# Research Papers — 2026-09 · bundle page 111 of 266 > Full-text markdown of papers #5501–5550 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/111 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/110.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/112.md) ### Can We Still Trust Disaster Social Sensing? Empirical Evidence on Detecting AI-Generated Social Media Posts Authors: Xiaoshan Zhou, Zaifu Zhan Published: 2026-09-21 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.35821v1 Disaster social sensing converts public social-media posts into evidence for situational awareness and humanitarian needs, but generative artificial intelligence (AI) can produce plausible messages that resemble eyewitness reports. This study investigates whether text-based AI detectors can reliably distinguish human-authored from AI-generated disaster posts. We construct a dataset of 12,000 texts organised into 3,000 matched semantic units from nine disasters: original human posts (H0), minimally LLM-proofread human posts (H1), factual AI-generated posts based on the same verified facts (A0), and affectively framed versions of those AI posts (A1). A separate 6,000-text corpus from 42 events supports model selection and threshold calibration. We evaluate OSM-Det, Fast-DetectGPT, Binoculars, and direct large language model (LLM) judges across five model families, then test disaster-domain calibration, a frozen-encoder linear readout, paired transformation sensitivity, and dataset artifact controls. Across fourteen frozen cross-family configurations, AUROC is 0.402-0.517 and the best prospective recall at a calibration-derived low-false-positive operating point is 3.6%; OSM-Det reaches AUROC 0.521 and 10.4% recall at a realised 6.7% false-positive rate. A disaster-trained linear head reaches AUROC 0.817, but a seven-feature surface classifier reaches 0.784 on the H0-versus-A0 contrast, and neutralising identified surface asymmetries reduces the head from 0.733 to 0.594. The head also separates A0 from A1 even though provenance is unchanged. The results show that text-based detection is not reliable enough to serve as an operational trust gate; multimodal claims, accountable sources, and other contextual evidence should be rested on to safeguard trust in disaster social sensing. --- ### $τ$-Multilingual: Benchmarking Voice Agents Across Languages Authors: Soham Ray, Edgard dos Santos Paiva, Ruben Valenzuela, Karthik Narasimhan, Keshav Dhandhania, Victor Barres Published: 2026-09-21 Categories: cs.CL, cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2609.35820v1 English-only benchmarks expose only a narrow slice of voice-agent behavior. We introduce $τ$-Multilingual, extending $τ$-Voice to Spanish, Brazilian Portuguese, Hindi, Korean, and Mandarin with native-speaker review and evaluation of generated language and spoken output. Across 4,500 full-duplex calls and five voice configurations, Spanish, Portuguese, and Hindi remain within 3.2 task-completion points of English, but Korean and Mandarin fall by 14.7 and 8.4 points. The failure modes also vary: Korean systems miss more responses, Mandarin systems interrupt more often, and both struggle with tools and entities. Grok leads task completion but scores lowest on generation quality, motivating separate task, interaction, and generation reporting. We release language packs, validated judges, and tools for community-built multilingual voice-agent evaluation. --- ### Less Uniform Discrete Diffusion is More Powerful and Scalable Authors: Kaibo Wang, Ding Ding, Fangyu Ding, Zijin Feng, Han Shi, Haili Bai, Jiacheng Sun, Yang Xiang Published: 2026-09-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.35817v1 Although uniform diffusion language models (UDLMs) represent a promising diffusion paradigm, scaling them remains challenging. We identify the core obstacle as an over-uniform training objective and condition-target confusion during sampling. To address these, we propose Less Uniform Diffusion (LUDI), a novel UDLM framework. Specifically, we (i) introduce a less uniform loss that directs each reverse transition toward the clean token, and (ii) equip the model with per-token time embeddings that supply token-level corruption hints, enabling confidence-based few-step sampling. Experiments across scales show that LUDI yields cleaner supervision and improves few-step generation. We further continue-train a 7B autoregressive model into LUDI-7B, resulting in a UDLM capable of complex reasoning. It achieves a 3-token-per-step speedup over AR decoding and competitive performance compared with masked diffusion baselines, revealing that the full potential of UDLMs for complex generation remains to be unlocked. --- ### LatentReRig: An SDF-Based VAE with Dual Decoders for Latent-Space Deformation Conditioning Authors: Daniele Dolci, Fabrizio Poggioni, Carlo Melchiorri Published: 2026-09-21 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.31720v1 Transferring deformation between characters with different geometry and topology is challenging because conventional rigs encode behaviour through character-specific structures and correspondences. We present LatentReRig, an experimental framework that investigates whether pose-associated changes can instead be represented as reusable directions in a learned geometric latent space. An SDF-based variational autoencoder is coupled with two decoders: one reconstructs the implicit field, while the other predicts target vertex positions from source geometry and latent deformation conditioning. The source geometry may be neutral or already deformed. Experiments on a controlled humanoid dataset show that several poses induce coherent latent directions across identities, particularly for broad articulated motions. These signals can guide deformation of unseen characters, but explicit predictions remain less accurate for localized changes and corrective contributions. Diagnostic comparisons with repeated SDF sampling show that inter-identity distances exceed same-geometry resampling variability on average, while pose signals exhibit different margins above this baseline. The results support the presence of reusable pose-related structure and identify stable local conditioning and accurate mesh decoding as complementary requirements for improving transfer. --- ### Distributional Metrics for Evaluating Spoken Conversational Systems Authors: Shree Harsha Bokkahalli Satish, Erica Cooper, Patrícia Schmidtová, Maike Züfle, Éva Székely, Nicholas Sanders, Ondřej Klejch Published: 2026-09-21 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.31719v1 Evaluating conversational systems is a difficult and unresolved problem. We introduce the Conversational Distribution Score (CDS), which compares distributions of conversational behaviour using human conversations as a reference. CDS describes speech rate, syllabic rhythm, and turn interaction through eight interpretable features plus a separate two-feature semantic baseline. We compare conversations with two reference scales: one based on conversational success within human dialogue and another contrasting human and synthetic dialogue. Using listener judgments from out-of-domain goal--oriented dialogues, we examine system ranking, preferences between conversations, and ranking stability. Composite CDS recovers five of six listener system comparisons while individual features show strong correlation with listener preferences between conversations. We examine how many minutes and conversations are required before rankings stabilize. These findings support distributional comparisons as a complement to specific interactional metrics to evaluate conversations and conversational models while showing their interpretable value. --- ### MM-VeriRec: Failure-Guided Fusion for Verifiable Agentic Multimodal Recommendation Authors: Yufeng Wang Published: 2026-09-21 Categories: cs.IR, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.31718v1 Images often carry recommendation constraints that text metadata only hints at. A movie may need to look dark, a product may need a minimal style, and a visually impossible request should be rejected. Agentic multimodal recommenders must reason over text-image evidence, decide when visual evidence is decisive, and abstain when no valid action exists. We introduce MM-VeriRec, a verifiable multimodal recommendation protocol and failure-guided fusion method for hidden visual constraints, image-text mismatch, and impossible-task abstention. MM-VeriRec builds tasks from real movie-poster and product-image datasets, verifies each recommendation with deterministic visual attributes, and converts failures into actionable labels: text-trap following, visual ignorance, and false acceptance. Fusion should not merely concatenate modalities, but should diagnose which modality failed and route to the appropriate repair. Across MM-ML 1M and Amazon Reviews datasets, stronger text and vision embeddings improve retrieval but do not remove these failure modes, whereas failure-guided fusion does. The adaptive attribute gate reads the same tags the verifier checks and its scores are verifier-aligned upper bounds testing whether the taxonomy routes to the correct repair. More informative is transfer under a non-aligned gate: an independently derived leave-one-out CLIP detector still reaches 0.7028 and 0.6111 visual-grounded success, above both a VBPR baseline and plain fusion. The text-versus-visual gap reproduces across two LLM families, and the repair that helps differs by domain. MM-VeriRec is both a benchmark and a practical diagnostic loop for trustworthy agentic multimodal recommendation. --- ### PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routing Authors: Peng Xu, Haoran Lin, Wanjun Jia, Kai Luo, Wenrui Chen, Zhiyong Li, Kailun Yang Published: 2026-09-21 Categories: cs.CV, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2609.31717v1 Vision-Language-Action (VLA) policies have shown promising performance in language-conditioned robotic manipulation. However, most existing VLA systems rely on conventional perspective cameras with limited fields of view, often missing global scene context and leading to unreliable manipulation under visual occlusions, distractors, and unseen environments. In this work, we propose PanoFuse, a panorama-enhanced VLA framework that complements local manipulation observations with global panoramic perception. PanoFuse introduces a dedicated panoramic branch that leverages a pretrained panoramic foundation model to extract complementary semantic and geometric representations from omnidirectional observations. Rather than directly mixing these heterogeneous features, we introduce Decoupled Semantic-Geometric Routing (DSGR), which maintains semantic and geometric representations as separate context streams and selectively routes both to downstream state and action representations through structured block-wise attention. This design provides the action expert with global spatial context while preserving task-relevant semantic information from the pretrained VLA backbone. We further develop a synchronized data collection pipeline and construct a new real-world manipulation dataset containing panoramic RGB observations, wrist-view images, language instructions, robot states, and actions. Across seven evaluation settings, PanoFuse achieves an average success rate of 52.9%, outperforming the evaluated baselines and achieving consistent gains under novel-object, unseen-background, and distractor-rich settings. Code and data will be released publicly at https://xux-hnu.github.io/PanoFuse. --- ### PanOVOcc: Panoramic Embodied Open-Vocabulary Occupancy Mapping with Long-term Spatial Voxel Memory Authors: Di Kuang, Mengfei Duan, Yuhang Wang, Weixing Peng, Kailun Yang Published: 2026-09-21 Categories: cs.CV, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2609.31716v1 Persistent semantic occupancy mapping is essential for embodied scene understanding. However, perspective-based systems provide limited spatial coverage, while existing panoramic methods primarily predict local volumes from single observations. We introduce PanOVOcc, a training-free framework for persistent open-vocabulary semantic occupancy mapping from panoramic sequences. PanOVOcc unifies panoramic SLAM, open-vocabulary perception, and long-term spatial voxel memory within an online architecture, continuously integrating geometric and semantic evidence into a global, language-queryable map. To facilitate systematic evaluation of this setting, we establish Pan-Replica and Pan-Holo360D, two benchmarks pairing continuous panoramic RGB-D sequences with scene-level semantic occupancy ground truth across synthetic and real-world scenes. Compared with the strongest evaluated baseline for each metric, PanOVOcc improves occupancy IoU and semantic mIoU by absolute +20.03 and +7.06 on Pan-Replica, and by +43.26 and +20.16 on Pan-Holo360D, respectively. The source code and the established benchmarks will be available at https://github.com/bakereet/PanOVOcc. --- ### Fysiverse-3D-SimReady Technical Report: Agentic Physical Simulation for Pragmatic 3D World Reconstruction Authors: Lintao Wang, Mingyang Sun, Yang Liu, Dingkang Yang, Lihua Zhang Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31715v1 Agentic recognition requires visual perception to move beyond static scene understanding and produce structured scene representations that support the perception--reasoning--action loop. Existing single-image 3D generation methods, however, mainly produce visually plausible object assets rather than simulation-ready scene states. When independently generated meshes are composed in a shared space, they may fail to align with the input camera, violate gravity, interpenetrate nearby objects, or become unstable under physics simulation. We present Fysiverse-3D-SimReady, a grounded refinement framework for reconstructing simulation-ready multi-object scenes from a single RGB image with instance and ground prompts. The method places generated object meshes into a shared gravity-aligned scene, refines their camera-space poses through differentiable rendering, and corrects scene-level supports and contacts for stable physical execution. The scene is then used by an agentic simulation workflow, which converts a scene-specific task goal into an executable physics rollout rendered from the original camera view. Experiments show that Fysiverse-3D-SimReady improves input-view alignment, contact plausibility, and physical stability over existing single-image reconstruction and scene generation baselines, while enabling goal-conditioned physical interactions from a single image. --- ### OmniFysics-Captioner Technical Report: Grounding Omni-Modal Understanding in the Physical World for Better Captioning Authors: Kaixiang Qiu, Minghao Han, Keliang Liu, Yizhou Liu, Jinghan Han, Yue Jiang, Xuecheng Wu, Shunli Wang, Lihua Zhang, Dingkang Yang Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31714v1 Building omni-modal models with physical intelligence requires fine-grained supervision that captures physical evidence such as contact, support, deformation, and state transitions. However, existing omni-modal captioners primarily model general audiovisual semantics and often overlook transient or spatially localized physical evidence. We present a unified framework for physics-aware audiovisual captioning spanning data construction, training, and evaluation. Firstly, we build a data construction pipeline that identifies physics-rich clips and leverages OmniFysics-Agent to coordinate audio, visual, and physical-perception tools for collecting spatiotemporally aligned and traceable cross-modal evidence; within the Agent, a physical perception model (PPM) fine-tuned on approximately 2M image-level samples serves as a dedicated tool for extracting object-interaction and state-change cues. Secondly, we build the Daily-Physics 50K dataset and introduce the evidence-driven OmniPhysCap (OPC) benchmark to evaluate the recovery of physical and cross-modal evidence from generated captions. Finally, we train OmniFysics-Captioner from the resulting data. Our Captioner matches Gemini 3.1 Pro on audiovisual captioning, achieves state-of-the-art results on multiple video-captioning benchmarks, and substantially outperforms other open-source models. Ablations show that PPM evidence improves physical coverage and produces finer-grained, more reliable cross-modal descriptions. --- ### Agentic Video Understanding: A Survey Authors: Xinyu Deng, Siwen Luo, Daochang Liu Published: 2026-09-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31713v1 As large language models (LLMs) become capable of processing increasingly diverse modalities and longer temporal contexts, an emerging line of work is moving beyond fixed video-language inference toward agentic systems that actively decide what information to inspect, retain, verify, and act upon. This survey reviews video understanding agents: systems that use video as the primary information source and solve understanding tasks through adaptive state construction and action selection. We first formalize an agent loop for video understanding, then address a central question: why do agents matter for video understanding? To answer this, we organize the literature through a challenge-to-design taxonomy, linking context bottlenecks to hierarchical evidence memory, evidence sparsity to active evidence acquisition, temporal causality to state and process tracking, and multimodal ambiguity to role-specialized coordination. We further review state space paradigms, learning paradigms, supervision signals, benchmarks, and evaluation protocols. Finally, we identify open directions toward agentic-native temporal modeling and video-native agents. Project page: https://github.com/DXY0711/Awesome-Agentic-Video-Understanding --- ### Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology Authors: Noriaki Hashimoto, Shuichi Nishino, Teruyuki Katsuoka, Tomohiro Shiraishi, Daiki Miwa, Hiroyuki Hanada, Jun Sakuma, Hidekata Hontani, Hiroaki Miyoshi, Ichiro Takeuchi Published: 2026-09-21 Categories: cs.CV, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.31712v1 Multiple instance learning (MIL) is widely used in computational pathology because it enables weakly supervised analysis of whole-slide images (WSIs) without requiring patch-level annotations. In attention-based MIL, instances with high attention scores are often interpreted as diagnostically important regions and used as visual explanations. However, attention scores alone cannot determine whether selected high-attention instances are significantly different from normal instances, limiting the reliability of attention-based explanations. In this paper, we formulate the evaluation of high-attention instances as a statistical hypothesis testing problem. Specifically, we assess whether a selected high-attention instance significantly deviates from a representative normal reference instance selected based on feature similarity. A major challenge is that both the target instance and the reference instance are selected through data-dependent procedures, rendering standard hypothesis testing invalid. To address this issue, we introduce a selective inference (SI) framework that explicitly accounts for the selection events induced by attention-based instance selection and adaptive reference selection, thereby enabling the computation of valid selective $p$-values conditional on these events. Experiments demonstrate Type-I error control on synthetic and MNIST-based data and practical applicability to pathological WSIs, with higher statistical power than the conventional over-conditioning approach. --- ### Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse Authors: Shreya Gopalan, Devansh Singh, Sundaraparipurnan Narayanan Published: 2026-09-21 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.26836v1 Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools. While prior research and benchmarks have studied about task success and task completion of these agentic systems, the research about agent to tool interaction, specifically in biology agentic workflow is limited. This study investigates specific failures in agent to tool interaction where a tool invocation appears successful, some or all of the information or functionality from the tool via API/ wrapper is incomplete or missing and there are no communications / notifications to the user or the agent about such missing information. We call this a silent failures as the user or the agents are not aware that such failure has occurred. For the purposes of this study we developed an audit mechanism to identify such silent failures in Agent to tool interaction, by examining 15 scientific tools (and their associated API documentation and tool documentations) integrated within ToolUniverse environment (ToolUniverse serves as our experimental environment rather than the object of the study itself). We structure our study around 7 failure locus characterising where the failure occurs in the chain. We observed 91 failures (manually validated post LLM based candidate discovery and automated testing), most frequent of them being missing data or fields and inconsistencies in search, filtering or ranking criteria. Most of the 91 failures occurred in API layer (51) or wrapper layer (25), with a potential of silent failure amplification downstream. The results show that silent failures originate upstream of the event and propagate downstream into apparently valid scientific outputs. We propose a concept of contextual reliability to handle such failures and suggest mechanisms for testing, disclosing, monitoring, and measuring such failures across the agent-tool interaction pipeline. --- ### Spec2COBOLRot: An Agentic-AI Degradation Loop for Realistic COBOL Corpus Generation Authors: Jean-Baptiste Espinasse, Djamel Eddine Khelladi, Mathieu Acher Published: 2026-09-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.26835v1 COBOL remains widely deployed, yet representative corpora reflecting real production code are rarely available, limiting rigorous benchmarking of modernization approaches. We propose a systematic agentic AI pipeline for generating realistic COBOL programs, combining specification-driven generation with iterative degradation guided by patterns and complexity targets extracted from real production code. Here, realism is understood as structural fidelity to production code as captured by our metrics. We evaluate whether degradation reaches target complexity levels while preserving business behavior, and examine the limits of the approach, across three programs from distinct business domains. Results show the pipeline reliably produces syntactically valid programs and moves them toward realistic structural complexity. However, preserving business behavior is not always achieved by construction, and targeting structural metrics independently of business logic risks producing programs whose complexity does not reflect a plausible maintenance history. We discuss these limitations and outline a more realistic alternative as a direction for future work, generating legacy programs from scratch along a simulated development history. --- ### Validation and Simulation Catch Different Errors: Four Levels of Evaluation for LLM-Generated Circuits Authors: Ali Hedayati Pirouzan Published: 2026-09-21 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2609.26830v1 Simulation success is not equivalent to structural correctness for LLM-generated circuits. We define and measure four evaluation levels -- schema validity, topological validity, backend executability, and component-set agreement -- on a 150-circuit trilingual benchmark, through a deployed pipeline built on a typed circuit interchange representation. The levels are not nested. On gpt-4o-mini, 16 of 150 circuits (10.7%, 95% CI 6.7-16.6) were rejected by the topological validator but executed in ngspice with no error or warning; 12 of these contained exactly the requested components, with one terminal disconnected. Conversely, 7 circuits (4.7%) passed the validator and ngspice refused them. Ten failed both checks and 117 passed both, so each check detects a class the other misses. A minimal three-component divider shows the cost: a dangling resistor reports 5.00 V instead of 2.50 V while ngspice stays silent. A paired ablation, in which every arm is evaluated from the same model sample rather than a fresh one, separates each repair stage from sampling noise. On a stratified 45-circuit subsample, model repair raised topological validity from 40.0% to 84.4% (+20 circuits, no regressions) while moving executability by a net 6 (+7, -1), an effect this sample size does not resolve, and component agreement by 2. One circuit moved in opposite directions at two levels in a single repair step. Against a direct-netlist baseline the pipeline executed 88.7% against 47.3%, or 62.7% under an accounting that credits the baseline with every failure we cannot confidently attribute to the netlist. These results support a narrow methodological conclusion: structural validation and simulation should be reported as distinct evaluation stages for LLM-generated circuits. A circuit that runs is not necessarily structurally valid, and a structurally valid circuit is not necessarily executable. --- ### SBMVTrack: Spike-Budgeted Multi-View Learning for Power-Efficient UAV Tracking Authors: Pengzhi Zhong, Jiwei Mo, Haolun Li, Ge Zheng, Jingqi Wang, Xinyi Bo, Shuiwang Li Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.25503v2 With sparse and event-driven computation, spiking neural networks show great potential for achieving accurate and power-efficient UAV visual tracking. However, existing SNN-based trackers typically use spike firing rates only for power consumption and lack explicit optimization of actual spike activity. Moreover, regulating spike activity alone does not explicitly encourage stable target representations under partial observations and temporal appearance changes. We propose SBMVTrack, a fully spiking tracking framework that combines spike activity regulation with complementary multi-view representation learning. Specifically, SBMVTrack introduces Energy-Weighted Spike Budgeting (EWSB), which incorporates layer-wise computational costs when regulating spike firing rates and penalizing saturated activations, thereby reducing redundant spike computation. To further improve target representations under the spike budget constraint, we introduce Masked Multi-View Target Modeling (MVTM), which treats the initial template, online template, and search region as temporal views of the same target. By aligning target embeddings between masked and corresponding unmasked views and enforcing cross-view identity consistency, MVTM encourages robustness to missing local cues and temporal appearance changes. Experiments on four UAV benchmarks demonstrate competitive tracking performance with a 24.1% reduction in estimated power consumption relative to the baseline. On VisDrone2018, SBMVTrack achieves a success rate of 70.0%, exceeding SpikeTrack by 9.7 percentage points while reducing estimated power consumption by 45.7%. The source code will be released upon acceptance. --- ### Continuous Optimization for p-adic Models Authors: Julian Salazar, Dimitri Kanevsky, Matt Harvey, Pascal Getreuer, Lucas Dixon Published: 2026-09-21 Categories: cs.LG, math.MG, math.NT, math.OC, stat.ML arXiv: https://arxiv.org/abs/2609.25501v1 We present the first method for native, continuous gradient descent for machine learning models with $p$-adic parameters. Existing native optimizers are discrete, mostly combinatorial searches, as the $p$-adic numbers $\mathbb{Q}_p$ are totally disconnected, with standard losses that are flat away from their minima. To enable continuous optimization, we propose working with $\mathbb{Q}_p$ via its Berkovich affine line: a canonical, path-connected expansion of $\mathbb{Q}_p$ that preserves its isometries and uniquely extends its analytic maps. This hull is a metric tree with interpretable points and local derivatives, which we show enables effective optimizers and backpropagation. We formulate gradient descent and show that its approximations efficiently learn linear models with coefficients in $\mathbb{Q}_p$ to do modular arithmetic, an XOR-like task not expressible by linear models in $\mathbb{R}$. We also demonstrate momentum and Adam variants, linear regression, and classification on binary-encoded hierarchies (Quillian semantic networks), addressing open problems posed by Martins (2025). Library at https://github.com/google-deepmind/padic-ml --- ### mbariml: a curation pipeline for turning deep-sea imagery and video into object-detection training data Authors: Lonny Lundsten, Kevin Barnard, Dave Caress Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.25500v1 Training data quantity and quality greatly affect object detection model performance, regardless of model architecture. When using object detection models on video and images from the deep sea, in which the objects of interest, primarily organisms, are sparse, faint, and hard to identify, incremental improvements to object detector performance may require an iterative approach to data labeling and management. This paper presents mbariml, a python-based video and image analysis pipeline built around the data labeling management process. mbariml uses an Ultralytics YOLO detection model, runs it over still images or video, stores every detection as a reviewable region of interest, groups those regions by visual similarity so that a human can accept or reject them in bulk, and exports the result as training data, statistics, image sidecars, and additional metadata. The human review stage is the centre of the design: an annotator can validate, relabel, resize, delete, and draw entirely new localizations, and every one of those edits is written back to the same database the detector wrote to. Video receives particular attention: the software treats each tracker-produced track as a provisional observation and selects one representative frame instead of retaining every detection in the track. We describe the pipeline stage by stage, including the operational middle-third heuristic used for track observation selection. --- ### Universal Fractal Natural Language Decision Map: Real-Time Edge Triage Across Heterogeneous Domains Authors: Volkan Dağlı, Zerrin Dağlı, Dağhan Dağlı Published: 2026-09-21 Categories: cs.NE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.25498v2 Deploying Large Language Models for runtime operational triage incurs prohibitive latency (>100-500 ms), high VRAM requirements (>4-8 GB), and excessive energy dissipation. Extending Mandelbrot Fractal Neural Synthesis (Dagli et al., 2026), this paper presents the Universal Fractal Natural Language Decision Map, realized via the werr machine-native edge reflex runtime and the production answerr platform (https://answerr.me). Operating entirely without stored weight tensors (0 Bytes VRAM), the engine synthesizes deterministic decisions---noul (Boolean), choice (categorical), and score (ordinal)---by dynamically modulating 24-byte coordinate seeds along the chaotic boundary of the Mandelbrot set and evaluating multi-scale escape dynamics. Drawing inspiration from biological System-One reflex arcs, the engine introduces: (i) an Auto-Seed Router with domain projector Phi_D yielding a +28.8% accuracy gain over linear baselines; (ii) an Information-Theoretic Semantic Token Damping Filter (T_desc = 0.045) insulating against prompt injections (0.0% empirical bypass; 95% Wilson CI: (0.0%, 27.8%)) while pruning iterations by 45.8% (accelerating throughput 2.5x to 3.31 ms latency); (iii) a Multi-Scale Harmonic Tripod Fusion; (iv) a Coupled Margin Expansion Operator (Pitchfork Bifurcation Offset); and (v) a Cyclic Z/9Z Modular Resonant Grid Discretization based on the closed sub-ideal {0,3,6} (Lean 4 Mathlib ZMod 9), reducing FLOPs by 68.4%. Evaluated on JevBench (N=231), werr achieves 100.00% TypeSafe compliance and 81.65% calibrated accuracy with 7.08 ms median latency. We provide an OpenAI-compatible API and demonstrate deployment on 32-byte EVM smart contracts via the open-source werracle on-chain oracle (21,438 gas). --- ### Towards participatory speech dataset curation: A queer case study and conceptual framework Authors: Brooklyn Sheppard, Anaelia Ovalle, Adina Williams, Levent Sagun Published: 2026-09-21 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.25496v1 In this paper, we motivate the need for a participatory speech dataset creation framework through a case study of the LGBTQIA+, or queer, community - a community with documented concerns about AI and reported harms, including attempts to develop 'gaydar' technologies that purportedly identify individuals as queer. We review common speech data collection practices, why these methods may be unsuitable for engaging with queer speakers, and discuss previous efforts in participatory AI with queer community engagement, as well as participatory endeavours specific to speech data collection for other marginalized communities. From this review, we develop a conceptual framework for participatory speech data curation by, for, and with marginalized communities drawing on insights from co-design and knowledge sharing. We propose a framework comprising overlapping and two-way processes of defining a community, project formulation, modes of participation, and personal autonomy. --- ### RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models Authors: Zhiping Wu, Dongdong Ren, Yangchengyu Zhou, Zhengjie Zhang, Wenbin Li, Hongbing Pan, Yang Gao Published: 2026-09-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.25492v1 Large vision-language models (VLMs) can be efficiently deployed under stringent memory and latency constraints through post training quantization (PTQ). However, most PTQ methods are designed for unimodal large language models (LLMs). These methods treat quantization errors as isotropic perturbations under the Euclidean assumption, which provides weak guidance on directions most sensitive to quantization in VLMs. Consequently, directly adapting unimodal PTQ approaches or solely employing modality-specific scaling often leads to uneven bit-width distribution and inconsistent performance in low-bit settings. To address these challenges, we propose Riemannian Geometry-Sensitive Quantization (RGSQ), which formulates quantization as a reconstruction problem under a unified Fisher-Riemannian metric. RGSQ identifies modality-specific sensitive directions via Riemannian manifold mappings built from modality-partitioned empirical Fisher factors and fused into a modality-aware Kronecker-structured metric. We then apply geometry-aligned rotations to reorient the local tangent frame, steering low-bit perturbations toward loss-insensitive axes. Finally, we apply a whitening transformation that maps the Riemannian objective to an equivalent Euclidean form, enabling standard unimodal PTQ methods to evaluate multimodal quantization error under their original assumptions. Across an extensive and diverse set of mainstream VLM benchmarks, RGSQ achieves the highest accuracy and stability under extremely low-bit settings (W2A8 and W3A8). It outperforms VLM-aware baselines, such as MBQ and MQuant, by up to 5.9% and surpasses single-modality improvements by up to 8.6%. --- ### Queer inclusion in speech datasets: An audit and taxonomy of practical tensions Authors: Brooklyn Sheppard, Anaelia Ovalle, Adina Williams, Levent Sagun Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25491v1 In this paper, we examine speech datasets for their inclusion of LGBTQIA+, or queer, voices and provide a taxonomy of tensions to better understand why there is a lack of such voices in current speech technology datasets. Through an audit of six diverse speech datasets, we find that measurable queer representation is low (0-1.4% of speakers) - insufficient for robust disparity measurement. We take this community as a case study to consider what challenges and tensions are associated with collecting speech data from marginalized communities. For comparison, we audit an additional two datasets from the speech sciences that were created by, for, and with the queer community. We note that many customs in speech dataset collection efforts in AI and speech technology research may conflict with values emphasized in participatory approaches with marginalized communities, and provide a taxonomy describing these tensions. --- ### SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation Authors: Jiangshan Gong, Yuqun Wu, Qiqian Fu, Yao Xiao, Chuhang Zou, Shenlong Wang, Derek Hoiem Published: 2026-09-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.25490v1 Consistent multi-view object segmentation is critical for 3D perception and robotics, yet remains challenging under severe viewpoint and occlusion changes. Existing methods typically perform 3D instance segmentation on point clouds or rely on offline 2D mask-matching pipelines. However, 3D instance segmentation is limited by scarce 3D annotations, while offline 2D matching suffers from object identity ambiguity across frames. To leverage strong 2D and 3D priors jointly, we propose SAM-V (Geometry-Aware Segment Anything for Multi-View Instance Segmentation). Instead of combining the two priors through post-hoc matching, SAM-V directly integrates features from a feed-forward geometry model (VGGT) into a 2D segmentation foundation model (SAM), trained end-to-end for cross-view instance prediction. SAM-V introduces a prompt-fusion mechanism that enriches sparse SAM prompt tokens with view-specific camera tokens and local VGGT features, making the prompt representation both view-aware and spatially grounded, together with a mask decoder that attends to dense 2D and 3D features. By conditioning the mask decoding directly on multi-view geometry, SAM-V produces consistent multi-view segmentation of a prompted object in a single forward pass without offline mask matching or explicit 3D reconstruction. On the IGGT 3D tracking benchmark, where consistent instance identity across frames directly determines performance, SAM-V improves overall IoU by 5 points and frame-level recall by 12 points on the ScanNet++ split over the state-of-the-art multi-view instance segmentation baseline and leads on all metrics in the zero-shot ScanNet split. Our code and pretrained models are available at https://github.com/gong208/SAM-V.git. --- ### Learning Defensive Policies against Diverse Inference Attacks for Smart Meter Privacy Authors: Ruichang Zhang, Mustafa A. Mustafa Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.25484v1 Smart meter (SM) data provides fine-grained visibility into household energy consumption, but also exposes users to privacy risks. Inference attacks, known as non-intrusive load monitoring (NILM), can perform appliance-level inference from aggregate signals and recover sensitive behavioral patterns. In practice, attacker models are unknown and heterogeneous, making robust defense challenging. We formulate SM privacy protection as a black-box inference defense problem, aiming to reduce the recoverability of appliance-level information while generalizing across diverse and unseen attackers. We propose a proxy-guided hierarchical reinforcement learning framework that learns battery-based load-shaping policies to inject realistic but misleading appliance-level signatures into the aggregate signal, thereby disrupting the structured patterns exploited by NILM. A self-supervised aggregate-structure privacy probe provides a reconstruction-error-based surrogate reward for disrupting recoverable load structure, while a signature library makes the perturbations appliance-relevant and physically realizable through battery control. We provide theoretical rationale showing that proxy-guided optimization improves inference robustness under attacker diversity. Experiments on real-world datasets UK-DALE and REDD demonstrate strong cross-model and cross-appliance generalization. Across six unseen NILM attackers, covering four appliances on UK-DALE and five on REDD, our proposed defense increases average appliance-level RMSE by 107% and 166%, respectively, while reducing F1 score by 79% and 80%. --- ### Terminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining Authors: Adam Ousherovitch, Yixin Wang Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.25482v1 Large language model (LLM) pretraining conventionally returns the raw final iterate. This couples two design choices: the learning-rate schedule that generates the parameter trajectory and the estimator that constructs the deployed model (e.g. the raw final iterate or a checkpoint average). A schedule that promotes optimization progress may differ from one that minimizes variation in the raw final iterate. Separating these choices creates an opportunity to maintain progress late in training while reducing variation in the returned model. To this end, we propose \emph{Terminal Shrinkage Averaging (TSA)}, which interpolates between the raw final iterate and the average of recent checkpoints to balance recent progress against terminal variation. We analyze how TSA changes the preferred terminal learning-rate schedule under a local quadratic approximation and test this interaction through a sequence of controlled NanoChat experiments. Finally, we demonstrate that the resulting gains transfer to depth-22 NanoChat, where the combined schedule and estimator improve validation quality. A qualifying time-to-GPT-2 run also finishes faster than the public baseline used in our experiments, providing preliminary evidence of benchmark acceleration. --- ### Spectra: A Rules-Driven LLM Pipeline for Automated KYC Document Processing Authors: Miray Wahib, Ethan Tran, Rea Mourad, Mira Muti, Nikita Dvornik Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25474v1 Know Your Client (KYC) onboarding in capital markets requires analysts to manually classify documents, extract structured data from heterogeneous sources, and validate compliance against complex regulatory policies. This process requires significant analyst time per client, with end-to-end onboarding often stretching to multiple weeks due to sequential handoffs. In this work, we analyze an on-boarding process and find that it comprises repeatable components well-suited to AI automation. We therefore propose a restructured workflow to be amenable to automation: we consolidate the traditional four-party process into two parties that share most of the work and can be automated together, eliminating intermediate handoffs that compound delays. To automate the remaining steps, we introduce Spectra, an AI-assisted document processing platform that combines a structured rules engine with LLM-based classification, extraction, and validation agents. The rules engine encodes compliance policy as a queryable database, enabling focused context injection that reduces token usage while improving extraction precision. Rather than a single monolithic prompt, the system decomposes document processing into isolated, auditable stages, each optimized independently and traceable to specific policy clauses. In evaluation on real KYC documents, Spectra achieves 100% classification accuracy and 89.4% extraction accuracy. Human review burden dropped by 96%. --- ### A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization Authors: Wonho Bae, Zakaria Aldeneh, Martin Pelikan, Jan "Honza" Silovsky, Tatiana Likhomanenko, Sheikh Shams Azam Published: 2026-09-21 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2609.25471v1 Semi-supervised federated learning (SSFL) trains models on clients' unlabeled data using a teacher to generate pseudo-labels, with a small labeled seed dataset on the server. Automatic Speech Recognition (ASR) is particularly fragile here: pseudo-label errors compound across the output sequence and across training rounds into divergence, leaving a large gap to fully-supervised FL. We show that closing this gap turns on two coupled design axes -- the teacher (which model generates the pseudo-labels) and the anchor (the server-side updates on labeled data that stabilize training). On the teacher axis, a per-client online teacher (each client's own evolving model) diverges on its own, but once stabilized it matches or beats the broadcast global teacher (one server model, fixed within a round) -- decisively in-domain and competitively under domain shift. As the seed grows stronger and the online teacher's advantage narrows, a transitioning teacher (global $\rightarrow$ online at round $r$) matches or beats both. On the anchor axis, the server must keep training on labeled data between rounds -- otherwise the online teacher drifts -- and this interleaving, more than the seed model, governs convergence. The two axes are inseparable: aggressive teacher choices pay off only once the anchor stabilizes training, which is highly sensitive to data augmentation and batch size -- the settings that govern how much input and gradient noise the server injects. How much stabilization is needed is domain-dependent, governed by the dispersion of the seed data and its overlap with client data. These findings yield guidelines for SSFL in ASR training, improving over the strongest prior method on 9 of 11 pairs, by $20.8\%$ on average in-domain and $10.0\%$ cross-domain, narrowing the gap to fully-supervised FL. --- ### RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation Authors: Abdullahil Kafi, Alvi Ataur Khalil Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25469v1 Retrieval augmented generation (RAG) systems have emerged as the dominant architecture for grounding large language model (LLM) outputs in verifiable external knowledge, yet their structural reliance on a dynamic retrieval pipeline introduces a largely unexplored class of adversarial vulnerability. Existing knowledge-base poisoning attacks are fundamentally static. Adversarial documents are pre-computed and injected without any awareness of what the victim system will actually retrieve for a given query, leaving the attack blind to the competitive documentary landscape that surrounds its payload in the generator's context window. Unlike traditional static poisoning attacks that are blind to the retrieved context, we introduce RAG-NAROK (Retrieval-Anchored Generation Negation And Response Quality Collapse), a RAG attack framework that adapts to the query text. RAG-NAROK exploits the transparency inherent in RAG pipeline to first extract the legitimate source identities, then generate Anchor-Specific Refutation documents that explicitly name and devalue retrieved sources while leveraging recency and authority biases to steer the text generation toward a target answer. Our results demonstrate that RAG-NAROK significantly outperforms static baselines across diverse domains, revealing a fundamental tension between RAG transparency and AI security. --- ### ShowTellArena: Evaluating Business Workflow Understanding from Demonstrations Authors: David Garg, Ritobrata Sarkar, Ehsan Azarnasab, Siddhartha Borah Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25467v1 We often teach a colleague by showing the work and explaining the decisions as we go. How can we check what an agent understood from the same lesson? We introduce ShowTellArena, a benchmark protocol and public dataset for comprehension after narrated business demonstrations. The v1.0 release contains 50 business workflow tasks, with recordings, screenshots, narration, fixture seeds, and 502 questions. Tasks span finance, hiring, procurement, customer decisions, inventory, and logistics. The protocol holds the business scenario and quiz fixed while allowing each product to capture the lesson through its own teaching interface. Questions test operational rules, boundaries, exceptions, and errors in proposed automations. We analyze 218 selected pilot attempts across 39 workflow cases, including 28 cases attempted by all three evaluated systems. These exploratory results expose both answer errors and failures to complete the teaching experience. We describe the release's verification gaps and the pilot's uneven coverage, exclusions, and grading provenance. The contribution is an inspectable dataset and assessment workflow that others can extend; the selected pilot is not a controlled product ranking. --- ### Real-Time Hand Gesture Recognition for OpenXR Using Transformer-Based Machine Learning Authors: Salar Rezayani, Russell Butler Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25466v1 Hand gesture recognition is a key component in human-computer interaction (HCI), enabling intuitive interfaces for applications in gaming, virtual reality (VR), robotics, and more. This study integrates transformer-based machine-learning models for real-time hand gesture recognition, using hand-tracking data captured through the OpenXR standard in Unity. We leverage positional data of hand joints and wrist rotation angles to train a custom gesture recognition system. By utilizing the sequential modeling capabilities of transformers, the system captures temporal dependencies within short gesture windows and classifies gestures robustly across hand orientations and sizes. The results show a significant improvement in gesture classification accuracy. Building on this, we outline how the approach can be extended toward detecting the flow of movement, i.e., the transitions between gestures, as future work. --- ### Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions Authors: Niloofar Gholipour, Marcos Assuncao, Gursimran Singh, Timothy Yu, Rajkumar Buyya, Julien Gascon-Samson, Zhenan Fan, Yong Zhang, Xiaojie Xu, Yaqiang Yao, Xiaolong Bai Published: 2026-09-21 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2609.25463v1 Reasoning-oriented reinforcement learning enables large language models to solve mathematical, coding, and other multi-step tasks, but shifts a substantial portion of the training cost to rollout, where trajectories are generated for policy updates. Efficient rollout mechanisms are therefore essential to reduce this cost while maintaining the freshness, consistency, and statistical validity of training data. This survey provides a systematic taxonomy of recent research on rollout efficiency for reasoning-oriented reinforcement learning, classifying existing approaches from both mechanism and bottleneck perspectives. Based on this taxonomy, we analyze how different technique families address distinct sources of rollout inefficiency, examine opportunities and potential conflicts for combining them, identify gaps in the evaluation and reporting of efficiency gains, and discuss open challenges and future research directions. --- ### Transformer-Informed Trajectory Optimization for Relative Motion in Cislunar Orbits Authors: Walter J. Manuel, Yuji Takubo, Simone D'Amico Published: 2026-09-21 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2609.25460v1 Autonomous spacecraft guidance and control requires a fast solution to non-convex trajectory optimization, which can be accelerated by providing a near-optimal initial guess to an optimization protocol, i.e., warm-starting. A robust warm starting method is especially useful for rendezvous, proximity operations, and docking (RPOD) in cislunar space, where the underlying dynamics become severely nonlinear and chaotic compared to those in Earth orbit, especially at perilune. This paper extends the Autonomous Rendezvous Transformer (ART), a transformer-based warm-start trajectory generation method, to cislunar RPOD scenarios for the first time. To accurately and reliably solve the nonconvex optimal control problems (OCPs) posed by these scenarios, a new and enhanced version of ART, ART-TWIN (Two-Way INference), is introduced. Inspired by forward-backward shooting methods used in other trajectory design applications, ART-TWIN autoregressively generates two arcs, one from the initial state and one from the desired terminal state, that are patched together at the midpoint of the timeseries. When evaluated on a set of simulated rendezvous scenarios that are initialized at perilune, ART-TWIN is demonstrated to substantially accelerate convergence and increase feasibility guarantees when used as a warm-start to sequential convex programming (SCP), compared to convex relaxations and the original ART. These results illustrate the necessity of ART-TWIN's dual-arc generation to enable the viability of and gain benefits from using transformer-based warm-start methods in the most challenging areas of the cislunar dynamical regime. --- ### MIND the Gap: A Geographic Implicit Neural Representation with Adjustable Spatial Scale Authors: Isaac Corley, Arjun Rao, Esther Rolf, Konstantin Klemmer, Evan Shelhamer, Nils Lehmann, Marc Rußwurm, Gengchen Mai, Nathan Jacobs, Hannah Kerner Published: 2026-09-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.25454v2 Geographic measurements are often sparse, leaving large areas without labels for the quantities we want to map. Geographic implicit neural representations (INRs) provide coordinate-based embeddings that can be combined with sparse labels to predict at unsampled locations without satellite imagery at inference. Yet existing INRs are largely evaluated with random holdouts, leaving their ability to generalize across larger geographic gaps unclear. We introduce Matryoshka Implicit Neural Distillation (MIND), a geographic INR whose spatial granularity can be adjusted after training. MIND distills several pretrained geospatial models using nested supervision at increasing embedding dimensions, dividing the representation into contiguous chunks. Early chunks capture broad spatial patterns, while later chunks add increasingly local variation. Downstream models can retain only the leading chunks or use our Chunked Penalty to reduce reliance on later chunks without retraining the INR. We also introduce CoordBench, comprising $52$ datasets and $78$ targets with both random and regional holdouts at multiple spatial scales. Across CoordBench, fine-scale features help most when labels are nearby, while smoother representations generalize better across larger geographic gaps. MIND with the Chunked Penalty achieves the highest aggregate regression and classification performance among tested INRs and the highest overall performance under regional holdout. These results show that geographic representations should be evaluated and adapted according to the spatial separation between labeled and prediction locations. --- ### Combinatorial Network-Based Manifold Topological Deep Learning for Image Analysis Authors: Alice Wachira, Xiang Liu, Zhe Su, Yiying Tong, Ge Wang, Guo-Wei Wei Published: 2026-09-21 Categories: cs.CV, q-bio.BM arXiv: https://arxiv.org/abs/2609.25453v1 Medical image analysis remains fundamentally challenging because of the intricate geometric and topological structures present in medical data. Conventional convolutional neural networks model images as regular Euclidean grids, limiting their ability to preserve geometric relationships and higher-order structural information. Recently, manifold topological deep learning (MTDL) has emerged as a promising paradigm that integrates deep learning with geometric and topological representations. Nevertheless, existing methods have not yet fully exploited discrete manifold structures within combinatorial complex neural networks. To bridge this gap, we introduce CNMTDL, a MTDL framework that integrates Hodge decomposition with a combinatorial attention mechanism. In our approach, medical images are represented as discrete manifolds and decomposed into three Hodge components. Features extracted from these components are concatenated and embedded into a combinatorial complex architecture, enabling enhanced higher-order message passing between $0$-cells and $2$-cells through attention-based blocks. We evaluate CNMTDL on six two-dimensional and three-dimensional datasets from the MedMNIST v2 benchmark, demonstrating its effectiveness for medical image analysis. --- ### Conduct Under Pressure: What Sixty Language Models Do When a User Pushes Authors: Tapan Parikh Published: 2026-09-21 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2609.25447v2 We study what LLMs do when a user applies pressure in an uncomfortable situation: a user insists, begs, flatters or grieves, and the model gives up a correct fact, writes a document it should refuse, or cheers a plan that will cost the user money. We send frozen multi-turn scenes, identical for every model regardless of the reply, to 60 models from 13 vendors, and label each transcript with a codebook built by open coding and then frozen: a trajectory (the model held its position or folded) and a manner (how it held or folded). Two findings separate. Whether a model holds tracks its generation, meaning how recent it is: fold rate correlates with a public capability index at Spearman -0.64, with little vendor effect. How it holds tracks the vendor: six of the 17 manner codes sort by vendor at permutation p <= 0.001, corrected across the codebook. We report four vendor profiles on the codes that cleared reliability. We also ask which parts of the labeling need a person. Six LLM coders from three vendors apply the codebook more consistently than three human coders do (Krippendorff's alpha 0.66 against 0.46), agree with the codebook's author on trajectory at kappa 0.84 to 0.91 on transcripts the codebook's examples never touched, and match an adjudicated human reference at 0.83. Blind machine readings recover the codebook's categories but cannot tell which of them a second reader would apply the same way. We conclude that for behavior a non-specialist can judge, the human contribution is authoring and bounding the codes and owning a small reference, not producing labels at volume. --- ### Mean Velocity Matching: Rethinking Generative Dynamics in Diffusion Models Authors: Yunhong Zhang, Changjie Cao, Zhihua Zhang, Bingli Liu, Zongjie Cao, Zongyong Cui, Ying Yang Published: 2026-09-21 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.25444v1 This work studies prediction parameterization for stochastic generative dynamics in diffusion models. Existing velocity-based generative models provide the simplicity of learning a single transport field, but their standard formulation is deterministic, whereas stochastic extensions generally require additional score information or an intermediate velocity-to-score reconstruction. To retain single-field prediction while directly supporting stochastic reverse dynamics, this paper introduces Mean Velocity Matching (MVM). MVM constructs a Gaussian perturbation process for which the conditional expectation of a restoration-oriented velocity, $(x_0-x_t)/t$, directly forms the reverse-SDE drift. Consequently, a single learned field is sufficient to parameterize the stochastic reverse process without separately estimating or reconstructing the score. Because direct regression of this velocity becomes unbounded near $t=0$, MVM further introduces a $\sqrt{t}$-scaled parameterization that preserves the reverse dynamics while yielding a bounded training target. The same learned field also induces a deterministic probability-flow ODE, enabling stochastic and deterministic sampling to be studied within a unified formulation. Experiments with Transformer-based generative models achieve an FID of $\MVMImageNetThirtyTwoFID$ at \MVMImageNetThirtyTwoNFE\ NFE on ImageNet $32\times32$ and $\MVMImageNetTwoFiftySixFID$ at \MVMImageNetTwoFiftySixNFE\ NFE on ImageNet $256\times256$. Controlled SDE--ODE comparisons further show that the ODE performs better under very low NFE, whereas the stochastic reverse process achieves lower FID when sufficient function evaluations are available. These results demonstrate that MVM provides a direct single-field parameterization of stochastic reverse dynamics while maintaining competitive generation quality. --- ### ZeroGate: Trust-Preserving Fast Paths for Governed AI Agent Runtimes Authors: Zexun Wang Published: 2026-09-21 Categories: cs.AI, cs.CR, cs.DC arXiv: https://arxiv.org/abs/2609.25443v1 Moving authorization earlier can shorten an agent's dispatch boundary without removing authorization work. It can also admit an action whose payload, authority, or relevant state has changed. ZeroGate separates exact-action approval from durable local admission: an issuer signs a short-lived ActionPass, and a trusted runtime adapter reconstructs the final action before a local gate checks its binding and consumes its nonce. A SQLite transaction couples nonce consumption, applicable quota updates, and an admission receipt. We state a conditional decision-preservation proposition: successful local admission implies that a specified synchronous policy would authorize the same action at the admission point, provided approval is sound, all policy dependencies are represented and current, observations are faithful, and consumption is atomic. The implementation alone establishes neither current-world freshness nor exactly-once remote effects. Evaluation separates authored semantic fixtures, controlled concurrency and crash experiments, and an Azure Blob study comparing synchronous and prepared execution through the same issuer and gate. Both modes mint an exact-action pass; lifecycle latency includes preparation and prepared-batch dwell. Across 4800 cloud attempts, prepared worker-admission-to-dispatch p95 ranges from 9.802 to 11.374 ms, versus 25.018 to 334.000 ms synchronously, across the tested concurrency levels. Prepared mean complete lifecycle is longer at every level: the boundary improvement is not a net speedup. The contribution is an explicit revalidation contract, a durable reference boundary, and an auditable comparison of where authorization cost is paid, not a new cryptographic primitive or a universal performance frontier. --- ### WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning Authors: Xuanlin Jiang, Samuel Hsia, Michael Kuchnik, Zachary DeVito, Minlan Yu, Carole-Jean Wu Published: 2026-09-21 Categories: cs.DC, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2609.25442v1 Weight transfer - the propagation of updated parameters from trainers to rollout generators - is becoming an important performance bottleneck in reinforcement learning (RL) systems for LLMs. The central challenge is supporting the diverse trainer and rollout layouts and synchronization requirements of modern RL workloads without sacrificing efficiency. Existing solutions are efficient under some configurations but perform poorly or lack support under others. We present WeightBridge, a flexible, efficient weight-transfer library designed to deliver high performance across diverse RL configurations. WeightBridge first automatically extracts the correspondence between trainer and rollout weight layouts, then plans and executes redundancy-free and load-balanced weight transfer. It exposes a small, general API while coordinating workers across diverse synchronization modes. Across configurations spanning different models, parallelization layouts, and synchronization modes, WeightBridge reduces average GPU stall time by up to 42$\times$ over the state-of-the-art open-source RL framework and achieves high performance in all settings. A coding agent was able to integrate WeightBridge into two different RL frameworks without manual guidance, demonstrating the generality and ease of use of its APIs. --- ### Mining Legal Arguments in U.S. Corporate Case Law Authors: Luis Brena, William Jurayj, Gregory Deyesu, Zaid Al-Huneidi, Andrew Blair-Stanek, Benjamin Van Durme Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.25441v1 Legal argument mining supports passage classification, retrieval, and argument completion. This work introduces an expert-annotated dataset of 42 U.S. federal tax opinions on corporate reorganizations under I.R.C. §368. To our knowledge, it is the first expert-annotated, tree-structured argument corpus for this domain. Explicit spans receive one of five functional labels: Rule, Analysis, Conclusion, Background Facts, and Procedural History. Rule, Analysis, and Conclusion spans can be linked into directed support trees, while Background Facts and Procedural History serve a contextual function. The corpus provides span-based, sentence-based, flat, and tree-structured representations. Agreement analysis shows that functional node labels are more reliable than directed support edges and implicit intermediate conclusions. Directed-path agreement is stronger than direct-edge agreement, which indicates that broad reachability is more stable than exact local decomposition. Classification experiments show that functional labels are learnable under case-disjoint evaluation. Retrieval experiments show that supervised fine-tuning improves within-case retrieval. However, cross-case generalization remains weak. The dataset supports legal passage classification and provides a conservative benchmark for structured argument mining in U.S. federal tax case law. --- ### PermuFormer: Multi-Task Pretraining for Permutation Representation in Algebraic Combinatorics Authors: Henry Kvinge Published: 2026-09-21 Categories: cs.LG, math.CO arXiv: https://arxiv.org/abs/2609.25438v1 Diverse pretraining has been shown to be an effective method for learning reusable, domain-aware representations that provide a starting point for fine-tuning on downstream tasks. While much of the excitement in AI for math has been concentrated in the use of frontier reasoning models to solve well-specified problems through the medium of language, narrow, specialized models remain an important component of the AI for math ecosystem. In contrast to large language models, specialized models are usually trained directly on the mathematical objects themselves (e.g., graphs, sequences of numbers) rather than the textual descriptions that characterize these objects. However, the common practice of training specialists from scratch may limit their ability to develop domain-aware representations that capture the multifaceted nature of mathematics. In this paper, we describe an approach to pretraining for permutation-focused tasks in algebraic combinatorics. We introduce PermuFormer, an autoregressive transformer trained on a 2.8 billion token multi-task, multi-encoding corpus. We show that PermuFormer is an effective starting point for fine-tuning on basic tasks unseen during pretraining and more complex research-level tasks, frequently outperforming the same architecture trained from scratch, baseline MLPs, and a fine-tuned generic language model of comparable size. We also analyze some of the internal mechanisms by which PermuFormer learns to solve training tasks. For example, we show that while some tasks can be linearly decoded directly from the internal representation of the prompt, other tasks require multiple rounds of generation before the answer can be decoded. --- ### Lightweight Ranking Heads: Accelerating Multi-Task Experimentation in Production Recommender Systems Authors: Sanjay Surendranath Girija, Aniruddh Nath, Li Wei, Yanhao Jiang, Shawn Andrews, Lukasz Heldt, Yi Wu, Aditya Mahajan, Mohit Sharma Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.25433v1 Modern production-scale recommender systems rely on complex, multi-task ranking models. Introducing new prediction tasks into these massive systems often causes bottlenecks - it risks negative task conflicts with existing tasks, and can lead to long development and experimentation cycles due to the expensive retraining of backbone models and downstream models or tuning of reward combination formulas. To address the critical challenge of slow experimentation velocity, we introduce the Lightweight Ranking Heads (Light Heads) framework. Designed for continuous online learning environments, Light Heads enable the dynamic injection of new tasks into existing multi-task ranking models, effectively obviating the need for model cold-starting and retraining of backbone models. By utilizing stop-gradients and stateless daily training, this design strictly isolates new tasks, mitigating the risk of adverse task conflicts. Crucially, this framework uses a centralized configuration that allows Light Heads to be added to multiple models simultaneously, unblocking faster training data generation and co-training of downstream models. Successfully deployed at YouTube scale, this approach reduces the iteration cycle for multi-task experimentation from several weeks to days. In this paper, we detail the system architecture, analyze the training dynamics of stateless cold-started heads, compare their performance to full heads, and demonstrate how Light Heads have enabled the rapid A/B experimentation and deployment of new ranking tasks that yield measurable production value. --- ### Predictive Uncertainty for Neural CAE Surrogates Authors: Kaustubh Tangsali, Mohammad Amin Nabian, Kelvin Lee, Carmelo Gonzales, Sanjay Choudhry Published: 2026-09-21 Categories: cs.LG, cs.AI, math.PR, physics.comp-ph arXiv: https://arxiv.org/abs/2609.25430v1 Neural surrogates can substantially accelerate computer-aided engineering (CAE) workflows, but their use in design requires uncertainty estimates that remain meaningful across varying geometries, spatial prediction fields, and engineering quantities of interest. We investigate how established uncertainty quantification (UQ) approaches behave when adapted to geometry-conditioned neural surrogates. We compare one closed-form and two sampling-based approaches-a Gaussian process (GP)-based method, concrete Monte Carlo (MC) dropout, and deep ensembles-and evaluate them on three large, industry-relevant CAE datasets for external aerodynamics and crash dynamics. We examine whether predicted uncertainties have credible magnitudes, identify locations with larger prediction errors, respond to unfamiliar inputs, and remain informative for derived engineering quantities. On the DrivAerStar dataset, where all three methods are compared, each generally assigns higher uncertainty to locations with larger prediction errors, and validation-based rescaling brings interval coverage close to nominal on a disjoint in-distribution test set. Results on AirFRANS and automotive crash also show useful error ranking and interval estimates, but the relative performance of the methods changes with the dataset and evaluation criterion. UQ methods and evaluation metrics should therefore be selected based on the intended downstream CAE decision. --- ### Directional Total Variation-Regularized Implicit Neural Representations (DTV-INR) for Continuous Super-Resolution in Degraded Imaging Domains Authors: Mahmoud Saeedi Kelishami Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.25429v1 In this paper, we introduce the Directional Total Variation-Regularized Implicit Neural Representation (DTV-INR), an advanced variational paradigm that synergistically integrates coordinate-driven implicit neural networks with an anisotropic, structure-tensor-informed total variation regularizer tailored for resolution-agnostic image super-resolution. Casting the continuous-to-discrete acquisition process into an ill-posed inverse problem framework, our formulation equips a SIREN-architected coordinate network with a dynamic Riemannian metric tensor field D(x). By leveraging its spectral decomposition, the proposed regularizer preferentially directs diffusion parallel to dominant structural contours while penalizing cross-edge dissipation, successfully circumventing the classical staircasing artifacts inherent to scalar total variation schemes. We rigorously prove the well-posedness of this formulation in H^1(Omega) by establishing the existence, uniqueness, and metric stability of the variational minimizer, and realize this via an alternating projected optimization algorithm that decouples network parameter tuning from adaptive tensor field updates. Comprehensive experiments conducted on clinical brain magnetic resonance imaging (MRI) and biomedical transmission electron microscopy confirm substantial quantitative and qualitative improvements, yielding PSNR enhancements reaching +5.05 dB over baseline unregularized INRs and +1.71-2.85 dB over isotropic TV-INR across continuous (non-integer) upsampling factors, alongside remarkable noise robustness up to sigma_eta = 0.10 and monotonic preconditioned convergence behavior. --- ### Beyond Natural Language: An Agent-Native Language for Autonomous Science Authors: Yifeng He, Jiachen Liu Published: 2026-09-21 Categories: cs.PL, cs.AI arXiv: https://arxiv.org/abs/2609.25421v1 As autonomous AI agents take on every stage of scientific inquiry, research output is expanding far beyond human review capacity. Yet scientific communication still relies on natural-language prose: an informal medium prone to ambiguity, hidden assumptions, and untracked limitations that machines cannot reliably audit. We introduce Lara, a machine-checkable language and protocol for checking and revising support for research claims. By turning research arguments into executable artifacts, Lara provides an epistemic kernel for autonomous science: it enables automated validation pipelines for research agents, lets declared bridges connect arguments across papers into an auditable network, and allows both humans and machines to recheck the standing of an encoded claim in milliseconds. In a Lara program, authors explicitly declare their claims, supporting evidence and assumptions, and known objections or limitations. A lightweight, deterministic checker adjudicates these interactions, assigning each claim a reproducible status: "justified", "defeated", "contested", or "gap", which marks a claim whose support is incomplete and locates the unanswered question. Case studies cover empirical review, a philosophical debate without measurements, and the loss of support when an assumed axiom is withdrawn. We establish the metatheory of claim checking and cross-context argument transport, and mechanize the semantic guarantees in Lean 4 (roughly 117,000 lines), leaving three arguments on paper. The audited public metatheory is "sorry"-free and uses only Lean's three standard axioms; some executable examples additionally trust native evaluation. --- ### Learnable Classifier-Free Guidance Null Embeddings for Enhanced Controllable Speech Synthesis Authors: Biel Tura Vecino, Yoach Lacombe, Julian Weber, Zbigniew Łatka, Haitong Zhang, Logan Hart, Eren Gölge Published: 2026-09-21 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2609.25411v1 Classifier-free Guidance (CFG) is widely adopted in text-to-speech (TTS) systems to enhance generation quality and conditioning fidelity by interpolating between conditioned and unconditioned predictions. A common unconditional technique is to use an empty representation, in the form of a fixed null vector. In this work, we propose replacing this representation with a learnable unconditional embedding, optimized to represent a meaningful unconditional state. Objective and subjective evaluations demonstrate that learnable null embeddings consistently outperform fixed null embeddings across speaker similarity, speech stability, and expressiveness, while exhibiting greater robustness to larger guidance scales. We further show that learning a distinct unconditional embedding for each of the TTS conditioning modalities allows fine-grained control over speaker and text guidance, showcasing the trade-off between similarity and quality, and stability and expressiveness in the generated speech. --- ### From Offline Proxies to Online Decisions: A Layered Engagement Evaluation Framework for Conversational AI Authors: Xuanyi Li, Vaskar Nath, Hossein Amirkhani, Jay Li, Alex Deng Published: 2026-09-21 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.25408v1 Online A/B experiments are the decision standard for user engagement, but traffic and readout time limit how many conversational-AI changes can be tested. We ask whether an offline signal designed to be computable without treatment-arm user exposure agrees with the outcomes of those experiments. We contribute a reusable construction and diagnosis checklist that treats an offline proxy as a chain of three alignments: behavioral label to product outcome, learned classifier to candidate-assistant behavior, and aggregated offline signal to experiment effect. A companion evaluation protocol audits the whole composite by interval-aware decision agreement, which compares offline and online confidence intervals instead of point estimates, and by within-experiment ranking. The instantiation we evaluate comprises a fixed evaluation suite on which candidate behavior is scored, an engagement classifier trained to predict session/prompt level engagements, and a calibration layer mapping sample-level score differences to online model-level engagement deltas. We then report the audit: 489 paired offline-online contrasts (one candidate arm against its control) from 27 experiments on a deployed multi-turn assistant, spanning model checkpoints to system-prompt tuning. Our primary test uses the 113 contrasts from eight experiments that ran after the map was frozen: on these the composite reaches 81.1% F1, against 34.3% for the raw classifier score it is built on, and makes no wrong-direction calls where that raw score makes 31. Every offline prediction was computed before its experiment ran to prevent overfitting. The evidence supports using the composite to prioritize candidates before scarce experiment traffic is allocated---in our deployment of the experiment, selecting among training checkpoints and tuning system prompts. --- ### Efficient Iterative Retrieval with Heterogeneous Batching Authors: Dohyun Park, Hubertus Franke, Daniel G. Waddington, Swaminathan Sundararaman, Yongjoo Park Published: 2026-09-21 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.25405v1 Modern information retrieval increasingly employs both embedding and generative models to handle complex queries. However, current serving systems suffer from low throughput and poor GPU utilization because they execute these models in isolation. Coarse-grained partitioning, such as dedicating GPUs to specific tasks, fails to adapt to dynamic workloads and creates computational "bubbles". To address these, we present Orthrus, a serving system that performs heterogeneous batching within a unified inference loop. The primary challenge lies in unifying embedding and generation workloads with conflicting computational patterns while optimizing batch composition for high performance. Orthrus addresses these challenges through chunked embedding with incremental pooling and by adjusting batch composition in a workload-aware manner. Evaluation on four A100 GPUs shows that, relative to baseline deployments, Orthrus achieves 1.28$\times$--4.52$\times$ higher throughput on controlled workloads and up to 55.8% lower end-to-end p99 latency on an iterative-RAG benchmark. We release our code at https://github.com/illinoisdata/Orthrus . --- ### Robust Failure, Conservative Repair: Textual Knowledge Distillation from Cross-Model Failures Authors: Andrew Ren, Haokun Liu, Chenhao Tan Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.25400v1 Failure-based textual knowledge distillation aims to discover gaps in a model's knowledge by examining its task errors. The distilled knowledge can be useful for the reasoning of both this model ("source model") and other models. However, this transfer of knowledge may not be stable. We define a rule atom to be a standalone rule injected into a model's textual input at inference time. A rule atom can encode transferable task knowledge or model-specific reasoning patches that can confuse other models. Also, the injected rule atoms can be misapplied to unrelated cases, causing the model to incorrectly flip its answer based on irrelevant information. Building on a pipeline that distills training examples into task-specific cheat sheets that aid model reasoning, we examine when failure-derived rules can improve these cheat sheets. Our early experiment shows rule distillation from a single model's failures underperforms the baseline cheat sheet on non-source model families. This motivates Robust Failure, Conservative Repair (RFCR), a textual distillation procedure that derives rules from failures shared across models, sharpens their application boundaries using boundary cases, and abstains when no useful rule is found. On a 400-item BIG-Bench Hard task set, RFCR improves the baseline cheat sheets from 68.50% to 71.25% (+2.75 pp; 95% CI (+1.25,+4.50)) without performance degradation on previously correct cases. Ablations and cross-model diagnostics support that accuracy gains come from both new knowledge injection and strict rule-application control. --- ### Deep Reinforcement Learning on Item-Compatibility Graphs for One-Dimensional Bin Packing Authors: M. Aslı Aydın Published: 2026-09-21 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2609.25397v1 The one-dimensional bin packing problem (1D-BPP) is a classical NP-hard combinatorial optimization problem with applications ranging from logistics and manufacturing to cloud resource management. Although deep reinforcement learning (DRL) has become a competitive paradigm for data-driven optimization, most learned packing methods target 2D and 3D variants, and intelligent learned solvers for 1D-BPP remain scarce. In this paper, we present a novel end-to-end, size-agnostic graph reinforcement learning framework for 1D-BPP. We formulate the packing process as a Markov decision process on an item-compatibility graph, serving as a structural knowledge representation in which every action merges two partial bins that fit together. A graph neural network actor-critic policy extracts relational features from this representation and is trained through reinforcement learning and decoded by stochastic beam search, enabling a single trained model to generalize zero-shot to instances of any size. We conduct a systematic empirical study across graph encoders, DRL algorithms, reward functions, training distributions, and hyperparameters. Evaluated zero-shot on the full BPPLIB benchmark against a constructive heuristic, a grouping genetic algorithm, and recent learned methods, our data-driven policy lowers the mean optimality gap of the constructive heuristic from 2.66\% to 2.31\%, with the largest gains on structured instances. Against learned baselines evaluated on the same benchmark, it attains a lower gap on most of the nine families and is far more stable across instance distributions. On the hardest benchmark family, it outperforms a state-of-the-art learned solver that relies on column generation and integer programming, while using no solver at all. A grouping genetic algorithm remains ahead overall, and we analyze where and why the residual gap arises. --- ### Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development Authors: Haocheng Xia, Eugene Wu, Yongjoo Park Published: 2026-09-21 Categories: cs.CL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.25396v1 Parallel coding agents can produce patches that work alone but fail when merged. This happens when one agent changes an interface or rule that another agent still relies on. We study these failures with stale, a benchmark for semantic coordination. Our evaluation runs the same tests on each patch alone and on their combination, counting only failures introduced by combining the patches. We use three tiers: synthetic tasks with controlled interface changes, pairs of merged pull requests, and constructed tasks that use real Django helpers. Among 834 runs on 417 mined Django pairs, only one showed interference after correcting the grading procedure. On constructed tasks using 12 Django helpers, interference occurred in 97% of runs. A message describing the completed concurrent change recovered 82% of runs. Reviewed pull requests may contain few unresolved parallel changes, even when agents fail on controlled tasks using real code. The constructed failure rates do not estimate how often these problems occur in practice. ---