singh, Siddharth Panwar Published: 2026-09-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.08788v1 Dense self-attention treats all token pairs as equally plausible before learning, an interaction-isotropic prior that can be mismatched to structured signals. For structured, low signal-to-noise ratio (SNR) signals such as EEG, dependencies are organized along the electrode and time axes, and this uniform prior exposes each token to many irrelevant interactions. We introduce Adaptive Anisotropic Attention (AAA), which splits attention into two paths: a temporal path, where each token attends to the tokens of its own electrode across time, and a spatial path, where it attends to the tokens of the other electrodes at the same time step. A small gate predicts, for every token, a convex combination of the two path outputs: two non-negative weights that sum to one. On six EEG downstream tasks, the resulting model, AXON (AXis-factorized Operator Network), improves mean balanced accuracy over a dense baseline under both linear probing and full fine-tuning. We show that both paths (temporal and spatial) are necessary and that the weighted sum beats a hard choice of one path; most of the benefit comes from the gate learning a different temporal/spatial balance at each layer of the network. Controlled audio spectrogram experiments show that axis factorization transfers beyond EEG. These results suggest that aligning attention with the natural axes of structured signals provides a useful inductive bias. --- ### Interpretable Hyperspectral Unmixing Framework with Fixed Endmember Prior and Structured Residual Refinement Authors: Ziyi Guan, Jianping Zhang, Qian Liu Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08786v1 Hyperspectral unmixing decomposes mixed pixels into material endmembers and their abundances from contiguous spectral observations. In modular sensing pipelines, endmembers are often first identified and then treated as fixed during abundance estimation. When this fixed endmember prior is inaccurate, spatially structured mismatch arising from illumination changes, sensor artifacts, or material boundaries may be incorrectly captured by the abundance variables, leading to unstable decompositions. This study presents an interpretable stage-wise hyperspectral unmixing framework (I-HyperSU) under fixed endmember priors, which is explicitly decomposed into a fixed endmember matrix $\mathbf{A}$, an abundance block $\mathbf{X}$, and a structural residual refinement block $\mathbf{S}$. The X-block estimates abundances using FISTA with nonnegativity and sparsity enhancement, and a soft penalty that approximately enforces sum-to-one constraints. The S-block jointly applies low-rank SVD structural regularization and a lightweight deep image prior (DIP) to refine structured residuals. This staged design makes the interaction between abundance and residual components transparent and interpretable. Experiments on Samson, Urban, and Jasper Ridge datasets demonstrate that, under fixed and imperfect endmember priors, soft abundance relaxation consistently outperforms hard simplex projection. Under the default N-FINDR endmember prior, the proposed framework reduces the joint reconstruction error by 61.7\%--69.5\% compared with a fixed-$\mathbf{A}$ UCLS baseline, while keeping the abundance RMSE nearly unchanged, indicating that the residual refinement branch accounts for structured model mismatch without degrading the abundance estimates. For example, on Urban, the reconstruction SAM decreases from $5.99^\circ$ for the X-only model to $1.92^\circ$ for the full model. --- ### Improving Term Evaluation in Machine Translation: Variation Matters Authors: Nicolas Dahan, Ziqian Peng, François Yvon, Rachel Bawden Published: 2026-09-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.08779v1 Terminology evaluation in machine translation (MT) usually assumes a single correct target form per source term. However, human translators routinely introduce variation that current metrics penalize as inconsistency. We examine how to account for this variation in document-level MT evaluation of English-French scientific translation, combining glossary-based accuracy, translation consistency, and a new cross-term variation (CTV) diagnostic measure that tests whether variation relationships are preserved across languages. Based on analyses of two parallel corpora, translated by four MT systems, we find that (1) MT systems generate less target-side variation than human translators; (2) transfer patterns strongly depend on the variation type; (3) consistency rankings vary with the choice of metric; and (4) constraining MT with a glossary improves accuracy and consistency but degrades CTV by suppressing valid variation. We argue for variation-aware evaluation that conditions consistency penalties on whether target-side variation mirrors source-side variation. --- ### AXS-Net: Interpretable Deep Unfolding for Hyperspectral Image Denoising via Spectral Basis Unmixing and Structured Noise Refinement Authors: Ziyi Guan, Jianping Zhang, Zheng Yang Published: 2026-09-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.08777v1 Hyperspectral images (HSIs) are often degraded by mixed noise, including band-dependent Gaussian perturbations and structured artifacts such as stripes, dead-lines, and impulse noise. Most deep denoisers regress the clean image directly, entangling signal and structured noise. We instead model HSI denoising as $\Y=\A\X+\Snoise+\Nnoise$, where $\A\X$ is a low-rank spectral-subspace (unmixing) reconstruction, $\Snoise$ is structured sparse noise and $\Nnoise$ is residual Gaussian noise. The resulting regularized optimization problem is unrolled into AXS-Net, a $K$-stage alternating proximal-point framework. Each stage combines an analytic spectral-basis gradient step, an SSX-Block proximal operator for abundance coefficients, and an SBlock proximal operator for the structured residual with column-consistent and sparse priors. This optimization correspondence exposes interpretable endmembers, abundance maps, and structured-noise estimates. Across ICVL, CAVE, and Harvard datasets and five noise configurations, the proposed AXS-Net achieves strong in-domain accuracy and competitive zero-shot transfer, with consistent gains across all five noise regimes on ICVL and Harvard. The recovered structured-noise closely follows the synthetic reference, and the recovered spectral basis is smooth and band-ordered rather than an arbitrary set of latent channels. --- ### It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction Authors: Andrea Apicella, Pasquale Arpaia, Matteo Orefice, Andrea Pollastro, Roberto Prevete Published: 2026-09-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.08772v1 Large Language Models (LLMs) are increasingly being investigated for physiological time-series prediction, yet their effectiveness may depend not only on the model itself, but also on how physiological information is represented and presented at inference time. This study investigates prompt-based general-purpose LLMs for postprandial hyperglycemia and hypoglycemia prediction in individuals with type 1 diabetes. Using the OhioT1DM dataset, we evaluate multiple open-weight LLMs under zero-shot and few-shot inference across prediction horizons of 30, 60, and 90 minutes. The analysis varies both the textual representation of the available physiological information and the amount of information exposed to the model, ranging from glucose observations alone to derived descriptors and additional contextual variables related to insulin, meals, carbohydrates, and physical activity. Performance is compared with conventional patient-specific supervised models and with Gluco-LLM, a language-model-based architecture explicitly adapted to glucose time-series forecasting. Results show a marked task-dependent behavior. Conventional supervised models achieve the strongest performance for hyperglycemia prediction, whereas the best observed prompt-based LLM configurations improve performance for hypoglycemia across all investigated horizons. The effectiveness of prompt-based inference is also strongly influenced by how physiological information is represented, while providing additional contextual information does not lead to a systematic improvement. Overall, these findings highlight physiological information representation as a central design factor in prompt-based LLM approaches to glycemic-event prediction. ---