# Research Papers — 2026-09 · bundle page 121 of 266 > Full-text markdown of papers #6001–6050 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/121 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/120.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/122.md) ### VGG16-MCA UNet: Whole-Tumor Segmentation in 2D FLAIR MRI with Decoder-Side Channel Attention Authors: Shubham Gajjar, Deep Joshi, Avi Poptani, Vishal Barot Published: 2026-09-20 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.23919v1 Automated brain tumor segmentation supports diagnosis, treatment planning, and monitoring of disease progression, but building models that generalize across heterogeneous tumors and limited annotated data remains difficult. We present VGG16-MCA UNet, a hybrid architecture pairing an ImageNet-pretrained VGG16 encoder with a decoder in which a Multi-Channel Attention (MCA) module recalibrates features after each skip-connection fusion, trained with the Focal Tversky loss to counter severe foreground-background imbalance. We evaluate the model as a 2D, FLAIR-only, whole-tumor segmenter on tumor-positive slices from two public datasets: the BraTS 2020 benchmark and the LGG MRI Segmentation dataset. Using 5-fold cross-validation and a single network formed by averaging the weights of the five fold models, the method attains an aggregate pixel-level Dice (F1) of 95.10% on our held-out BraTS 2020 split and 88.32% on LGG. These scores are computed over all test pixels pooled into a single confusion matrix rather than averaged per case, and are therefore not directly comparable to the per-case mean Dice used in the BraTS challenge protocol. All partitions were drawn over individual slices rather than over patients, so every patient contributes slices to both training and test; the figures above therefore measure interpolation within known patients and should be read as an upper bound rather than as generalization to new ones. The model segments a 256x256 slice in 66.32 ms on a single 6 GB NVIDIA RTX 2060, approximately 8 ms more than an equivalent VGG16-UNet without MCA. We release the split records and report the protocol in full, with the aim of providing a precisely specified and reproducible 2D FLAIR baseline. --- ### Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer Authors: David Litman Published: 2026-09-20 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.23917v1 Chess involves complex reasoning in a deterministic environment, which makes it a useful setting for studying the mechanisms of computation inside transformers. The Maia-3 chess transformer takes Elo, a measure of competitive chess skill, as an input to the pre-trained network, so we can vary the skill the network is conditioned on with no change to its weights. Here we investigate how turning this skill dial affects self-attention. Ablating every attention head at every Elo from 700 to 2500, we find 1) increasing skill pushes the causal center of mass of the computation deeper, monotonically, for every chess piece and move type we measured; 2) the depth migration is much greater for specific tactics, especially knight forks, than for other move types; 3) the migration consists of deeper heads getting recruited for more specialized computations while one shared shallow head keeps a roughly constant contribution. These results may shed light on how conditioning inputs redistribute computation in larger transformers. --- ### Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting Authors: Fırat Öncel, Salman Hussain Ali, Mirco Ravanelli, Cem Subakan, Çağatay Yıldız Published: 2026-09-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.23916v1 Large language models (LLMs) drift out of date the moment their pretraining ends, yet retraining from scratch is prohibitively expensive. Continued pretraining (CPT) is the natural remedy, but it is typically evaluated through a continual learning lens that assumes disjoint data streams. This is a poor fit for time-incremental updates on web-scale crawls, where successive snapshots share substantial URL overlap by design. We study time-incremental CPT in this realistic regime: continued pretraining on FineWeb-Edu dumps drawn strictly from after each model's knowledge cutoff, evaluated across six open-weight models spanning three families (OLMo2, Llama-3.1/3.2, Gemma-3-1B) and four parameter scales (1B-3B-7B-8B). We organize our findings around four practical questions. (i) Is knowledge acquired? Yes, but heterogeneously, and without catastrophic forgetting: five of six models also improve on pre-cutoff factual recall, and the gains track pretraining saturation (driven primarily by token budget per parameter). (ii) What does it cost? Almost nothing: the macro-average across a thirteen-task suite stays within 0.01 of the base for every model. (iii) What is the recipe? Data quality dominates quantity (a curated 6B-token slice matches a broader 40B one); the optima for knowledge acquisition and general capability are separated by roughly an order of magnitude in learning rate; and LoRA at sufficient rank matches full CPT. (iv) Does it survive deployment? CPT gains transfer through SFT, while DPO's effect is family-dependent. Together, these results paint a more optimistic picture of time-incremental CPT than the prior continual learning literature suggests. --- ### Learning-Based 3D Reconstruction of Power Networks from Aerial Point Clouds Authors: Rishabh Jain, Anuja Saini, Vishal Jain Published: 2026-09-20 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.23915v1 This paper presents an end-to-end framework for reconstructing overhead power utility network topology and extracting span-level physical metadata from large-scale aerial LiDAR. The pipeline begins with semantic segmentation of the input point cloud using an improved KPConv-based model, in which data sampling and loss functions are adapted to emphasize pole and conductor (wire) classes. Network topology inference then proceeds in two stages: (i) pole instances are obtained by clustering pole-class points and validating candidates using geometric criteria, including height and verticality estimated via PCA, and (ii) candidate pole pairs are evaluated using a heuristic method and a lightweight ResNet-based classifier on 2D top-view projections of pole and wire point distributions to determine whether a physical conductor span exists. By explicitly classifying candidate spans, the approach mitigates common failure modes of heuristic connectivity rules in dense or cluttered scenes and under partial wire observation. For each validated wire, attributes regarding utility infrastructure geometry are computed, including endpoint conductor heights, ground elevation, sag-related lowest-point features, conductor arrangement, and wire width. Evaluation on multiple real-world aerial LiDAR datasets demonstrates decimeter-level endpoint height accuracy and approximately 9% relative improvement in recall for topology reconstruction compared to heuristic nearest-neighbor baselines, with larger gains in complex layouts. --- ### ReVeal: A Reconstruction-Aware Real-to-Sim Framework for VLA Policy Evaluation Authors: Xinyi Wang, Heng Hao, Wenjun Hu, Anna Enyu Li, Dizhi Ma, Karthik Ramani, Hankyu Moon, Yeong-Dae Kwon Published: 2026-09-20 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.23910v1 Simulation-based evaluation provides a scalable and repeatable alternative to real-world evaluation of vision-language-action (VLA) policies. However, reconstruction errors can cause simulated policy performance to diverge from real-world performance, motivating the need to assess reconstructed environments for downstream VLA policy evaluation. We present ReVeal, a real-to-sim assessment framework combining workspace reconstruction, reconstruction-level assessment, and matched closed-loop policy evaluation. Novel-View Mesh Fidelity (NVMF) and Annotated Planar Geometry Fidelity (APGF) assess observation and planar geometric fidelity, respectively. We also develop PGSR-D, a reconstruction pipeline incorporating monocular depth supervision to improve geometry where multi-view visual cues are limited. Across 8 assessment scenes, NVMF and APGF consistently distinguish the fidelity of 2DGS, PGSR, and PGSR-D. Matched evaluations of GR00T, SmolVLA, and pi0.5 across 8 humanoid manipulation tasks show consistent ordering between reconstruction fidelity and real-sim performance agreement across pipelines. Further analysis of the evaluation workspaces shows that higher fidelity is associated with stronger real-sim agreement. --- ### A discrete generative model of neuronal spiking activity on microelectrode arrays Authors: Md Sayed Tanveer, Mohammed A. Mostajo-Radji, Ge Wang Published: 2026-09-20 Categories: cs.LG, eess.SP, q-bio.NC arXiv: https://arxiv.org/abs/2609.23907v1 Generative models of neural activity could help characterize tissue dynamics, compare experimental conditions, and simulate population activity for applications ranging from disease and drug-response studies to closed-loop experimentation. Existing approaches, however, typically assume a fixed set of sorted neurons, whereas high-density microelectrode arrays produce extremely sparse, array-wide binary spike volumes in which the observed subset of electrodes varies across assays. We introduce a discrete generative model that represents this activity using a shared vocabulary of spatiotemporal motifs. A residual vector-quantized autoencoder learns the motif vocabulary, while a factorized masked transformer predicts where activity occurs and which motif appears at each active location. We evaluate the model on 31 assays spanning human brain organoids and acute \emph{ex vivo} human hippocampal tissue. The learned motifs are broadly reused: assay identity explains only $9%$ of the entropy in motif use, and motif overlap across tissue types is comparable to overlap within them. When representation quality is evaluated independently of the generative prior, our approach achieves $5.2\times$ the voxel-level reconstruction average precision of a matched flat tokenizer. For masked completion and free generation, the full model achieves $1.4$--$2.6\times$ the site-level average precision of the matched generative baseline and outperforms it across all four families of generation metrics. These results establish a compact, reusable representation for array-wide spiking activity without learned assay-specific parameters, providing a scalable foundation for generative modeling across diverse neural preparations. --- ### Multivariate quantile regression via Kolmogorov-Arnold Networks Authors: Andrew Polar, Michael Poluektov Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23906v1 This paper introduces a novel algorithm for predicting conditional joint distributions of vector-valued targets in stochastic systems whose randomness is intrinsic rather than arising from observation errors or additive noise. Multivariate quantile regression also involves modeling conditional joint distributions but represents a less challenging task. It predicts the probability that vector-valued targets fall within predefined regions, identifies regions corresponding to predefined probability levels, or performs both tasks simultaneously. The proposed identification technique employs ensembles of Kolmogorov--Arnold networks (KANs) as flexible function approximators. Although the suggested technique is not theoretically restricted to KANs, KANs are particularly well suited to the proposed construction and are therefore used throughout this study. In addition to the training procedure, this work introduces a new discrepancy measure for joint distributions and a goodness-of-fit (GoF) test based on it. This GoF test was initially developed to validate and calibrate the proposed identification technique and is used here in an ad hoc manner. Although the test could be tabulated for broader use, such a tabulation is not pursued in this work. The test is also applicable more generally. --- ### GDN Tree-Scan: Served Tree Verification for Recurrent-Hybrid Language Models Authors: Zhiyuan Ma Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23900v1 Tree speculative decoding verifies multiple candidate continuations in one target forward pass. For attention-only transformers, the verifier mainly needs an ancestry mask. Recurrent-hybrid language models break this assumption: a candidate row must also carry the recurrent state that native sequential decode would have produced along its root-to-node path. Otherwise, a verifier can use a correct attention mask while still conditioning on an impossible recurrent history. We present GDN Tree-Scan, a served verifier for Gated-DeltaNet hybrid language models integrated into vLLM. The system combines FlashAttention-2 tree-bias attention, branch-local GDN scan/replay, device-side multidraft commitment, and accepted-chain-only state publication. On the public Qwen3.6-27B-FP8 checkpoint, in a clean batch-one (B=1) SWE/Codex decode gate at temperature 0.6, a six-node root-branch tree increases committed tokens/event by 17.2% at near-native verify-forward time and reaches 23.88 token-weighted decode tokens/s versus 18.80 for native five-step MTP (E5), a 27.0% token-weighted decode-throughput gain. The per-request-equal latency view is +4.0%, and end-to-end task wall time remains prefill-heavy. Empirical equivalence evidence is scoped to recurrent-oracle probability-rescore (p-rescore) closure within the observed native flip floor, not a full distribution-distance proof. --- ### Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challenges Authors: Heewon Baek, Alsharif Abuadbba, Kristen Moore, Hyoungshick Kim, Surya Nepal Published: 2026-09-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.23894v1 Agentic AI extends LLM security beyond generated content to persistent state, autonomous actions, tool use, and interactions with humans and other agents. Existing threat classifications often emphasize individual dimensions, obscuring connections among entry points, affected components, and security consequences. The known threat landscape also differs from the coverage demonstrated by empirical research. Through a structured review of 66 studies published from 2022 to 2026, we introduce T={S, B, P, A}, a cross-dimensional representation linking affected functional or system surfaces {S}, interaction or trust boundaries {B}, violated security properties {P}, and empirically examined architectures {A}. We analyze 22 artifact-backed red-teaming studies and 11 representative security benchmarks to characterize empirical coverage and evaluation maturity. Within the selected studies, evidence concentrates on prompt/reasoning, memory, and tool-mediated attacks, predominantly in single-agent settings. Persistent, Human--Agent, complex multi-agent, systemic, and long-horizon threats receive less coverage. These findings describe the selected corpus rather than establish gaps across all empirical research. Heterogeneous metrics, limited adaptive defense evaluation, architectural imbalance, and incomplete execution-state capture further constrain comparison and reproducibility. We derive 13 open research questions to guide more systematic, architecture-aware, and reproducible security evaluation of agentic AI. --- ### Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs Authors: Edward G. Friedman, Xiangchen Song Published: 2026-09-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.23892v1 Mechanistic interpretability defines features as the fundamental units of a neural network and circuits as the weighted subgraphs that carry out its computation. Because individual neurons are polysemantic, Cross-Layer Transcoders (CLTs) were introduced as a way to approximate a model's circuits by generating an attribution graph. The nodes of that graph, however, are unlabeled features: reading a graph means pruning it and then working out by hand what each surviving node means. To make CLTs easier to use for circuit discovery, we introduce Circuit-Diff, which intervenes on the model itself with a low-rank factual edit and takes the features whose role in the attribution graph changes under that edit as related to the edited knowledge. On the edits we examine, the flagged nodes are not only detectors of the object token: read off the CLT's released feature dashboards, they include features for the history, geography and associations surrounding the old and new objects. We formalize the method, measure how reliable a frozen CLT remains after a factual edit, test the selected nodes causally by patching them on up to 24 CounterFact edits, give a case study, and release an open-source implementation built on the circuit-tracer package, together with two further tools (multi-prompt aggregation and rule-based supernode labeling). --- ### SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses Authors: Xingyu Li, Juefei Pu, Haonan Li, Arrdya Srivastav, Kareem Shehada, Srikanth V. Krishnamurthy, Zhiyun Qian Published: 2026-09-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.23889v2 Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and efficient solution. The core challenge is twofold: a reproducer must first recover the trigger scaffold needed to reach the vulnerable state and determine the precise concrete values that actually trigger the bug. Existing directed fuzzing approaches are ineffective at recovering the necessary trigger scaffold, while LLM-only generation is brittle because it struggles with concrete-value discovery and runtime nondeterminism. We design SyzHarness, a framework that combines LLM reasoning with coverage-guided fuzzing for patch-based Linux kernel vulnerability reproduction. Given a patch, SyzHarness uses an LLM agent grounded by code navigation tools to synthesize a parameterized fuzzing harness that fixes the prerequisite setup logic while exposing only uncertain, bug-critical input parameters to be mutated by Syzkaller. SyzHarness then translates this harness into a Syzkaller compatible interface and iteratively refines it using hierarchical reachability feedback. We evaluate SyzHarness on multiple datasets of triggerable real-world Linux kernel vulnerabilities. On 100 KernelCTF cases, SyzHarness achieves a 78% bug reproduction success rate. On the SyzDirect benchmark, SyzHarness achieves a 73% bug reproduction success rate, substantially outperforming prior directed greybox fuzzing. On 50 recent, known-triggerable syzbot bugs fixed after March 2026, SyzHarness reproduces 40/50 (80%) using only the fix commits as input. --- ### this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent Authors: Zehua Cheng, Wei Dai, Jiahao Sun Published: 2026-09-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.23886v1 Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears without a person. What the program needs back is not prose. It is one of n declared options and a number it can threshold. Today that costs a round trip to a frontier model -- hundreds of milliseconds, a per-token bill, and a parser -- for a question that is usually a conjunction of three clauses. this-that-model-1.0 is a 2B-parameter typed decision model. Its answer is read directly from the hidden state at a designated position and restricted to the option set the caller declared, so no text is generated, nothing can be malformed, and every question in a request is answered in the same forward pass. It decides in 30.9 ms on one laptop GPU and generates zero output tokens doing it, where a frontier API call costs 8758 ms and the hosted systems that answer these questions well spend between 21 and 212 generated tokens per question thinking first, billed for every one. It sustains 32 decisions per second on one consumer GPU and never lets the state leave the machine. On a third party's recorded cohort of 68 decision questions, on their inputs and their wording, it scores 0.941 with a Brier score of 0.042, against 0.765 and 0.133 for the hosted service Jev on the same items. One pass of our 42-family internal suite takes 32 seconds and 0.000217 USD of electricity; the most accurate hosted model we measured needs 155.2 minutes and 10.636 USD. We also report where it loses. On multi-step arithmetic, which a single forward pass cannot carry intermediate results through, it scores 0.560 against their 0.98 to 1.00, and a targeted second training round improved the five task families it was written for and transferred to none of the other 13. The model is open-sourced in https://huggingface.co/flock-io/this-that-model-1.0 --- ### HumynexSurg-1: A Curated Expert Liposuction Dataset Authors: Rhea Huang, David L. Matlock, Laurence Reich Published: 2026-09-20 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.23885v1 Robot foundation models learn manipulation from large demonstration corpora, but surgery is missing from those corpora: across the 780-hour Open-H surgical collection, one dataset carries synchronized force and none covers an aesthetic procedure. Liposuction is the hard case, because the instrument works under the skin and the surgeon operates by feel and by judgment. Humynex Robotics builds curated expert datasets for this kind of procedure. HumynexSurg-1 is the first release: a master liposuction surgeon performing on porcine abdominal tissue while narrating every decision, recorded with synchronized suction pressure, six-axis hand force/torque, top-down RGB-D video, side video and a lavalier microphone -- 14 episodes, 42,738 frames, 35.6 minutes, 356 utterances of which 95% compile into a liposuction-specific label schema. The capture follows a patent-pending sensing plan organized around the quantities a policy needs, so a channel captured today by a model can be upgraded to a sensor tomorrow without changing the data format. This release captures the instrument motion as a tool-hand track in the side video and provides the force channel as state; the funded capture adds a measured 6-DoF handle pose, a validated force channel, ultrasound imaging of the fat layer, and palpation sensing. As a proof of concept, NVIDIA Isaac GR00T N1.7 fine-tunes on the dataset with no custom code in under an hour per run and learns the recorded sessions; scaling probes on the same episodes show where further gains come from: every new session lowers the error on an unseen session. The dataset, its label schema, its quality-assurance reports and its evaluation protocol are the product; the next capture, many short sessions across fat regions with the sensors named here, is what the probes point to. --- ### Collaborative Streaming Anomaly Detection with Interactive Explanations and Ensemble Consensus Authors: Diogo Risca, Afonso Lourenço, Ricardo Martins, Goreti Marreiros Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23883v1 We present a collaborative streaming anomaly detection system for high-speed data streams that explicitly integrates human analysts into the decision loop. The system combines heterogeneous detectors and aggregates their outputs through a normalization-based weighted consensus, complemented by artifact-aware rules to stabilize anomaly scoring under deployment. To improve interpretability, it derives surrogate models that approximate the ensemble consensus and expose human-readable sensor conditions associated with anomalous behavior. Analysts can actively intervene by reviewing anomaly episodes, adjusting consensus behavior, and refining surrogate rules used for anomaly prediction, producing a human-adjusted ensemble. We evaluate the approach on an industrial stream with 260\,000 events and 3 anomalous episodes, showing robust detection and actionable human-AI interaction. --- ### MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space Authors: Markus Karmann, Shile Li, Christian Internò, Bruno Andreis, David Klindt, Randall Balestriero, Jindong Gu, Philip Torr, Qi Zhang, Peng-Tao Jiang, Hao Zhang, Bo Li et al. Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23881v1 Joint Embedding Predictive Architectures (JEPAs) are a promising paradigm for learning task-agnostic latent world models without visual reconstruction. However, standard JEPA training exhibits a strong inductive bias towards slow features, causing feature suppression and the collapse of latent representation. While inverse dynamics provides temporal anti-collapse, it relies on action labels and offers little incentive to embed general, unlabeled dynamics. We introduce Difference Image and Single image embedding Regularization (DISReg), a novel regularizer that builds on an inverse-dynamics-style module that predicts temporal difference image embeddings without any pixel reconstruction loss, encouraging balanced static and dynamic feature learning. DISReg consists of a static term that shapes the distribution of the image embedding and encourages slow features, and a dynamic term, which, unlike direct regularization on the embedding, imposes no constraint on the image embedding's shape or distribution and instead only incentivizes that dynamic features be present. By integrating this regularizer into a standard JEPA, we establish our new architecture, MotionJEPA. Latent probing demonstrates that MotionJEPA produces more complete representations than other methods, and our trajectory analysis shows it maintains geometrically simple latent embeddings with low curvature. We further show that MotionJEPA improves downstream planning success under static-background distractors across four environments. --- ### Q-TIE: A Lightweight and Generalizable Re-ranking Framework for Temporal Information Retrieval Authors: Soyeon Kim, Hyunjin Kim, JinYeong Bak, Steven Euijong Whang Published: 2026-09-20 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.23880v1 Temporal Information Retrieval (TIR) has been increasingly critical given the rise of Retrieval-Augmented Generation (RAG). Since temporally mismatched evidence can be highly misleading, TIR aims to retrieve documents that are both semantically and temporally relevant to a query. Two TIR paradigms have emerged - temporal retrievers and temporal re-rankers - differing in how temporal relevance is modeled. While these paradigms provide complementary strengths, our analysis reveals that each alone falls short of robust TIR: temporal retrievers provide flexible query understanding via learned representations, but often fail to explicitly account for temporal constraints; temporal re-rankers can enforce such constraints more explicitly, but often rely on predefined re-ranking rules. To address this, we propose Q-TIE, a re-ranking framework based on learned Temporal Intent Extraction (TIE). By introducing a TIE model that maps each query's temporal constraint into a unified interval representation (i.e., $\langle t_{start}, t_{end} \rangle$), Q-TIE generalizes beyond predefined rules via model-based learning while explicitly modeling temporal constraints as a separate signal - jointly achieving what each paradigm typically trades off. Experiments demonstrate that Q-TIE consistently outperforms existing TIR methods with stronger generalizability across temporal query types, and provides a lightweight yet effective add-on for temporally-aware RAG pipelines. Code: https://github.com/ssoy0701/Q-TIE. --- ### Explainable Recommendations at Scale: LLM Rationales for YouTube Music Artist Discovery Authors: Xiao Liu, Yanwei Song, Srivaths Ranganathan, Yuan Chen, Zheyun Feng, Parker Steenburgh, Jochen Klingenhoefer, Nathan Lasche, Gergo Varady, Tim Steele Published: 2026-09-20 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.23877v1 Modern music streaming platforms face a persistent tradeoff: exploiting familiar content versus driving the exploration of novel items. While users frequently desire discovery, they hesitate to select unknown artists over proven favorites. Providing transparent, natural language rationales that explain why an unexplored item is recommended lowers this barrier. However, while Large Language Models (LLMs) excel at this nuanced explainability, their real-time deployment is severely bottlenecked by prohibitive inference costs and computational overhead. In this paper, we present an industry case study of a decoupled recommendation architecture that successfully scales exploration without compromising latency. Our system isolates LLM inference asynchronously offline, pre-computing personalized candidate pools of undiscovered artists alongside tailored rationales. Large-scale online A/B experiments validate our design. We demonstrate that combining LLM-backed recommendations with these explanatory rationales significantly reduces the trust barrier for new content, yielding statistically significant improvements in both user exploration and overall engagement on the discovery surfaces. --- ### GLR-MM: Graph-Based Global-Local Reconstruction for Robust Multimodal Chest X-ray and EHR Representation Learning under Missing Modalities Authors: Surbhi Sharma, Nikhil Manali, Devesh Maheshwari Published: 2026-09-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.23876v1 Clinical multimodal models must often predict before all chest X-ray (CXR) and electronic health record (EHR) inputs are available. Existing approaches align observed representations, model missingness, or reconstruct across modalities, but do not jointly exploit within-patient and clinically similar inter-patient evidence. We propose GLR-MM, a Graph-Based Global-Local Reconstruction framework for early ICU mortality prediction. It maps five CXR-EHR modalities to a shared space, reconstructs missing embeddings through complementary local cross-modal and global graph-attention branches, adaptively fuses their estimates, and optimizes class-balanced prediction, reconstruction, and contrastive objectives. On 9,620 MIMIC-derived ICU stays, we evaluate 10%, 30%, and 50% random modality missingness with shared deterministic masks. MUSE performs better under mild and moderate missingness, whereas GLR-MM achieves higher AUROC and AUPRC at 50% by 0.0088 and 0.0249, respectively. These results indicate that graph-guided reconstruction is most useful when inputs are severely incomplete. --- ### VISTA: An Attention-Based Multi-Agent Reinforcement Learning Architecture for Space Situational Awareness Sensor Tasking Authors: Miguel Leiva-Vélez, Adalberto Claudio Quiros, Nicolas Gaston Rozado, Hodei Urrutxua, Víctor Rodríguez-Fernández Published: 2026-09-20 Categories: cs.LG, cs.AI, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2609.23875v1 The rapid growth of resident space objects is increasing the complexity of space situational awareness sensor tasking, challenging classical optimization methods as they allocate finite, heterogeneous, and distributed sensing resources across ever-larger catalogues. Existing deep reinforcement learning approaches show promise in reduced settings, but fixed-dimensional state and action representations limit their ability to scale to large, dynamic catalogues and distributed sensing networks. We introduce VISTA (Variable-Entity Intelligent Sensor Tasking Architecture), a scalable deep reinforcement learning architecture for persistent uncertainty-driven catalogue maintenance across variable object populations and sensor configurations. VISTA combines physics- and mission-informed top-K retrieval with entity-centric attention, recurrent memory, and pointer-based action decoding, thereby keeping each agent's observation and action spaces independent of catalogue size. We evaluate VISTA across different scenarios, from fixed-size single-sensor benchmarks to large-scale space-based tasking and heterogeneous cooperative sensing. With 30 orbiting targets, VISTA recovers the catalogue 31.2% faster than the fixed-dimensional recurrent baseline. In the large-scale regime, VISTA reduces five-hour uncertainty by 97.5% relative to the strongest classical reference and by 99.3% relative to the recurrent learner. Zero-shot tests up to 20,000 objects reveal near-linear relations between sensing capacity, catalogue size, and recovery horizon. Learned policies also exhibit sensor modality adaptation and generalization to population and initial-uncertainty shifts. Together, these results demonstrate that VISTA provides a scalable framework for adaptive space situational awareness sensor tasking across large, distributed networks of heterogeneous ground- and space-based sensors. --- ### Pretraining of Medical Visual Encoders Toward Multi-modal Large Language Models Authors: Tianyou Jiang Published: 2026-09-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.23860v1 Multimodal Large Language Models (MLLMs) commonly reuse visual encoders pretrained with CLIP, although the features of these ViTs are ultimately consumed by autoregressive LLMs. We refer to this mismatch as the semantic-interface gap and introduce MedMLIP, a framework that pretrains the visual encoder through report generation with a frozen LLM, while employing Local Relational Distillation (LRD) to preserve relationships among visual patches to avoid visual collapse. We pretrain MedMLIP on IU-Xray and Open-PMC-300K and evaluate the resulting encoders on VQA-RAD and SLAKE. Only the ViT is transferred, while the guiding LLM and projector are replaced, allowing us to assess cross-LLM transferability. Our cross-LLM transfer experiments demonstrate the value of pretraining visual encoders for their autoregressive LLM interface while trying to preserve more fine-grained visual information. Code and the pretrained model are available at https://github.com/SkyCol/MedMLIP --- ### From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters Authors: Camilla Andreozzi, Phuong-Anh Nguyen-Le, Zhijing Jin, Revati Mani Published: 2026-09-20 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.23853v1 Disaster-risk-reduction archives describe hazard events in prose that databases such as EM-DAT (Delforge et al., 2025) cannot ingest directly. We present an LLM pipeline that generates candidate georeferenced event records using a controlled hazard vocabulary and fixed schema, retaining evidence for review. Applied to 10,000 documents from PreventionWeb, the knowledge hub managed by UNDRR, it produced 3,572 records from 1,913 documents across 24 hazard types and resolved 81% of location mentions to OpenStreetMap geometries. On 171 human-positive document windows from a stratified 217-document reference set, GPT-5 achieved 86.0% pooled attribute $F_1$, versus 44.2% for the spaCy-gazetteer baseline. Evaluation pools hazard families, location strings, and event years within documents, without assessing their assignment to individual events. GPT-5.4 ranked highest among ten LLMs (86.6% $F_1$). Verbatim evidence occurrence was 72.0% for GPT-5 and 47.2% for GPT-5.4, measuring textual traceability without establishing attribute support. We report production failure modes and automated label and location-rule compliance checks. Prompts, schema, and outputs will be released for adaptation to national reporting archives. --- ### PROSE: A Theory of Optimal Stopping with Perishable Evidence for Peer Selection in Intermittently Connected Decentralised Learning Authors: Christos Anagnostopoulos Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23845v1 Decentralised federated learning removes the aggregation server but makes collaboration dependent on transient peer availability. In mobile and intermittently connected systems, evaluating a promising peer consumes contact time and may cause the exchange opportunity itself to vanish, so that the evidence a learner gathers about a peer is perishable: it decays because links expire and because peer models drift while old measurements age. This paper develops a self-contained theory of optimal stopping for the resulting peer-selection problem. We formalise a receiver's within-contact decision as a finite-horizon Markov optimal-stopping problem with costly information acquisition and a future-arrival outside option, and prove that it admits an optimal policy characterised by a reservation value (Snell-envelope structure). Around this formulation we prove: (i) stage-uniform, drift-aware concentration and a maximin certification rule that is correct with high probability together with a finite-sample identification bound; (ii) a mobility-aware value of-information stopping rule and comparative statics showing that higher link hazard lowers the value of continued probing and enlarges the stopping region; (iii) a closed-form value of waiting under marked-Poisson contact arrivals, together with a search-theoretic reservation value whose comparative statics we characterise; and (iv) a myopic-optimality theorem establishing that, in sufficiently volatile (monotone) mobility regimes, the one-step confidence-safe rule is a sound surrogate for the optimal policy and never stops prematurely. We instantiate the theory as PROSE (Perishable-evidence Reservation-value Optimal Stopping for Exchange), a lightweight, fully local policy, and delineate the static contact and drift-free limits in which classical sequential decision problems are recovered. The development is entirely analytical. --- ### Adaptive Determinantal Client Scheduling in Federated Learning Authors: Wen Xu, Ben Liang, Gary Boudreau, Hamza Sokun Published: 2026-09-20 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2609.23843v1 Scheduling clients for model training is critical in federated learning due to both data and system heterogeneity. Most previous works focus on the quality of the scheduled clients to achieve faster convergence, shorter wall-clock convergence time, or better average model performance. They rarely consider the diversity of clients, which is important to counter heterogeneity and improve performance for the worst-off clients. In this work, we advocate the use of determinantal point processes (DPPs) to model and enhance the diversity in client scheduling. We first design the kernel matrices of DPPs using gradient information and quality scores, which inherently enables a flexible quality-diversity trade-off. Applying fast MAP inference over DPPs, we propose Adaptive Determinantal Client Scheduling (ADCS) in FL. We further quantify the gradient approximation error of ADCS and develop convergence analysis for general biased client selection in FL with non-convex loss functions. We conduct comparative numerical experiments showing that ADCS outperforms state-of-the-art client scheduling algorithms, including both quality-based and diversity-based ones. --- ### From Regional to Global: Transfer Learning for Atmospheric Transport Emulators Authors: Jeff Clark, Elena Fillola, Nawid Keshtmand, Raul Santos-Rodriguez, Matthew Rigby Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23838v1 Greenhouse gas emissions estimates can be derived using inverse methods by combining atmospheric concentration observations with chemical transport models. The latter traditionally use physics-driven simulators such as Lagrangian Particle Dispersion Models (LPDMs), which are expensive to run and do not scale well to modern satellites' high resolution data. Previously we developed a performant atmospheric transport emulator that approximates LPDM outputs ("footprints") over South America ~1,000X faster than the UK Met Office's LPDM. Expanding towards global emulation is not straightforward, as atmospheric transport is regionally heterogeneous. This paper evaluates spatial transferability capabilities of models across four world regions: South America, East Asia, South Asia, North Africa using both region-specific and multi-region models, and leave-one-region-out experiments. Regional differences are characterised in the context of input variable and output footprint distributions. This work builds intuition in cross-region generalisation and transfer learning, aiding regional performance towards efficient global emissions estimates. --- ### The Exponential Price of Determinism in Nonsmooth Nonconvex Optimization Authors: Guy Kornowski Published: 2026-09-20 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2609.23837v1 We study the complexity of finding $(δ,ε)$-Goldstein stationary points of nonsmooth nonconvex Lipschitz functions. By now, it is known that randomized first-order algorithms can solve this task with a dimension-free oracle complexity (Zhang et al., 2020), whereas deterministic algorithms cannot, as their complexity must scale at least linearly with the dimension $d$ (Jordan et al., 2023, Tian and So, 2024). This leaves open whether deterministic algorithms can nevertheless solve the problem with oracle complexity polynomial in $d$. We answer this question negatively by proving a lower bound of order $(1/ε)^{Ω(d)}$ for deterministic algorithm, closing the exponential gap between the previously known lower and upper bounds and resolving an open problem posed by Jordan et al. (2023). We further discuss several extensions and implications of this result to weaker stationarity notions, finding a descent direction and deterministic smoothing. Overall, our results establish an exponential computational advantage in nonsmooth nonconvex optimization offered by randomization. --- ### Actionable Insights from Observational Data: The Case of Advanced Classes in K-12 Education Authors: Nabit Bajwa, Seth B. Hunter, Sanmay Das Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23836v1 A fundamentally challenging question in K-12 education is about the effects of taking more advanced or challenging classes. It is particularly complex because students (and/or their parents) choose whether to enroll in these classes, making causal analysis challenging. In this paper, we begin to tackle this question by taking advantage of a novel dataset from a public school system in the US. This dataset records students' course enrollment decisions, prior academic histories, demographics, and subsequent outcomes around the time of a district-wide change that introduced optional open-enrollment advanced middle-school courses in subject areas. This is a rich observational dataset, but enrollment in advanced classes is driven by student characteristics and choices rather than random assignment. This creates a core identification challenge: the same factors that influence enrollment in advanced courses are also predictive of academic outcomes. As a result, simple comparisons between enrolled and non-enrolled students are confounded, and naive estimates may reflect underlying differences in student ability, motivation, or support rather than the impact of coursework itself. Our analysis shows that enrolling in advanced English courses has a net positive but modest effect on student achievement outcomes. However, these benefits are unevenly distributed: some students with relatively large predicted gains ("middle achievers" in prior years) are less likely to enroll than others. Some other groups (e.g. Black students and those with lower socio-economic status) also demonstrate significantly lower propensity to enroll. This gap between predicted benefit and observed enrollment illustrates how careful data analysis can extract actionable insights from large observational datasets, including identifying students who appear well-positioned to benefit but do not select into advanced options. --- ### Comparative Performance and Parameter-Efficient Adaptation of DINOv2 for Active Trachoma Classification Authors: Kibrom Gebremedhin, Hadush Hailu, Bruk Gebregziabher, Yordanos Hailu Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23832v1 Automated grading of conjunctival photographs could reduce the cost and variability of trachoma prevalence surveys, but the relative value of modern pretrained visual representations, lightweight feature adaptation, and training-objective design has not been established under a common protocol. This study presents a controlled evaluation for binary classification of Trachomatous Inflammation-Follicular (TF) versus Normal using 1,546 images from the public UCSF/Lietman collection. Images are processed using the OPTED pipeline for zero-shot tarsal-conjunctiva segmentation, alignment, cropping, and standardization. We first compare six pretrained backbones using a common classification pipeline and then evaluate four lightweight adaptation mechanisms on DINOv2 ViT-B/14. Under stratified five-fold cross-validation, DINOv2 with Efficient Channel Attention (ECA) and focal-plus-center loss achieved 91.66 +/- 0.97% accuracy, 90.69 +/- 1.10% macro-F1, and 96.06 +/- 0.71% AUC. ECA introduces only five learnable parameters while matching the performance of substantially larger alternatives. Objective ablation further showed that ECA did not consistently improve plain DINOv2 across loss functions; the lowest-variance 91.66% accuracy was obtained with cross-entropy plus center loss. Overall, the fine-tuned DINOv2 representation provided most of the predictive performance, while ECA offered a highly parameter-efficient refinement whose effect depended on the training objective. The resulting workflow provides a reproducible benchmark for active trachoma image classification. --- ### DFD-Lab: A Modular Audio-Visual Deepfake Detection Pipeline Authors: Jan Rybarczyk, Mateusz Roszkowski, Jacek Komorowski Published: 2026-09-20 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2609.23830v1 Comparing audio-visual deepfake detectors requires coordinating dataset adaptation, temporal input representation, model interfaces and experimental conditions. We present DFD-Lab, a modular pipeline that separates these responsibilities while supporting shared training and evaluation workflows. We integrate three implementations: Xception-based maximum-logit fusion, ResNet with temporal LSTM fusion, and our AVFF reimplementation. Experiments cover external testing, degradation-based training augmentation and evaluation-time corruption. On a filtered subset of Deepfake-Eval-2024, models trained on FakeAVCeleb attain baseline AUROC values of 0.504, 0.538 and 0.458. JPEG50 training augmentation raises these to 0.691, 0.605 and 0.570, respectively, while all three accuracies decrease. These results illustrate why training interventions, evaluation corruptions and metric-dependent outcomes should remain distinct within a common pipeline. The contribution is the integration of audio-visual processing, interchangeable detectors and configurable experimental workflows, supported by empirical case studies. The findings highlight the challenge of cross-dataset detection and the complementary information provided by ranking and classification metrics. --- ### A Physics-Conditioned Neural Operator for Generalization of Atrioventricular Valve Mechanics across Pressure and Tissue Properties Authors: Shawn Koohy, Wensi Wu, Matthew A Jolley, Paris Perdikaris Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23826v2 Mitral and tricuspid regurgitation are the most common regurgitant valvular lesions, yet only a minority of severe cases undergo corrective surgery. Rapid assessment of valve mechanics could enable earlier, more precise intervention, but finite element (FE) analysis is slow to repeat across the many loading and tissue-property values of interest, which for a given valve are not known in advance. We introduce the Physics-Conditioned Neural Operator (PCNO), a transformer-based neural operator predicting leaflet displacement, strain, and stress fields conditioned on systolic blood pressure and tissue properties. PCNO is trained on, and evaluated against, FEBio simulations of functional and regurgitant mitral and tricuspid valves and of three mitral pathologies. With pressure and all material parameters simultaneously outside the training support, displacement error against FE reaches 4.48% and the mean errors of unsupervised geometric measures of valve function stay within 3.5%, indicating a conditioned solution operator over parameter space rather than an interpolator of the training set. Under this shift, PCNO is also more accurate than graph neural network and graph neural operator baselines trained on the same simulations, with the largest margins in stress. --- ### Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking Authors: Jordi Luque, Aleix Sant, Fernando López Published: 2026-09-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.23825v1 We present a comprehensive benchmark of Federated Learning (FL) for multilingual Automatic Speech Recognition (ASR), evaluating four Speech-LLM architectures on the Multilingual LibriSpeech dataset. We compare FedAvg and FedProx across frozen and unfrozen encoder configurations, demonstrating that optimized learning rates are critical for performance. Specifically, independently tuning the learning rates for the speech encoder, connector, and decoder yields the lowest error rates, with full three-component adaptation (LoRA for encoder and decoder, full training for the connector) producing the best FL results. We observe that FedProx efficacy is architecture-dependent, providing notable advantages in multilingual pre-trained architectures (e.g., EuroLLM over TinyLlama when keeping the encoder fixed); this indicates that LLM backbone capacity plays a key role in mediating resilience to heterogeneous data distributions. These findings offer concrete design guidance for deploying multilingual Speech-LLMs in privacy-sensitive, distributed environments. --- ### On Generalized Naive Bayes with Continuous Features Authors: Ábrahám Papp, Botond Szilágyi, Edith Alice Kovács Published: 2026-09-20 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.23819v1 The Generalized Naive Bayes (GNB) model was introduced for discrete and categorical random variables as an extension of classic Naive Bayes. We now accommodate the GNB framework to continuous explanatory variables. A central result of the paper is that structure learning of the GNB depends only on the pair copulas of the bi-variate marginals. We proved that the GNB structure can be assigned to the basis of a matroid, therefore we give greedy algorithms for finding the optimal GNB structure on the training data, in sense of minimizing Kullback-Leibler divergence. Three cases are considered: joint Gaussian distribution, then a more flexible model where we suppose the dependence structure to be described by a Gaussian copula with arbitrary marginals, and an even more flexible case where the joint continuous probability distribution is arbitrary, i.e. copula and marginal distributions are arbitrary. A method for model reduction, based on the newly introduced concept of GNB forest is given. We close the paper by comparing the newly introduced GNB classification results to other classical "glass-box" algorithms on real datasets. --- ### VISTA: Video-Injected Stylized Text-to-Animation Authors: Monseej Purkayastha, Anindita Ghosh, Philipp Slusallek Published: 2026-09-20 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.23817v2 We present VISTA, a two-stage framework for generating stylized 3D human motion by fusing structural content from text prompts with expressive style from reference videos, without requiring jointly paired (text, video, stylized motion) triplets. A Dual-channel Autoencoder first maps motion sequences and video clips into a shared latent manifold. A masked autoregressive diffusion backbone then operates within this manifold, injecting video-derived style through a dedicated late-fusion Dual-AdaLN pathway while preserving text-conditioned content structure. A cross-batch unpaired training protocol with latent cycle consistency enables joint learning across separate semantically rich and stylistically diverse datasets. As a proof-of-concept for controllable animation synthesis, we validate VISTA on rendered motion-capture references: it achieves the highest style recognition accuracy among video-conditioned methods while preserving competitive content alignment, and its decomposed 3-way classifier-free guidance provides independent, user-controllable calibration of the content-style balance at inference time. --- ### Confidence-Aware Teacher-Student Distillation for 3D Medical Segmentation Authors: Georgios Triantafyllou, Dimitris K. Iakovidis Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23815v1 Medical image segmentation models typically rely on large amounts of densely annotated volumetric data, limiting their scalability across tasks and imaging modalities. This work addresses the challenge of predicting entire 3D anatomical structures from extreme annotation sparsity. An annotation-efficient student-teacher framework is proposed for automatic 3D medical segmentation that requires only a set of point prompts on a single 2D slice per volume, as input. A foundation model serves as an offline teacher, utilizing the provided point prompts from the selected slice to full-volume pseudo-annotations alongside their corresponding spatial confidence scores prior to student training. To mitigate the error propagation of noisy pseudo-annotations, a task-specific 3D student network is trained using a confidence-aware optimization strategy. By leveraging the teacher's pre-computed confidence scores, this strategy explicitly excludes statically uncertain regions of the pseudo-annotations from the loss calculation, while simultaneously emphasizing regions with higher confidence. Evaluated on 3D cardiac MRI datasets, our framework outperforms state-of-the-art semi-supervised methods, improving segmentation performance by up to 43.6%. Furthermore, it drastically reduces the manual annotation burden to just a few positive point prompts per volume, while improving surface boundary precision by up to 14.7% over the teacher and successfully recovering up to 34.1% of the performance gap toward the fully supervised upper bound. --- ### Iterative Atom Refinement: A Monotonicity Principle for Dictionary Learning Authors: Alexander Christie, Miguel Moscoso, Alexei Novikov, George Papanicolaou, Chrysoula Tsogka Published: 2026-09-20 Categories: cs.LG, math.PR, stat.ML arXiv: https://arxiv.org/abs/2609.23812v1 Dictionary learning seeks to recover an unknown dictionary $A$ from observations ${\bf y}_i = A{\bf x}_i$ with sparse coefficient vectors ${\bf x}_i$. We introduce the \emph{Iterative Atom Refinement} (IAR) algorithm, a simple procedure for recovering individual dictionary atoms. Starting from a random direction, IAR repeatedly selects the observations most strongly correlated with the current iterate and updates the direction by averaging the selected data. Our main contribution is a rigorous convergence theory of IAR. Using high-dimensional probabilistic estimates and a novel monotonicity principle for atom-selection probabilities, we show that a small initial advantage of one atom is amplified until that atom is isolated. Under our model assumptions, IAR identifies a generating atom after only three refinement steps. Numerical experiments support the theory and show that the resulting dynamics accurately capture the behavior observed in dictionary refinement. --- ### FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model Authors: Jingxuan Xu, Gang Wu, Yanan Wu, Yutao Mou, Songwei Yu, Tianzhuang He, Zhengshuo Gong, Zhao Liu, Zihang Xu, Wenqiang Zhu, Xinping Lei, Weihao Li et al. Published: 2026-09-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.23808v1 While test-time scaling enhances Large Language Model (LLM) agents in long-horizon software engineering (SWE), sparse binary rewards (Pass/Fail) create a severe credit assignment crisis and waste failed exploratory trajectories. Current trajectory optimization and scaling methods are costly and structurally limited, relying on heuristic state reuse without causal diagnosis or delayed scalar scoring without actionable online guidance. We propose FLARE (Full-Lifecycle Alignment and Reward Engine), a novel dense supervision paradigm driven by a lightweight Generative Reward Model (GRM). First, RADAR, an offline causal-aware diagnostic framework, extracts high-fidelity, hindsight-free supervision through causal-chain backtracking to distill a GRM providing real-time, step-level risk feedback. Second, FLARE uses this GRM to continuously optimize the agent across its entire lifecycle. During inference, FLARE acts as an Active Scaffold, autonomously intercepting high-risk generation steps for localized breakpoint re-execution, drastically reducing compute overhead. During post-training, the GRM's structured signals serve as process-supervised reranking scores for Supervised Fine-Tuning (SFT) and step-level dense rewards for Reinforcement Learning (RL), mitigating policy collapse in sparse environments. Extensive evaluations show that FLARE establishes a new Pareto frontier across the agent lifecycle: FLARE (N=1) outperforms Global Rollout (N=5) with a 5x reduction in token consumption. Extending FLARE to training overcomes the sparse reward problem in long-horizon interactive tasks, delivering relative performance gains of 19.13% in SFT through process-aware data curation and a consistent 9.19% improvement in RL. --- ### WorkWorlds: An Infrastructure for Evaluating AI Agents on Workplace Tasks Authors: Yining Hua, Levi Lian Published: 2026-09-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.23806v2 Many knowledge-work benchmarks are constructed around individual tasks, with the context needed for each task selected together with or after the task has been specified. This design measures performance on workplace-like tasks in an environment assembled for the task. When task specification guides which context is selected, the evaluation can encode task information into the environment and pre-complete part of the information-localization work that workplace performance normally requires. We introduce WorkWorlds, an evaluation infrastructure that separates organizational state from task specification. A world first fixes a revision, date, and employee seat and materializes the organizational state that employee can access; tasks are introduced only afterward. We implement WorkWorlds in a primary synthetic pharmaceutical company with 8 measured tasks across 6 employee seats, and construct additional organizational worlds. Across 192 matched evaluations, task-level curation increased evidence access by 17.6 percentage points, from 72.8% to 90.4%, and criterion pass by 8.7 points, from 68.0% to 76.7%, while pass conditional on evidence access remained nearly unchanged; most of the measured difference occurred before the agent reached sufficient evidence. --- ### MoSAT: Human Motion Generation from Spatial Audio and Textual Description Authors: Shuyang Xu, Zhiyang Dou, Yiduo Hao, Zekun Li, Liang Pan, Jingbo Wang, Cheng Lin, Yuan Liu, Wenping Wang, Mingmin Zhao, Taku Komura Published: 2026-09-20 Categories: cs.GR, cs.CV, cs.RO, cs.SD arXiv: https://arxiv.org/abs/2609.23797v1 Human motion is shaped by both external acoustic events and behavioral intent: spatial audio conveys environmental cues that elicit or guide a response, while text specifies the desired action and how it should be performed. In this paper, we study the novel task of human motion synthesis jointly conditioned on spatial audio and natural language, a problem that has been largely overlooked in previous research. To support this task, We introduce STAM, a dataset of motion sequences paired with spatial audio and detailed textual annotations whose rich vocabulary affords precise and nuanced specification of human motions. We further introduce MoSAT, a latent flow-matching framework for full-body motion generation jointly conditioned on natural-language intent and directional spatial-audio cues through hierarchical cross-attention before generating motion. Such a hierarchical design enhances temporally coherent and semantically aligned motion sequences. We also develop tri-modal evaluators for comprehensive evaluation on this novel task. Extensive experiments show that MoSAT achieves the SOTA performance by leveraging spatial audio's intrinsic motion-shaping properties alongside textual semantics, enabling precise and diverse motion in various scenarios. --- ### Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction Authors: Yang-Tian Sun, Tianjia Liu, Zehuan Huang, Yi-Hua Huang, Xiaoyang Lyu, Ziyi Yang, Zi-Xin Zou, Yuan-Chen Guo, Yan-Pei Cao, Xiaojuan Qi Published: 2026-09-20 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.23796v2 Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challenge. A central difficulty lies in how object layout is represented. Holistic methods absorb placement into a scene-level generation process, sacrificing object-level detail. Compositional methods preserve object fidelity by decoupling geometry from layout, but typically parameterize layout as sparse, unbounded pose variables that are difficult to learn and generalize poorly under scarce scene-level supervision. We present Mira-Scene, a compositional 3D scene reconstruction framework that replaces sparse pose regression with dense, bounded correspondence recovery. At its core is the Canonical Coordinate Map (CCM), a pixel-aligned field that maps each visible object pixel to a surface coordinate in the object's bounded canonical space. When paired with a scene-space Point Cloud Map (PCM) from monocular geometry estimation, CCM induces dense canonical-to-scene correspondences from which object transformations are recovered through robust geometric alignment. Because CCM operates in bounded canonical space, it provides a stable prediction target that can be trained from scalable object-level 3D data without requiring scene-level layout annotations. Mira-Scene further introduces a multimodal diffusion transformer that jointly generates object geometry and CCMs, using modality-specific expert streams with shared attention and positional encoding to promote geometry-layout consistency. Experiments on indoor, outdoor, synthetic, and in-the-wild scenes show that Mira-Scene substantially outperforms strong baselines in layout accuracy, achieving relative gains of 39.8% in 3D-IoU and 16.5% in 2D-IoU over SAM3D, using limited open-source training data. --- ### Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows Authors: Vivek Kumar Singh, Preeti Priyam, Gautam Bhowmick Published: 2026-09-20 Categories: cs.AI, cs.MA, cs.PF arXiv: https://arxiv.org/abs/2609.23790v1 Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected tokens are billed as input tokens at the same per-token price as the system prompt and the user query. Production observability tools report total token cost but do not separate the tokens a node generates from the tokens it is handed, so this component of the bill is invisible to the teams paying it. We introduce the Total Cost of Agency (TCA), a decomposition of multi-agent workflow cost into base prompt, inference, memory injection, miss penalty and context-accumulation components, and an exact attribution method: a two-pass, non-billable token count that measures injected tokens directly rather than estimating them from word-count proxies. On a 200-task enterprise benchmark executed against real model APIs, memory injection accounts for 13.6 percent of the variable cost a compile-time optimizer can act on, about 12 percent of the full billed cost, and its share rises from a structural zero at workflow depth one to 27.6 percent at depth six. Injected tokens grow linearly with depth over the measured range (R^2 = 0.9974, depths two through six); a quadratic fit yields a negative leading coefficient, so the data do not exhibit convex growth at these depths. We show the component is controllable at fixed model tier: reducing the retrieval window capacity from 32 to 2 entries lowers injected tokens by 28.7 percent with an accuracy change within seed-level variation. We report in full that our graph-rewriting transforms are approximately cost-neutral in isolation, that two of the five decomposition terms are zero by construction in this harness, and that total workflow cost is dominated by model tier assignment, which we hold fixed and treat as prior work. Prompt caching is not evaluated; all figures are for the uncached case. --- ### Belted Engression: Sufficient Dimension Reduction for Generative Distributional Regression Authors: Wenxi Tan, Bing Li, Lingzhou Xue Published: 2026-09-20 Categories: cs.LG, cs.AI, math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.23789v1 Modern conditional generative models face significant challenges when learning complex covariate dependencies. While sufficient dimension reduction (SDR) provides a principled approach to compress these dependencies, traditional SDR frameworks were not formulated for conditional generation. To bridge this gap, we propose Belted Engression, a unified and architecturally parameter-efficient framework for generative distributional regression. Our approach establishes an end-to-end compress-then-generate paradigm driven by sufficient representation learning, embedding a structural bottleneck into the generative architecture. Theoretically, we prove that the standard SDR condition is equivalent to a law-preserving generative factorization, which is achieved at the global optimum of the population Belted Engression objective. Furthermore, by uncovering a localized Bernstein-type control for the energy-score loss, we establish finite-sample convergence rates that are sharper than those of existing results. We also prove that this belted architecture is strictly smaller, operating with an asymptotically vanishing parameter count relative to the unstructured baseline. Extensive simulations and real-world applications demonstrate that Belted Engression achieves superior distributional prediction and SDR recovery with fewer trainable parameters. --- ### Falling Trees: A Model Class for Interpretable Risk Prioritization Authors: Varun Babbar, Zachery Boner, Margo Seltzer, Cynthia Rudin Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23780v1 Many real-world decisions require prioritizing high-risk cases, such as clinicians prioritizing high-risk patients before lower-risk ones. Falling rule lists (FRLs), which are ordered if--then rules with monotonically decreasing risks, provide an interpretable framework for such tasks; however, their single-path structure yields a highly restricted model class. We introduce falling trees, a new family of interpretable models that enforces the same monotonic risk constraint while permitting tree-structured branching. We present GRAVITree, a novel dynamic-programming-with-bounds algorithm for learning the Rashomon set of falling trees under depth and branching constraints. Our formulation can interpolate between rule lists and full decision trees, enabling user-desired model expressivity. In a new clinical dataset and in many public classification benchmarks, falling trees match or outperform FRLs and other interpretable baselines, often producing more sparse decisions for high-risk instances. Our results show that falling trees strike a practical balance between interpretability, expressiveness, and risk prioritization for high-stakes settings. --- ### Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning Authors: Suman Banerjee, Hiroyasu Tsukamoto Published: 2026-09-20 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.23775v1 Obtaining the optimal action-value function in Markov decision processes is computationally intensive in large state--action spaces. In this study, we present statistically rigorous convergence results for a robust reinforcement learning algorithm warm-started by a transformer-based action-value function prediction, where natural language prompts encode task specifications. Our framework adopts the R-contamination model to characterize uncertainty in the state transition kernel, and employs conformal prediction to certify convergence via trajectory-level nonconformity scores constructed from the contracting Bellman residual. The resulting conformal quantile bounds the gap between the running and optimal action-value functions simultaneously over all iterations, thereby yielding a pre-certified stopping rule that requires little knowledge of the true transition kernel. Numerical case studies on perturbed maze environments of varying size and contamination level confirm that the transformer-based warm start measurably reduces the initial error and accelerates convergence, while the proposed conformal bounds track the true error trajectory more tightly than existing guarantees. --- ### On Probabilistic Inference Through Parametric Tensor Decomposition in Base Tensor Networks Authors: Sagad Hamid, Tanya Braun Published: 2026-09-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.23774v1 Probabilistic inference is generally only tractable in low-treewidth graphical models, limiting its effective applicability in high-treewidth settings. Many existing methods improve efficiency by exploiting specific parametric structure, such as symmetries. However, they typically require such structure to be explicitly present, limiting their applicability to a broader range of graphical models. To address this limitation, we propose a framework where tractable inference is controlled by latent parametric structure exploitation, rather than requiring it to be explicitly present a priori. Our approach first reparameterises a graphical model as a specific tensor network representation, which we call a base tensor network. This representation yields two key properties that allow inference tractability to be controlled by parametric structure: 1) First, the complexity of inference is mainly determined by the parametric structure of a single tensor, called the base tensor. We characterise several tractable classes of base tensors for which the entire base tensor network can be contracted efficiently. 2) Second, decomposing the base tensor yields again a collection of base tensor networks. This allows inference to be naturally reduced to decomposing the base tensor into tractable components with sufficient parametric structure. We call this procedure parametric tensor decomposition. By exploiting parametric structure within the base tensor, our framework enables a novel view on inference beyond settings where such structure is explicitly present. --- ### SAGE: Optimal-Stopping Peer Selection for Decentralised Federated Learning Authors: Ke Xiao, Qiyuan Wang, Christos Anagnostopoulos Published: 2026-09-20 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.23773v1 Decentralised federated learning replaces server aggregation with peer-to-peer model exchange, making collaborator selection a local decision under uncertainty. Fixed probe budgets waste effort on easy choices yet fall short when peers are hard to distinguish. We propose SAGE (Sequential Anchor-Gated Exchange), an optimal-stopping peer selector under a one-model-bearing-exchange budget. A receiver scores candidate neighbours on receiver-owned anchor evidence and selects once an advantage is certified. It continues probing only while further evidence repays its cost, and otherwise falls back to random gossip. We show that the stopping problem admits an optimal rule attained at a finite stage, and that the anchor schedule is order-optimal in the peer-risk gap and the confidence level. We further show that the selector never returns a peer worse than random gossip with high probability, and prove that no such guarantee holds for selectors that commit without a certificate. A separability threshold follows, below which no probing budget improves on gossip. Experiments span two image benchmarks, two graph families and three heterogeneity levels. Selectors that always act on their evidence lose to gossip in every configuration tested. SAGE-OS matches gossip on 75.5% less evidence than a fixed budget, at half the communication overhead of two published selectors. The operative decision is not which peer to rank first, but whether the evidence justifies ranking at all. --- ### PRISM-RAG: Multimodal Hypergraph Retrieval-Augmented Generation for Tobacco Product and Legislative Policy Reasoning Authors: Manuel Serna-Aguilera, Raegan Anderes, Page Dobbs, Khoa Luu Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23769v1 The disambiguation of semantically similar statutory text across jurisdictions is a retrieval problem that existing methods do not solve. This inter-context conflict can steer generative models toward confidently produced answers grounded in topically relevant but jurisdictionally incorrect sources. Tobacco and nicotine regulations vary by US jurisdiction, often sharing similar language, thus, robust reasoning requires identifying which jurisdiction's law governs a given product, not merely retrieving relevant text. Emerging products (e.g., pouches) exploit ambiguous definitions to evade regulation. State-of-the-art (SOTA) document retrieval-augmented generation (RAG) methods struggle to address this inter-context conflict, and thus struggle to connect image attributes (e.g., rich attribute captions) to the set of similar legislation texts. We introduce NicoPRISM (Nicotine Product and Regulation Image-and-Text Surveillance Multimodal), comprising 161,563 images, attribute captions, a knowledge base of product, health, and legislative documents spanning 13 US jurisdictions, and 1,495 validated question-answer pairs across two tasks: policy compliance QA and product knowledge QA. We also propose PRISM-RAG, a multimodal hypergraph RAG framework built over images, captions, and entities without any LLM calls at index time, grounding every query in a product image and routes retrieval through a jurisdiction-aware context assembly mechanism guaranteeing that statutory text from the queried jurisdiction reaches the language model by construction. PRISM-RAG retrieves passages from the correct jurisdiction in 93.9% of policy compliance queries, a 48.6 percentage point advantage over standard RAG (p<0.001), using zero LLM calls at index time and one at query time, and is competitive with or outperforms SOTA RAG frameworks across keyword, semantic, jurisdiction-, and compliance-accuracy metrics. --- ### TriFleetRCA: On-Premise LLM Root Cause Analysis for Kubernetes Authors: Rohit Patel, Susil Kumar Mohanty, Jeenal Chaudhary Published: 2026-09-20 Categories: cs.CR, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.23766v1 Root cause analysis at a remote site is slow: evidence is scattered across pod logs, Kubernetes events and cluster-level objects, and many operators cannot send production logs to a hosted model at all. On-premise inference removes the second constraint but raises a question live-cluster benchmarks have not addressed: when one workstation GPU fixes both the model and the context budget, how should evidence be retrieved, and what happens when the runbooks the model consults have been tampered with? We present TriFleetRCA, a pipeline running entirely on one on-premise GPU that collects evidence at one of three scopes (pod, namespace, cluster), ranks it by template de-duplication then BM25, filters runbooks through an ingest guard, and returns a root cause with the evidence lines supporting it. We evaluate on a live Kubernetes cluster into which we inject four faults, so ground truth is known by construction, across 100 analyses with Qwen2.5-14B-Instruct at temperature 0. The hit rate was 0.85, 0.90 and 0.95 at pod, namespace and cluster scope; intervals overlap, but the whole scope effect comes from the one fault whose cause is a cluster-level object, and cluster scope costs 55% more tokens. De-duplication before ranking raised the hit rate from 0.75 to 0.90 at equal token cost. A poisoned runbook telling the model to delete the namespace was rejected by the guard every run; with the guard disabled the model declined to follow it in all 20 analyses, making the guard defence in depth rather than the sole barrier. Separating citation quality from accuracy proved informative: one fault was diagnosed correctly and cited incorrectly every trial, a failure mode accuracy conceals. Median latency was 1.6 s at 2,200 prompt tokens. We release the pipeline, the fault injector and all records. --- ### GenVoid: Uncertainty-Aware Learning of Subsurface Material Defects with an Experimentally Validated Physics-Informed Generative Model Authors: Trishit Mondal, Prajwal Bharadwaj, Nikhil Karanjgaokar, Ameya D. Jagtap Published: 2026-09-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23761v1 Internal voids are ubiquitous defects in manufactured structures, yet their characterization remains challenging because their geometry is hidden and can only be inferred indirectly from accessible measurements. Here we introduce \textit{GenVoid}, a physics-informed generative model-based framework for identifying internal voids in complex two- and three-dimensional solids from surface displacement measurements alone. By incorporating the governing mechanics into a generative inference framework, \textit{GenVoid} enables void identification across linear elastic, hyperelastic and plastic material behaviours and accommodates complex two- and three-dimensional structural geometries. Importantly, the framework explicitly accounts for uncertainty and noise in displacement measurements, producing probabilistic reconstructions of internal void geometry rather than a single deterministic estimate. We demonstrate the approach using high-fidelity synthetic datasets and experimentally measured displacement fields obtained from in-situ mechanical experiments, establishing its ability to infer hidden voids from realistic displacement measurements. To quantify the fundamental limits of such inference, we further introduce an observability measure that characterizes the sensitivity of boundary measurements to localized stiffness perturbations within the interior under an ensemble of applied loads. This framework provides a direct connection between defect location, sensor configuration and reconstruction fidelity, enabling systematic assessment of how the number and spatial distribution of boundary measurements govern void-identification accuracy. To this end, these results establish a physics-informed and uncertainty-aware approach for non-invasive characterization of hidden defects and provide a quantitative basis for designing measurement strategies for inverse problems in solid mechanics. --- ### Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classification Authors: Fahim Rahman, S. M. Tanjeeb Meheran Rohan, Md. Taimum Ibne Sayed, Asaduzzaman Herok, Md. Bakhtiar Hasan Published: 2026-09-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23758v1 Few-shot recognition with frozen visual features is especially fragile under domain shift and one-shot supervision, where a single labelled image is an unreliable estimate of its class. We ask how far this fragility can be reduced purely at test time, without retraining the encoder or augmenting the source domain. We present Spectral Transductive Refinement (STR), a training-free transductive inference rule that exploits the geometry of the complete support-query episode. Given frozen embeddings, STR builds a joint k-nearest-neighbour graph, maps the episode into a normalized-Laplacian spectral coordinate system, initializes class representatives from the labelled support, and iteratively refines them using pseudo-labelled queries. We evaluate STR under two protocols. A controlled component study with frozen ResNet-18 features shows that spectral refinement consistently improves over single-prototype spectral initialization across five shifted domains, with the largest gains in the one-shot regime where support estimates are weakest. We then benchmark STR against recent Cross-Domain Few-Shot Learning (CD-FSL) methods using the standard miniImageNet-pretrained ResNet-10 backbone over eight established target domains. Operating entirely at inference time, STR attains the highest 1-shot average among compared methods and remains competitive at 5-shot, rivalling approaches relying on heavy source-domain meta-training augmentations. Because STR is transductive, we report its setting explicitly. Diagnostics attribute its gains to iterative refinement in spectral coordinates rather than added prototype capacity, which remains inactive in our configuration. --- ### OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling Authors: Yikun Miao, Fangqi Zhu, Quanxin Shou, Xiaoyi Pang, Zhengyang Yan, Junhao Li, Haodong Wang, Zicong Hong, Song Guo Published: 2026-09-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.23753v1 Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeling. While recent efforts leverage simulator-generated data to enhance this capability, existing training pipelines face two fundamental limitations. First, static offline data collection leads to a distribution misalignment between training sets and the model's evolving error patterns, failing to resolve critical long-tail scenarios where dynamics predictions remain unreliable. Second, the standard objective of minimizing observational discrepancy often encourages the model to exploit spurious correlations instead of capturing the underlying action-effect causality. To address these limitations, we propose OnlineWM, an online training framework that continuously improves world modeling through active simulator interaction and causality-aware optimization. OnlineWM introduces two key innovations: (1) Active Online Learning: Instead of using fixed datasets, OnlineWM adaptively queries the simulator for new interaction sequences that target the model's current predictive weaknesses, ensuring high-utility data acquisition. (2) Causality-Aware Fine-Tuning: We propose a counterfactual learning strategy that contrasts the outcomes of different actions from identical states, forcing the model to attribute state transitions to specific actions rather than ambient environmental evolution, thereby grounding its predictions in reliable causal mechanisms. By integrating active data acquisition with causal optimization, OnlineWM establishes a closed-loop refinement process that ensures the model is both robust to diverse scenarios and precise in its causal attribution. Extensive experiments demonstrate that OnlineWM significantly enhances action controllability and generalizes effectively to unseen domains. --- ### Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap Authors: Akash Chavan Published: 2026-09-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.23742v1 Small open-source large language models (LLMs) in the 0.6B-4B parameter range are increasingly deployed for structured output generation (JSON, function calling, data extraction), yet little is known about how constrained decoding (CD) interacts with model scale in this regime. We benchmark five models from three families across 14 structured-output tasks under three decoding conditions (native, Outlines, XGrammar). We introduce a two-axis evaluation that separates structural correctness (schema validity) from semantic correctness (content accuracy). We find that CD eliminates all structural failures across all models (schema validity: 78.6-92.9% to 100%), but content accuracy reveals a persistent semantic gap that is scale-dependent: type coercion failures are fully CD-rescuable, while instruction-semantic failures (e.g., multi-step function calling) remain CD-resistant. Schema conformance is necessary but not sufficient for semantic correctness; CD's reach ends exactly where schema conformance ends. ---