# Research Papers — 2026-09 · bundle page 174 of 266 > Full-text markdown of papers #8651–8700 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/174 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/173.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/175.md) ### Building Legal Reward Models for Grounding and Abstention Authors: Rilton Franzone, Valentin Noël, Puyu Wang, Philip Torr, Fabio J. Fehr Published: 2026-09-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.14739v1 Large language models are increasingly used in high-stakes domains such as law, where systems must ground their reasoning in retrieved evidence and abstain when that evidence is insufficient. However, existing reward models are largely optimised for general preferences rather than contextual grounding, limiting their ability to evaluate these behaviours in retrieval-augmented generation (RAG) settings. We introduce a framework for transforming existing legal QA datasets into contextual preference data and use it to construct LegalRewardBench (LRB), a benchmark for evaluating grounded legal generation under noisy and insufficient retrieval conditions. Across general and legal contextual evaluation, we find that contextual DPO improves grounded evaluation, but performance is sensitive to preference-data construction. Length-balanced augmentation substantially improves grounded legal evaluation, with the strongest configuration combining length-balanced legal and general contextual preference data and improving performance by up to $\mathbf{+25.6}$pp over baseline. We further find evidence of cross-jurisdiction transfer: models contextually refined primarily on Victorian criminal-law data improve grounded evaluation on external US legal benchmarks, including a $\mathbf{+16.2}$pp improvement on \textsc{Housing Statute QA}. Together, these results provide a reproducible foundation for constructing and evaluating grounded legal reward models in retrieval-augmented settings. --- ### AppliedScientist: Automated Scientific Revision Through Iterative AI Reviewing Authors: Vidushee Vats, Karun Sharma, Shengzhi Li, Shichao Pei Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14738v2 Automated reviewing systems are increasingly evaluated based on the quality of the reviews they produce. Yet a review is only useful if acting on it leads to a measurable improvement in the paper. We present AppliedScientist, a closed-loop system that couples an autonomous AI scientist with an AI reviewer, and evaluate it by iteratively revising rejected papers from a range of research subfields. To mirror how human authors build on earlier drafts, the AI scientist has access to its previous versions during revision. To avoid bias from prior judgments, however, each review is generated independently, with the reviewer having no memory of earlier feedback or scores. We compare three revision settings: one initialized with the original venue reviews, one initialized with AI-generated reviews, and autonomous self-revision using the same fixed prompt in every round. Because the reviewer both guides and evaluates the revision, we also assess the human-initialized revisions using Stanford Reviewer as an independent evaluator. Reviewer-guided revision consistently improves more than fixed-prompt self-revision, and Stanford Reviewer also assigns higher scores to later revisions. AppliedScientist resolves 128 of 150 execution-related weaknesses (85.3%), but only 2 of 18 idea-related weaknesses (11.1%), suggesting that iterative revision is effective at improving experiments and implementation, but rarely changes concerns about novelty or significance. --- ### HELENA for 5G NR LEO NTN Channel Estimation: A Comparative Evaluation Authors: Miguel Camelo Botero, Nina Slamnik-Kriještorac, Johann Marquez-Barja Published: 2026-09-13 Categories: eess.SP, cs.LG, cs.NI, cs.PF arXiv: https://arxiv.org/abs/2609.14735v1 Deep Learning (DL)-based channel estimation has shown high accuracy and low latency in terrestrial 5G NR, but Low Earth Orbit (LEO) Non-Terrestrial Networks (NTNs) introduce Doppler and synchronization impairments that may require NTN-specific architectures. We test whether High-Efficiency Learning-based channel Estimation using dual Neural Attention (HELENA), originally designed for terrestrial channels, remains effective after NTN retraining and suitable across high-performance and power-constrained inference platforms. Its unchanged architecture is trained on paired receiver-compensated (NTN-1) and residual-impaired (NTN-2) datasets and compared with eight terrestrial-origin models trained on the same NTN data and the NTN-specific MDELAN-SISO. HELENA achieves the lowest observed SNR-averaged NMSE among the DL estimators in both conditions, including 55.8-62.7% lower linear-scale NMSE than MDELAN-SISO. All DL models degrade in NTN-2, demonstrating the challenge posed by residual Doppler and its associated impairments. On an RTX PRO 4500, HELENA achieves 0.0595 ms 99th-percentile (P99) inference latency, 88.1% below the 0.5 ms budget, with lower energy than its closest attention-based competitors. On a 10 W Jetson Orin NX, it retains a favorable accuracy-energy trade-off, but no model meets the P99 budget. Thus, HELENA needs no NTN-specific redesign for the evaluated task, while embedded tail latency remains an open challenge. --- ### OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise Authors: Sina Gholami, Abdulmoneam Ali, Tania Haghighi, Rashadul H. Badhon, Behafarin Emam, Sally S. Y. Ong, Atalie C. Thompson, Theodore Leng, Ahmed Arafa, Jennifer I. Lim, Minhaj Nur Alam Published: 2026-09-13 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2609.14734v1 Federated learning enables collaborative model development without centralizing patient data, but annotation reliability at participating institutions cannot always be assumed. In ophthalmic imaging, differences in disease prevalence and class composition can resemble changes caused by corrupted supervision. We introduce OCT-FedSIR, a reliability-aware spectral framework for federated OCT classification under client-dependent annotation noise and heterogeneous data distributions. OCT-FedSIR combines class-balanced spectral estimation, Stage-I logit adjustment, complementary spectral descriptors, selective spectral relabeling, and noise-aware federated optimization. We evaluated the framework on the Kermany, University of Illinois Chicago, and Wake Forest datasets under symmetric and structured asymmetric noise and three levels of non-IID heterogeneity. Across 117 experimental conditions, OCT-FedSIR achieved a mean accuracy of 86.73%, compared with 79.94% for RoFL and 78.75% for FedCorr. It correctly separated clients with original and corrupted annotations across all evaluated conditions, while the original FedSIR identification procedure was less robust, particularly under asymmetric noise. Spectral relabeling recovered 77.2% of corrupted annotations with 91.3% correction precision and a 3.5% false-correction rate. Retaining corrected clients outperformed spectral pruning by 9.30 percentage points on average. These findings show that annotation noise can often be identified and corrected without discarding informative client data. --- ### WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion Authors: Aashish Bohra, Vivek Vijay Published: 2026-09-13 Categories: cs.LG, q-fin.ST arXiv: https://arxiv.org/abs/2609.14733v1 Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), channel-indiscriminate multi-scale decomposition that conflates heterogeneous frequency signatures, and static multi-branch fusion that cannot adapt to market regime shifts. WaVeFuse addresses these limitations through a unified dual-branch architecture. Symlet-4 wavelet denoising (level 2, MAD soft threshold) suppresses microstructure noise in OHLCV. Seven low-lag TIs computed from denoised prices are encoded by a causal channel-wise continuous wavelet transform (Morlet, 32 scales) into a per-timestep scale-space matrix. A CNN-BiLSTM branch captures temporal dynamics, while a dual-layer Transformer (heads=4, dk in {16, 32}) models inter-scale spectral dependencies, and their representations are integrated by a 2-token softmax gate Vertical Attention Fusion (VAF) that dynamically reweights branches as market regimes shift. Evaluated under walk-forward validation (WFV) on KOSPI, DAX, NYSE Composite, and Russell 2000 (2010-2023), WaVeFuse achieves R2 = 0.81-0.96 and directional accuracy 70.5-78.3%. It outperforms seven state-of-the-art models by 8.9-20.2% MAE across twelve dataset-period configurations. Diebold-Mariano statistics (4.62-10.38, p<0.001) confirm superiority over a well-tuned XGBoost benchmark across four indices. Ablation verifies component-wise contributions. Under realistic backtesting with 10 basis point transaction costs, WaVeFuse's directional strategy achieves a mean Sharpe ratio of 3.69 across four markets and limits maximum drawdown to 7.5% during the COVID-19 crash. With 152k parameters (0.68MB) and sub-1.3ms GPU inference, WaVeFuse delivers a computationally efficient, regime-robust framework suitable for research and decision-support deployment. --- ### Parameter isolation with domain-specific experts for incremental audio classification Authors: Jongyeon Park, Do-Hyeon Lim, Sang-won Park, Hong Kook Kim, Kyungdeuk Ko, Hyeongcheol Geum, Jeong Eun Lim Published: 2026-09-13 Categories: eess.AS, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2609.14730v1 To successfully deploy a model in time-varying environments such as streaming data prediction and sensing control, domain-incremental learning (DIL) has attracted attention since it aims to adapt a previously trained model to newly arriving domains, while reserving knowledge from earlier domains without accessing their data. Incremental learning across domains can be regarded as a recurrent update, in which the current model is obtained by updating the model carried over from previous domains. Conventional DIL approaches that rely on domain-invariant feature learning and weight regularization gradually overwrite or constrain parameters learned in previous domains, leading to catastrophic forgetting. Instead, this paper proposes a new domain-specific parameter-isolation architecture that retains all past domains. The proposed architecture mitigates catastrophic forgetting through a full-order recurrent update, constructing a new expert using domain-specific data conditioned on all previously frozen models. To achieve this, we incorporate data-free generative replay to reconstruct previous-domain data and cross-domain feature generation to recover later expert features missing from earlier domain samples. Finally, we apply the proposed model architecture to domain-agnostic incremental learning for audio classification, as defined in the DCASE 2026 Challenge Task 7. Consequently, we achieve micro and macro accuracies of 78.4% and 78.9%, respectively, representing increases of 33 and 25 percentage points over the Challenge baseline. Ablation studies are conducted to examine the effectiveness of each processing component in terms of classification accuracy. --- ### CALICO: A Human-Centered, Codebook-Aligned System for Annotation Authors: Boqin Yuan, Xiaoyi Gu, Fiona Li, Chang Wan, Angel Hsing-Chi Hwang, Jieyu Zhao Published: 2026-09-13 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2609.14726v1 Large language models are increasingly used to scale codebook-based annotation in scientific research, but existing workflows provide limited support for translating domain experts' codebooks into reliable, revisable, and auditable prompts. Prompts are often treated as fixed instructions and hidden from annotators, making it difficult for non-technical domain experts to diagnose and correct model behavior when outputs violate codebook guidelines. In this paper, we present CALICO, a human-centered, codebook-aligned annotation workflow that treats prompts as editable, versioned, and optimizable artifacts. CALICO integrates codebook parsing, prompt generation, result inspection, prompt versioning, natural language human feedback, and label-supervised prompt optimization through existing optimizers such as GEPA, MIPROv2, and OPRO, together with our reflection-based optimizer, ReflectAgent. Empirically, we evaluate CALICO on domain-specific AI-companion chatbot conversation codebooks. Across evaluated dimensions, CALICO improves mean held-out performance by +13.0 and +7.4 absolute points for two coders, respectively. A coder-specificity analysis further suggests that optimized prompts capture coder-specific interpretations rather than only generic codebook clarification. CALICO runs as a web application that takes users from raw codebook materials to inspectable, exportable labels; the website, codebase, and live demo are released at https://calico-annotation.github.io/ under the Apache 2.0 License. --- ### CrossDistill: Balancing Quality and Diversity via Trajectory-Level Hybrid Few-Step Distillation Authors: Yuxi Liu, Haoyu Li, Yixiang Cai, Tengxu Sun, Zekun Zhang, Baole Ai, Ang Wang, Jiamang Wang, Lin Qu, Kun Yuan, Kai Zhang Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14725v2 Few-step distillation accelerates diffusion models but must balance diversity and fidelity: trajectory-based distillation preserves mode coverage, while distribution matching sharpens samples but can reduce diversity. We show that this tension can be exploited in a noise-regime-dependent way: high-noise steps largely determine global modes, whereas low-noise steps refine local details. We propose CrossDistill, a trajectory-level hybrid distillation framework that splits the sampling trajectory at a crossover point, applies a trajectory-preserving objective on the high-noise interval and a distribution-matching objective on the low-noise interval, and couples the two stages through the crossover state. In contrast to loss-level mixing, and complementarily to training-time two-stage recipes, CrossDistill explicitly assigns complementary objectives along the noise axis, so that global branching is preserved before local statistics are sharpened. CrossDistill is a noise-level scheduling policy: PCM and DMD are plug-in instantiations, while the noise partition, crossover coupling, and objective ordering are the key design elements. Experiments on text-to-video diffusion models and qualitative image-to-video results show that CrossDistill expands the few-step quality-diversity frontier, retaining seed-level variation while achieving competitive visual fidelity. --- ### Bayesian Intelligence from the Outside Authors: Alex Smolin, Bryan Wilder Published: 2026-09-13 Categories: cs.AI, econ.TH arXiv: https://arxiv.org/abs/2609.14724v1 Inferring intelligence from observable behavior is a foundational challenge in artificial intelligence. We develop a theory of Bayesian intelligence for agents such as language models. Each prompt induces a possibly imperfect internal experiment; the agent updates a full-support prior by Bayes' rule and faithfully reports its posterior over the possible answers to the question. Repetitions draw fresh, independent outcomes from the same unobserved experiment at one fixed state. We show that the agent's behavior admits this explanation if and only if its reports are not fully contradictory, i.e., some state remains possible under every report across all prompts. Report frequencies and the sizes of positive probabilities impose no further restrictions. We further propose and characterize the behavioral implications of an intelligence order that makes the behavior of two agents consistent with one agent having access to a more informative experiment: there should exist a coupling of report distributions such that the more informative agent's report excludes every answer excluded by its counterpart. Finally, we show the difficulty of aggregating coarse reports from intelligent agents: unless the agent reports a belief about the complete state of the world, the optimal aggregation can assign arbitrary weights to states that have not been excluded. These results provide a basis for understanding when agents' behavior is intelligent and highlight the difficulty of rejecting Bayesian rationality. --- ### PC$^2$-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devices Authors: Yutong Gu, Yingxi Xie, Kejin Huang, Jian Ning, Hanzhe Liang, Linlin Shen, Jinbao Wang Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14722v1 Low-cost and low-resolution sensors used in edge deployments can produce test point clouds that are substantially sparser than the normal training data. This train-test sampling-resolution gap changes the local geometry available to a 3D anomaly detector. We propose PC$^2$-AD, a point cloud upsampling framework that compensates sparse test inputs before downstream detection. Target Domain Candidate Generation (TCG) adapts a pretrained upsampler to normal training geometry and generates a dense candidate pool. Geometry-Aware Candidate Filtering (GACF) selects candidates according to geometric spacing and spatial coverage. Normality-Preserving Point Compensation (NPPC) refines the selection by comparing candidate normality scores with those of their input anchors. The selected points are combined with the unchanged input points and processed by the existing detector. Experiments with six detectors on two Anomaly-ShapeNet settings and Real3D-AD show improvements in the mean of object-level and point-level AUROC for all six detectors in each Anomaly-ShapeNet setting and four on Real3D-AD. These results support point cloud compensation as an input-level approach to improving 3D anomaly detection under low-resolution sensing conditions. Code is publicly available at https://github.com/gyutong406-commits/PC2-AD. --- ### Are Gradient Boosting Models Suitable for Intermittent Demand Forecasting? Authors: Vladislav Kislinskii, Mazhar Hameed Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14718v1 Demand forecasting is critical in modern industry, offering opportunities to reduce costs and gain competitive advantage through improved inventory management. However, forecasting becomes particularly challenging for products with intermittent demand, where demand occurs infrequently and time series contain many zero observations. Such dynamics are common across diverse sectors, such as industrial organizations, consumer goods, aviation, automotive, and electronics. Motivated by these challenges, this paper explores the potential of gradient boosting models to improve forecasting performance. We evaluate statistical, specialized, machine learning, and ensemble approaches across multiple datasets. The results show that specialized methods achieve the strongest performance among individual models, while gradient boosting on its own tends to underperform. However, combining a machine learning model with a specialized approach improves forecasting accuracy by up to 10%, demonstrating that even simple ensembles can outperform single models. Overall, the findings highlight the value of combining machine learning with domain-specific forecasting techniques for intermittent demand. --- ### Carryover Drafting: Recycling Rejected States for Speculative Decoding Authors: Jahyun Koo, Sunghyeon Woo, Jaeeun Kil, Jeongtae Lee, Sungjae Lee, Kyomin Jung, Minsub Kim Published: 2026-09-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.14717v1 Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept several tokens. By construction, verification computes representations for both accepted and rejected tokens. Yet, conventional drafters retain only the representations of accepted tokens, leaving the substantial verifier computation spent on rejected tokens effectively wasted. We find that these discarded hidden states generated during target forward retain useful information about future tokens that can improve subsequent drafts. However, realizing this opportunity poses two distinct challenges. At inference, recycling overhead can increase drafting latency, diminishing the speedup gained from increased acceptance length. During training, standard parallel drafter training does not produce inference-aligned rejected states, while obtaining them through sequential rollouts would sacrifice parallelism across training positions. We introduce Carryover Drafting, which addresses both challenges. Carryover recycles rejected target hidden states as temporary KV context, allowing the drafter to selectively attend to them. It reuses the drafter's existing interface and adds only a single learned embedding to distinguish rejected states from committed context. The additional KV context is replaced each drafting round, keeping its length bounded by one proposal block. We introduce parallel draft--verify--draft training that exposes the drafter to inference-aligned rejected states while preserving parallelism across training positions. Experiments with DFlash and a DSpark-derived semi-autoregressive drafter across two target models show that this simple Carryover mechanism improves average acceptance length by 6.5--14.7% and end-to-end vLLM speedup by 7.9--14.4% over the corresponding baselines, with speedup gains reaching 28.8% on translation. --- ### Moral Rebel Agents: Decision-Making Under Conflicting Obligations Authors: Hector Munoz-Avila, David W. Aha, Paola Rizzo Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14716v1 Autonomous agents are typically obliged to follow user-assigned tasks. However, strict obedience may conflict with moral obligations that arise during execution. This paper investigates \textbf{moral rebellion}: the ability of an autonomous agent to deviate from a user-assigned task when morally justified. We formalize five agent architectures: an \textit{amoral agent} that pursues assigned tasks without considering moral obligations, and four forms of \textbf{moral rebel agency}: (1) \textit{utilitarian agents} that opportunistically maximize task outcomes; (2) \textit{deontic} agents that enforce normative constraints; (3) \textit{utilitarian-deontic} (UD) agents that combine deontic constraints with utilitarian reasoning; and (4) \textit{dutiful} agents that additionally preserve commitments to assigned tasks. We implement these architectures within a hierarchical task network planning framework and evaluate them in a Mini Search-and-Rescue domain that exposes trade-offs among assigned-task completion, opportunistic rescue, and norm compliance. Our empirical results show that the proposed agents exhibit distinct trade-offs among rescue results, assigned-task completion, and norm compliance. In particular, the preservation of task commitments emerges as an important dimension of moral rebellion, for which the UD and dutiful agents produce substantially different behaviors despite their shared utilitarian and deontological foundations. These findings highlight the importance of commitment-aware moral reasoning for autonomous agents operating in morally consequential environments. --- ### Depth and Scale in the Sub-150M Regime: JugnuLM-53M vs JugnuLM-110M Authors: Dushyant Rajput, Nirdesh Chauhan, Siddharth Kosaraju Published: 2026-09-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.14715v1 We scale our conventional sub-150M pretraining recipe from 53.5M to 109.7M parameters, holding the method fixed (Qwen3-style decoder with grouped-query attention, RoPE, SwiGLU, RMSNorm, QK-Norm, and a z-loss; FineWeb-Edu data) and changing only the geometry to a deep-and-thin 23-layer x 576-hidden design. The larger model improves across the board -- BLiMP 78.1 -> 81.3, ARC-Easy 51.4 -> 52.5, WikiText-2 byte-perplexity 2.04 -> 1.95 -- and its 81.3% BLiMP essentially matches GPT-X2-125M (81.28) at about 12% fewer parameters. Notably the 110M model achieves this on fewer training tokens (about 8B vs 12B), so the gain is attributable to capacity and depth, not more data. Both models are deliberately conventional; this report is a clean scaling control and the baseline rung (R0) of an ablation study of what further improves models in this regime. An ablation ladder follows: value residuals (R1) and the Muon optimizer (R2) lift ARC-Easy by a cumulative +3.6 (52.5 -> 56.1) at a near-flat BLiMP and are kept; a diverse data blend (R3) and two logit-distillation settings (R4a/R4b) are not kept -- honest negatives. R3 pins ARC-Easy to FineWeb-Edu's educational filtering rather than raw diversity; distillation from a 1.7B teacher can reach the class-leading ARC-Easy (56.99, matching GPT-X2-125M) but only at a perplexity cost that dialing KD down then erases -- so R2 remains the best kept stack. --- ### Learning Metastable Dynamics Authors: Rupak Majumdar, Mahmoud Salamati, Nikhil Singh, Sadegh Soudjani Published: 2026-09-13 Categories: cs.PF, cs.LG arXiv: https://arxiv.org/abs/2609.14712v1 Metastability---a phenomenon where systems remain trapped in quasi-stable states before abruptly transitioning under rare perturbations---is ubiquitous in physical systems. Although metastability is a widely observed phenomenon, its identification and analysis present significant challenges. To address these challenges, we propose a novel framework for analyzing metastability using Koopman theory. We use a finite set of system trajectories to learn a representation of the dynamics that defines a latent space in which the system evolves linearly, thereby enabling a systematic characterization of metastable behavior through the spectral properties of the linear mapping. Empirical evaluations demonstrate that our approach is capable of anticipating metastable behavior significantly earlier than its actual manifestation, even with $10\%$ of the simulation duration. Moreover, we establish that the dominant eigenvalue of the learned Koopman matrix in the latent space serves as a critical indicator for detecting metastability across both single-server and multi-server configurations. --- ### GRPO-QPS: Target-Preserving Reinforcement Learning for Quantum Posterior Sampling Authors: Yufeng Wang, Parivesh Priye, Lu Wei, Haibin Ling Published: 2026-09-13 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2609.14711v2 Bayesian quantum tomography requires efficient inference while preserving a posterior fixed by the prior and Born likelihood. Learned transport provides fast amortized samples, but reward tuning can reshape the generated distribution rather than improve exploration of this fixed target. We introduce GRPO-QPS, a target-preserving framework in which GRPO learns proposal behavior and an exact Metropolis correction preserves the posterior after training. Across the evaluated reconstruction benchmarks, GRPO-QPS improves over BuresTomFlow and Flow-GRPO on thermal, cat, Dicke, and cluster families, and it closely matches an exact two-qubit reference posterior. Tuned conventional MCMC is slightly stronger on several original continuous benchmarks where the available fixed proposals already match the posterior geometry well. To test whether this reflects a fundamental limitation of learned exploration, we evaluate a more challenging multimodal thermal posterior. At six qubits and 800 shots, the learned proposal achieves a minimum effective sample size of 102 per $1{,}000$ likelihood calls, compared with 28 for prior independence, 27 for a tuned fixed mixture, and 20 for Haario adaptive Metropolis. A record-conditioned policy also transfers to unseen 3,000-shot records, matching or exceeding the strongest conventional baseline in all nine held-out seed-record comparisons. These results show that GRPO-QPS combines target-preserving Bayesian inference with broad gains over learned transport baselines and a sampling advantage when efficient exploration requires proposal geometry beyond the evaluated conventional kernels. --- ### An immune world model for multiscale forecasting and therapeutic hypothesis generation Authors: Taoyong Cui, Xi Wang, Zonghang Li, Jinchao Ding, Lingsen You, Yuzhi Xu, Wanghan Xu, Fang Wu, Kejun Ying, Wanli Ouyang, Pheng Ann Heng, Ling Yang et al. Published: 2026-09-13 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2609.14709v1 Immune therapies act across cell-intrinsic programs, tissue ecosystems, and patient-specific immune states, yet most predictors address these scales separately. We used a governed evolutionary AI Scientist to construct the Immune World Model, an action-conditioned model that learns how interventions move immune states across cellular, tissue, and individual levels. The Immune World Model--building Scientist searched candidate architectures and workflows, and the resulting world model was frozen before independent confirmation. The frozen model generalized to unseen interventions and biological contexts, recovered intervention-specific cellular programs, integrated cell and tissue information to improve ecosystem and patient-response prediction, and forecast unseen perturbation combinations. Immune World Model--guided analysis then combined measured perturbations with cross-axis inference to nominate IL-36$γ$ plus SIRP$α$ inhibition as a complementary-axis therapeutic hypothesis, whereas a governed self-correction audit rejected every screened cytokine pair. The Immune World Model provides a framework for multiscale immune simulation that connects AI Scientist-driven model construction, intervention forecasting, and the generation of prospectively testable therapeutic hypotheses. --- ### Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition Authors: Yecheng Wu, Song Han, Han Cai Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14708v2 A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning accuracy and inference efficiency can be challenging, as the two objectives can favor different reasoning behaviors. Independently post-trained models already offer distinct strengths in accuracy and efficiency. We introduce Lightning Weave, a post-training framework that extracts and composes these independently learned capabilities in a single student through on-policy distillation. Each acquired capability is represented by the policy shift from the model before post-training to the resulting specialist. Lightning Weave combines aligned log-ratio shifts at shared student token states and uses Tilted-Target DOPD to convert the cached signals into a stable learning target. Each anchor pair scores the cached trajectories once, enabling subsequent student training without serving multiple live anchor models concurrently. Across diverse student models and benchmarks in mathematics and code, Lightning Weave substantially improves upon the base students and achieves a state-of-the-art accuracy-efficiency frontier. On Qwen3.5-4B, it raises HMMT 2025 accuracy from 59.2% to 64.0% with 10.7% fewer response tokens, and LiveCodeBench v5 accuracy from 41.7% to 54.2% with 9.6% fewer response tokens. Adjusting the relative strengths of the anchor signals yields a strong empirical accuracy-efficiency Pareto frontier. These results establish Lightning Weave as a new practical route to efficient reasoning through capability composition. Code is released at https://github.com/jet-ai-projects/Lightning-Weave. --- ### WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians Authors: Johann Birnick, Rayan Saab Published: 2026-09-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.14706v2 How should a Kronecker-factored Hessian approximation be chosen for post-training quantization? We address this question through WaterKron, which combines two-sided GPTQ with row- and column-dependent waterfilling scales and entropy coding. We derive its high-rate distortion with respect to the full Hessian using an explicit Kronecker-Hessian mismatch factor $Φ$. This factor quantifies the asymptotic distortion penalty due to the Kronecker Hessian approximation and provides a criterion for selecting the factors optimally. Minimizing $Φ$ leads to a Gaussian covariance-fitting problem with classical ``flip-flop'' updates. We thus give a rate-distortion justification for using the resulting FlipFlop Hessian in quantization. We evaluate it empirically, finding that the FlipFlop Hessian consistently improves KL divergence and perplexity over input-only, marginal, and Frobenius-based Hessian choices. --- ### Patient-Level, Leakage-Aware Deep Learning for Cross-Center Periapical Radiograph Classification Authors: Md Jubaer Rahman, Ulas Bagci Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14703v1 Dental caries and endodontic disease are among the most common health conditions worldwide, and intraoral periapical radiographs are central to their detection, treatment planning, and follow-up. Automated tooth-level classification of these images, however, lacks reproducible benchmarks, is often evaluated with image-level splits that leak patients between training and test, and is rarely validated across clinics. This paper presents the first patient-level, leakage-aware classification benchmark for single-tooth intraoral periapical radiographs on the DentIRO dataset, which comprises 5,300 images from 3,243 patients across two clinics and four classes: Healthy, Caries, Crowned, and Root Canal. Five transfer-learning models are compared with patient-grouped stratified cross-validation, so that every patient remains within a single fold. DenseNet121 gave the strongest and most stable result at a mean macro-F1 of 0.9787, while the four ImageNet-initialized backbones performed comparably. A controlled comparison on a fixed architecture showed that chest-radiograph pretraining transferred less effectively than ImageNet initialization. Bidirectional cross-center validation produced a small average generalization gap of 0.0077, and Grad-CAM confirmed that predictions rely on clinically meaningful tooth regions rather than acquisition artifacts. The benchmark offers a rigorous and reproducible baseline for intraoral radiograph classification. --- ### Perceive, Refine, Reason: A Calibrated Pipeline for Measuring Indicators in Strategic Visual Communication on Social Media Authors: Weihong Qi, Chen Ling Published: 2026-09-13 Categories: cs.CV, cs.CY arXiv: https://arxiv.org/abs/2609.14699v1 Visual content shapes audience perception and opinion on social media, and computational social science increasingly relies on automated tools to analyze images at scale. Yet a measurement gap persists: existing tools rely on predefined categories or produce only coarse image-level labels, while measuring which specific objects appear in an image, how prominently, and where in the frame remains difficult at scale. We introduce Perceive, Refine, Reason (PRR), a calibrated pipeline that turns flexible vision-language detectors into auditable measurement instruments for social-scientific research. PRR combines natural-language category prompts with pixel-level spatial refinement via the Segment Anything Model (SAM) and a multimodal LLM arbitration layer whose reasoning chains externalize domain knowledge and lower the expertise threshold for human-in-the-loop validation. A complementary three-tier auditability framework applies quantification learning to profile per-category reliability, support task-aligned configuration, and statistically correct prevalence estimates. Across four vision-language detectors and nine sociological categories, the pipeline yields substantial precision gains over zero-shot baselines, including a 43.3-point improvement for the strongest backbone. Applying PRR to 103,920 Facebook images from U.S. legislators during the 2024 election cycle and linking detections to DW-NOMINATE ideology scores, we find that more conservative legislators display U.S. flags as larger visual elements, with a weaker tendency toward peripheral placement, a spatial pattern invisible to binary detection. PRR provides computational social scientists with a model-agnostic toolkit for accessible, spatially-grounded, and correctable visual measurement. --- ### Speak to the City: Multimodal Resolution for Outside-the-Vehicle References Authors: Alireza Parchami, Artin Saberpour, Robin Connor Schramm, Jürgen Steimle, Ulrich Schwanecke Published: 2026-09-13 Categories: cs.HC, cs.CL, cs.IR, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2609.14691v1 As autonomous vehicles and Extended Reality (XR) headsets enable novel in-car interactions, seamlessly querying physical landmarks, known as Outside-the-Vehicle Referencing (OVR), remains challenging due to ego-motion and referential ambiguity. We present a robust, multimodal OVR framework fusing user gaze and natural language to identify Points of Interest (POIs). To address the scarcity of dynamic vehicular data, we developed a VR-based pipeline synchronizing 360-degree transit videos with vehicle GNSS telemetry. Through a user study (N=46) mapping passenger head orientation into a 3D geospatial Digital Twin, we captured authentic gaze-speech behaviors. We subsequently trained a lightweight Transformer network, leveraging LLMs to dynamically align continuous spatial gaze vectors with discrete verbal context. Experimental results demonstrate high accuracy and low computational overhead, achieving an 83.33% Top-1 accuracy (87.72% Top-2) and an average inference time of 24.3 milliseconds. This real-time paradigm effectively resolves referential ambiguity, enabling context-aware spatial retrieval for passengers within the vehicle. --- ### LIMODENet: Attention-Free Compact Encoders for Information-Preserving Onboard Satellite Image Restoration Authors: Thanh-Dung Le, Vu Nguyen Ha, Ti Ti Nguyen, Symeon Chatzinotas Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14690v1 Onboard satellites must restore a channel-degraded image on a few watts, using neuromorphic accelerators (e.g., BrainChip Akida, Intel Loihi-2) that support no softmax or attention. We ask which encoder restores best under that constraint and introduce LIMODENet (LinearMix-ODENet), a 0.69M softmax-/QKV-free backbone whose residual stages read as ODE discretizations and which is empirically information-preserving (probe accuracy rises 79.9% -> 98.4% from stem to head). At iso-parameters it restores 1 dB DVB-S2X-degraded EuroSAT better than a CNN autoencoder (+1.75 dB PSNR) and a skip-connection U-Net (+1.07 dB), three seeds, non-overlapping. Unconstrained modern restorers (NAFNet, Restormer) win on fidelity; we decompose that gap: spiking-legal additive skips recover about half, and the rest traces to attention and channel gating. LIMODENet then converts end-to-end to a spiking network with zero blocked operations, versus 22-24 for the competitors: not the best restorer available, but the best verified deployable within a real power budget. --- ### One Feedback System Does Not Fit All: Localising Data-to-Text Driver Coaching for the United Kingdom and Nigeria Authors: Iniakpokeikiye Peter Thompson, Jawwad Baig, Ehud Reiter, Dewei Yi Published: 2026-09-13 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2609.14687v1 Data-to-text driver coaching is often presented as a generic pipeline from telematics events to advice. This paper argues that its content requires localisation because usefulness and credibility depend on drivers' knowledge, prevalent risks, regulation, infrastructure, and available data. Two independently developed systems in the United Kingdom and Nigeria are compared by tracing requirements through content selection, generation, and field evaluation. The UK system prioritises post-trip reflection, explanations tied to road and place context, and tone-sensitive wording. The Nigerian system combines legally grounded, once-daily Tips based on detected events with weekly persuasive Reports; it foregrounds safety education and alcohol-related risk in response to reported gaps in formal training and traffic-rule knowledge, as well as local road-safety priorities. Reliable speed-limit metadata supported speeding feedback in the UK, whereas its scarcity led the Nigerian evaluation to exclude speeding from its outcome metric. Both interventions were associated with reduced distance-normalised unsafe-event rates in their own field studies, although their designs and metrics preclude an effect-size comparison. The analysis yields a requirements-to-content design process for localising safety-critical NLG without treating a high-income deployment as the default. --- ### The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation Authors: Advait Deshmukh, Nora Benedict, Melanie Walsh, Maria Antoniak Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14677v1 Large language models (LLMs) have changed the way people engage with stories. Drawing on public chatbot logs, we can see that when users generate stories, they iteratively edit their prompts to explore narrative possibilities, adjusting characters, redirecting plots, and swapping fictional universes. As aggregated data, these prompts represent rich traces of creative preference at scale. Yet story generation evaluation benchmarks rely on static, one-shot prompts that cannot capture this exploratory behavior. In this work, we study how users revise consecutive story prompts in the wild. Using a dataset of naturally occurring user-chatbot conversations, we construct WildStories, a sample of 275,635 story generation prompts (labeled with story format, prompt components, and explicitness), and WildEdits, a collection of 24,291 edit trees that model how users iteratively edit base story prompts and explore branching story possibilities. From these trees we develop a framework of edit types crossing four directions (adding, removing, changing, and extending) with fourteen targets (e.g., plot, character, genre). We then use our datasets and this framework to analyze user behavior in navigating narrative space via LLMs. Finally, we show how automated permutations based on the framework can be used for story generation benchmarking. Content Warning: This paper works with "wild" chatbot logs, which often include toxic and sexually explicit themes. --- ### From Density to Biopsy Decisions and Malignancy Prediction: A Benchmark Study of Multimodal Large Language Models Against Radiologists in Digital and Contrast-Enhanced Mammography Authors: Ali Abbasian Ardakani, Afshin Mohammadi, Taha Yusuf Kuzan, Beyza Nur Kuzan, Alisa Mohebbi, Masume Behruzi, Hamid Khorshidi, Ashkan Ghorbani, Elham Asadiara, Zeinab Khorshidi Lotfi, Ansar Rahman, Nedim Christoph Beste et al. Published: 2026-09-13 Categories: cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2609.14676v1 Purpose: To compare four multimodal large language models (MLLMs) with radiologists of varying expertise in breast density assessment, BI-RADS assessment, biopsy candidacy determination, and continuous malignancy probability estimation using digital mammography (DM) and contrast-enhanced mammography (CEM). Methods: This study included 179 women with paired DM/CEM examinations and reference standards. Four MLLMs (ChatGPT-5.2, Gemini-3.1 Pro, Sonnet-4.6, Muse Spark) interpreted images with and without masks; three radiologists interpreted non-masked images. Results: For binary density classification on DM, radiologist accuracies ranged from 55.81% to 78.60%, exceeding most MLLM values (62.33%-71.63%), while masks added limited benefit. Five-category BI-RADS accuracies were higher for radiologists on DM (56.74-67.44%) and CEM (62.33-82.79%) compared with MLLMs (DM 31.16-45.12%; CEM 40.00-55.81%). Binary biopsy-candidacy accuracies were likewise higher for radiologists (DM 85.12-89.77%; CEM 86.98-92.09%) than for MLLMs (DM 61.39-75.35%; CEM 69.30-82.79%), although CEM improved performance across all readers. Lesion masks substantially improved MLLM continuous malignancy-probability accuracies from 64.65%-71.63% to 72.56-78.60% on DM and from 67.91%-77.21% to 72.56%-81.86% on CEM, approaching radiologist ranges (DM 63.72-82.79%; CEM 81.86-88.84%). The corresponding AUCs for the top masked models overlapped those of the human readers. Overall, Muse Spark, followed by Sonnet-4.6, demonstrated the strongest performance among the MLLMs across domains. Conclusion: Radiologists generally outperformed MLLMs in categorical tasks, while selected masked models approached human performance for continuous malignancy probability estimation, suggesting a potential adjunctive role. --- ### PU classification under Non-SCAR: clustering-assisted logistic model with oversampling enhancement Authors: Konrad Furmańczyk, Kacper Paczutkowski Published: 2026-09-13 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.14675v1 This study addresses the PU classification problem under violations of the SCAR assumption. We investigate logistic regression-based approaches, namely the cluster method and its extensions with strict and non-strict Lasso regularization. The primary contribution of this work is the integration of the SMOTE technique to alleviate class imbalance and systematically assess its impact on the performance of the considered algorithms. SMOTE is first applied to rebalance the training dataset. Next, cleaning labels are derived via 2-means clustering. Logistic regression is then trained on the cleaned data, where identified positive instances are augmented with additional true positives and the remaining observations are treated as negative. The experimental evaluation is conducted on 13 real benchmark datasets and one synthetic dataset. For comparison, we include the naive approach and the Spy-EM method. The results demonstrate that incorporating SMOTE improves classification performance when the SCAR condition is violated and indicate moderate robustness of the LassoJoint method in this setting. --- ### Floquet Fibre Geometry and Higher-Order Reduced Coordinates for Off-Manifold Transients near Nonlinear Aeroelastic Flutter Authors: Puxue Tan Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14674v2 Assigning reduced coordinates to states near an attracting limit cycle requires the correct invariant-fibre geometry. The classical first-order phase-isostable chart obtained from adjoint Floquet modes projects along the strong-stable quotient fibre, whereas a metric-orthogonal complement of the retained slow bundle generally does not. We prove locally that a chart satisfying the linearised semiconjugacy relation leaves an O(delta^2) invariance residual, while projection along a non-invariant complement generically leaves an O(delta) term. For a nonlinear aeroelastic limit cycle, the metric-normal and strong-stable directions differ by 48.5 to 71.7 degrees, and metric-normal perturbations contain first-order retained phase and slow-amplitude components. Replacing the metric normal by the strong-stable fibre changes the measured residual scaling from delta^1.01 to delta^1.87 without fitted parameters. We then test learned higher-order corrections whose linearisation is pinned to the adjoint-Floquet chart, whose symmetry is exact, and whose reduced flow is fixed. Although they reduce the registered fixed-normalisation latent residual, post-hoc amplitude recalibration and adjoint-Floquet-targeted future consistency move or reverse the ranking. Because the learned maps already share the baseline's first-order gauge and the future target is supplied by the baseline chart, these diagnostics establish neither an independent positive nor negative higher-order result. Correct first-order Floquet geometry is therefore necessary in this benchmark, while the additional predictive value of the learned correction remains unidentified by the available representation-dependent diagnostics. --- ### Exploring Multimodal Turn-Taking Cues in Face-to-Face Conversation using Voice Activity Projection Authors: Willem Berner, Julio Cesar Cavalcanti, Kalle Åström, Gabriel Skantze Published: 2026-09-13 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.14666v1 Turn-taking is a fundamental component of spoken interaction, and while humans naturally rely on both verbal and non-verbal signals, dialogue systems usually depend on audio cues alone. This paper investigates whether visual features from face-to-face conversations can enhance turn-taking prediction beyond what is achievable from audio-only. We extend the Voice Activity Projection (VAP) model, a self-supervised transformer-based model for predicting future voice activity, by incorporating visual features extracted from the large-scale Meta Seamless Interaction dataset of dyadic face-to-face conversations. The visual features include gaze direction, head movement, body and hand pose, and facial action units (FAU). For incorporating the visual features, we explore concatenation, cross-attention fusion, delta features, and trainable gating mechanisms. Results show that visual information improves performance over the audio-only baseline, with FAU being significantly more informative than other feature groups. Body and gaze features nevertheless contribute complementary information, as the model combining all features performs best. Furthermore, results indicate that performance on specific tasks varies depending on whether training and test data come from improvised (acted) or naturalistic (non-acted) conversations. --- ### Symmetries and Singularities Authors: Vishnu Varadarajan, Mihir More, Aritra Das, Debayan Gupta Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14663v1 Deep neural networks are highly over-parameterized, and different parameter values represent the same predictive function. This makes their effective complexity difficult to measure using only the number of parameters or the rank of the Hessian. Singular Learning Theory addresses this issue through the local learning coefficient (LLC), which characterizes the effective complexity of a model near a given solution. Existing methods for estimating the LLC often rely on posterior sampling, which can be computationally expensive for large neural networks. This makes accurate LLC estimation difficult at scale. In this work, we use known structures in the model to simplify the analysis and make LLC estimation more tractable. Specifically, we study the LLC of a graph attention model by exploiting symmetries in both the graph structure and the attention parameters. An analytic framework through a teacher--student setting, and explicit LLC estimates after considering the symmetry--induced degeneracies are developed. --- ### MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks Authors: Sokratis Nikolaidis, Stylianos I. Venieris, Leonidas Malachias, Iakovos S. Venieris Published: 2026-09-13 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2609.14660v1 Split computing constitutes a widely used distributed inference approach, where a lightweight head model is onloaded onto the device and a heavier tail model resides on an edge server, leveraging the growing computational capabilities of modern System-on-Chips while alleviating server load. As intelligent indoor environments such as smart offices grow increasingly populated with diverse IoT devices, a single edge server must simultaneously assist multiple devices, each competing for the same shared inference resources. Without a principled mechanism to manage this shared load, the server is quickly overwhelmed, causing latency SLO violations and rendering server-assisted inference ineffective. In this work, we present MANE, a distributed inference framework that equips the server with a multi-path tail architecture, enabling a dynamic accuracy--throughput trade-off at runtime. By introducing a novel multi-path model architecture, a three-stage training scheme featuring a Joint Head Network Distillation loss and a hysteresis-based scheduler with an equitable device-fallback policy, MANE maintains over 80% SLO satisfaction rate where state-of-the-art onloading methods fail completely, while preserving accuracy 6pp higher than on-device alternatives, across up to 40 concurrent devices. --- ### Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing Authors: Sehwan Park, Taehoon Kim, Geonhee Han, Dohyun Kim, Seung Wook Kim, Paul Hongsuck Seo Published: 2026-09-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.14657v1 While Vision-Language Models (VLMs) excel at visual reasoning, generating structured, editable Scalable Vector Graphics (SVG) remains a fundamental challenge. Existing pipelines predominantly yield flat, semantically agnostic collections of paths, where editing a single object requires manually identifying its constituent paths. To address this, we propose a VLM-driven agentic framework for semantic compositional SVG generation. Our pipeline recursively parses visual scenes into semantic and geometric hierarchies via top-down decomposition, visual grounding, and prompt-driven amodal occlusion recovery, ensuring each component is geometrically complete. Furthermore, we introduce the Semantic SVG Benchmark with human-annotated semantic groups and novel sub-component metrics (Semantic Recall/Precision, PERE) to explicitly evaluate structural compositionality and functional editability. Experiments show that our natively predicted structures surpass the upper bounds of existing flat-generation methods in both grouping quality and editability, while maintaining state-of-the-art visual fidelity. --- ### Evaluating Contextual Bias in CNN Image Classification: Evidence from Agricultural Benchmark Datasets Authors: Abhilekha Dalal, Michael Okonoda, Eder Martinez, Lior Shamir Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14654v1 Convolutional neural networks (CNNs) are typically evaluated using held-out classification accuracy, an approach that presupposes predictions are based primarily on the intended object of interest rather than incidental surrounding context. We test this assumption in CNN-based agricultural image classification by comparing model performance on original images with performance on background-dominated patches extracted from the same images across eight publicly available agricultural benchmark datasets and four widely used CNN architectures. Background-dominated patches were classified above dataset-specific random chance for six of the eight datasets, and substantially above chance for four of them, indicating that contextual information contributes to model predictions for the majority of datasets evaluated. For these four datasets, we further evaluated whether this behavior reflected genuine class-discriminative information or was primarily attributable to class imbalance using macro-averaged precision, recall, and F1 together with class-balanced test subsets. The results show that contextual reliance does not admit a single explanation: class imbalance accounts for a substantial portion of the observed signal for some datasets and architectures, whereas above-chance contextual classification persists after balancing for others. Together with previous evidence from curated object recognition and cancer pathology imaging, these findings support the growing view that contextual bias is a recurring characteristic of CNN-based image classification rather than a phenomenon confined to a single application domain. More broadly, this work provides a systematic framework for quantifying contextual bias across heterogeneous image datasets by combining dataset-specific random-chance baselines, contextual bias categorization, macro-averaged evaluation, and class-balanced robustness analysis. --- ### Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the LLM Context Window Authors: Blake G. Fitch Published: 2026-09-13 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2609.14652v1 Large Language Model (LLM) applications often transfer domain concepts into the model's context informally, through prompt prose, schema dumps, and examples. We show that for database queries, data model concepts pass to LLMs more effectively through representations whose vocabulary terms carry declared, machine-readable semantics (controlled semantics). NLKGQ is a working system and reusable framework that does this for data modeled in a knowledge graph. A formal OWL ontology serves as the transfer mechanism, concentrating the meaning of the data into semantically precise tokens the model can use directly. In a single LLM call, NLKGQ places in the context a system prompt instructing on SPARQL, the complete domain OWL ontology, and a domain-specific prompt addition, together with the user's natural language query. The model then generates the SPARQL query directly, zero-shot. Where the native vocabulary of an existing database or federation of databases is opaque, a wrapper ontology substitutes clean terms and a runtime rewriter restores the native forms. Evaluating on DBLP-QuAD 2.0 showed that its scores depend on the graph snapshot, the endpoint used, and the wording of its machine-generated questions, so we propose DBLP-QuAD 3.1, which maintains the intent of 2.0 while making reference results deterministic, revising reference SPARQL where needed, and rewriting the natural language questions, with a frontier model, to state each reference query's intent clearly and completely. We evaluate on the DBLP-QuAD 2.0 benchmark (57.6% Match under deterministic re-scoring), DBLP-QuAD 3.1 (89.9% Match on 1,000 questions), SemOpenAlex (98% Match against a published baseline's 86% on the identical test set), and neuroimaging metadata (100%). --- ### Optimizing Sparse Outcomes Through Dense Behavioral Signals via Value-Guided Preference Distillation Authors: Ziyi Zhu, Daniel R. Cahn, Thomas D. Hull, Caitlin A. Stamatis, Olivier Tieleman, Guilherme B. Freire, Jinghong Chen Published: 2026-09-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.14648v1 Aligning multi-turn dialogue agents is usually framed as matching turn-level human preferences, yet direct optimization of long-term outcomes is often ineffective and prone to reward hacking. We formulate long-horizon dialogue optimization as a multi-objective reinforcement learning problem and train a multi-head value model that predicts a vector of observed user behaviors across multiple look-ahead horizons. Our findings demonstrate that a scalarized composite of dense auxiliary behavioral signals enables effective credit assignment and optimization of sparse outcomes. However, optimizing unconstrained single-objective proxies might induce policy degradations that are harmful when the agent is exposed to real users. To identify these failure modes prior to deployment, we establish a safety framework combining counterfactual user simulation with a validated dialogue-level outcome model to evaluate preference weightings and policy optimization methods. Finally, we demonstrate that distilling multi-objective value preferences into the policy via reference-anchored preference optimization matches on-policy online RL at a small fraction of its compute budget. Live A/B testing confirms that our distilled policy significantly improves long-term user retention, while simultaneously enhancing the positive behaviors and therapeutic-process markers. --- ### Skill Composition for Legged Robot Reinforcement Learning Authors: Daniel Gigliotti, Flavio Maiorana, Fabio Patrizi, Luca Iocchi Published: 2026-09-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.14647v1 Robots, and humanoid robots in particular, are increasingly competent at individual behaviors, each obtained by training a specialized controller. A specialized skill is quick to train, converges reliably because the problem it faces is narrow, and can be validated on its own, none of which is true of a single end-to-end policy asked to cover everything. What remains fragile is the transition between them. We argue that the composition of independent sub-policies deserves to be treated as a research problem in its own right, rather than as an implementation detail left to whatever mechanism happens to be at hand. Reliable composition is what turns a collection of separate skills into a repertoire that can be used, extended and shared. More fundamentally, if control can be passed between specialized policies safely, and at any moment, the choice of what the robot should do next can be delegated to a component of an entirely different nature, such as a planner, an automaton or a symbolic controller, whose behavior can be inspected in advance. The policies would then only ever have to act, and what the robot can be trusted to do would become verifiable. --- ### CompCQR: Compositional Query Generation for Training-Free Conversational Search Authors: Yunah Jang, Kang-il Lee, Joongbo Shin, Kyomin Jung Published: 2026-09-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.14646v1 Multi-turn interactions with LLMs are becoming increasingly common in information-seeking scenarios. However, user queries are often ambiguous and context-dependent, making them ill-suited for direct use as retriever queries. Conversational query reformulation (CQR) addresses this issue by rewriting the current utterance into a stand-alone query grounded in the dialogue history. Recent LLM-based CQR approaches achieve strong performance; however, their repeated LLM invocations and misalignment with downstream retrievers remain challenges. In this work, we begin from the observation that retrievers are highly sensitive to content ordering: simply reordering the same content can lead to changes in retrieval coverage and performance. Based on this, we propose a novel training-free method that generates a very large number of queries with minimal LLM usage by compositionally combining a small set of atomic components. We further apply LLM reasoning to construct a high-quality document set that balances precision and recall while capturing the user's core intent. Our framework generalizes across both open- and closed-source LLMs as well as dense and sparse retrievers. It achieves strong performance on four widely used conversational benchmarks, with up to 22.5% relative MRR improvement over the previous state-of-the-art baseline with far fewer LLM calls. --- ### Diffusion-Based Generation of Gait Trajectories Authors: Damian Benasco, Juan Carballeira-Lopez, Jaime Ramos-Rojas, Julio S. Lora-Millan, Antonio J. Del-Ama, David Rodriguez-Cianca, Pablo Lanillos Published: 2026-09-13 Categories: cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.14642v1 Generation of musculoskeletal gait trajectories conditioned on patient-specific parameters remains a key challenge for wearable robotics and rehabilitation. Assistive systems such as lower-limb exoskeletons require reference trajectories that adapt to individual morphology and therapeutic goals while preserving biomechanical realism. Traditional approaches rely on hand-crafted gait templates or optimization procedures that scale poorly across subjects and walking conditions. In this work, we explore conditional diffusion models for generating lower-limb joint-angle trajectories conditioned on gait parameters such as step length. We compare a baseline transformer diffusion model with a controllable diffusion transformer variant incorporating adaptive normalization and classifier-free guidance. Experiments on a dataset of 4,590 gait cycles show that diffusion models can generate realistic periodic gait trajectories while enabling some controllability variation in gait characteristics, highlighting their potential for personalized gait synthesis in assistive robotics. --- ### Investigating the Impacts of Generative AI on Information Seeking Authors: Alexi Orchard, Shannon Lodoen Published: 2026-09-13 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.14638v1 This paper is an encore submission of our 2026 journal article "Expertise and Information Seeking in the Age of Generative AI: New Procedures, New Problematics" with an extended discussion for the CSCW 2026 "Broader Impacts of GenAI in Communication" Workshop on October 10, 2026. In the original article, we employ procedural rhetoric to analyze how generative AI chatbots leverage natural language signifiers of expertise and intelligence to influence users' perception of their trustworthiness. In this submission, we extend our conversation in the CSCW community with the goal of cultivating a cross-disciplinary vocabulary for describing, analyzing, and mitigating the risks posed by the integration of generative AI into human communication practices. It is important to develop an understanding of how the procedures surrounding information-seeking practices are informed by users' values, experiences, and expectations - and how these procedures might in future be altered by the emerging turn toward AI "experts" and authority. --- ### DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents Authors: Zhichao Shi, Xuhui Jiang, Wenjie Zhang, Xiaojun Wu, Cehao Yang, Chengjin Xu, Jian Guo, Yuanzhuo Wang Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14637v3 Large language model agents are increasingly deployed for long-horizon task execution, raising a central granularity question for trajectory evaluation: whole-trajectory verification is too coarse to capture concrete failures and their associated evidence in long trajectories, while atomic-step scoring is too fine-grained, noise-sensitive, and computationally expensive. This granularity gap makes a single-reference trajectory paradigm inadequate for assessing the rich space of valid agent execution paths and delays timely feedback and early stopping in long-horizon tasks. To address these issues, we propose DynSTEER, a dynamic stage-wise framework for agent trajectory evaluation. DynSTEER bridges the granularity gap through stage-wise dynamic evaluation that segments rollouts at key execution nodes and adapts its multi-level review strategy based on stage-level results; it compiles a path-tolerant milestone graph from available task inputs to preserve diverse legal paths without reference leakage; and it supports terminating unrecoverable agent executions to curb resource waste. Experimental results show that DynSTEER improves evaluation discriminability by over 85\% compared with whole-trajectory evaluation and saves 17.74\% of execution steps. The code is available at https://github.com/zhichao-stone/DynSTEER --- ### Know When to Stop, Where to Restart: Accelerating Multi-Turn Agentic On-Policy Distillation Authors: Zhiyu Gui, Kexin Huang, Jia Guo, Junkang Wu, Zihao Wang, Zhiqiang Zhang, Jun Zhou, Jiancan Wu, Xiang Wang Published: 2026-09-13 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.14636v1 On-policy distillation (OPD) has become a standard approach for transferring capabilities from large teachers to compact students. Its cost, however, is dominated by autoregressive student rollouts and scales poorly in multi-turn agentic settings. Existing acceleration methods truncate or relocate the supervision signal according to fixed, offline budgets, despite substantial variation in teacher-signal reliability both within and across trajectories. Our empirical analysis on $τ^2$-bench reveals a clear structure in this variation: informative supervision is concentrated in the prefix of each turn, and, most importantly for multi-turn agentic training, the cross-turn loss of teacher endorsement is temporally locked to the student's first erroneous action rather than accumulating gradually over turns. Building on these findings, we propose STRIDE (Stop-and-Restart on-policy Distillation acceleration), which combines two complementary techniques: adaptive early stopping, which terminates a rollout once the cumulative teacher log-probability falls below an out-of-distribution threshold, and a prefix buffer, which caches high-quality prefixes and restarts generation at the weakest correct turn. Together, these mechanisms induce a data-driven curriculum that progressively extends coverage to later turns. On $τ^2$-bench retail, our method matches full-trajectory OPD and exceeds the 30B teacher at a $3.73\times$ speedup, surpasses the baseline itself at $2.34\times$, and retains a $4.51\times$ speedup under cross-domain multi-teacher training. As a supplementary generalization test beyond the agentic setting, STRIDE outperforms full OPD on AIME 2025 at a $5.10\times$ speedup and on AIME 2024 at a $3.08\times$ speedup; averaged across the two evaluations, both fixed-budget truncation baselines remain below full OPD. --- ### SCOUT-SLAM: Structurally-Coupled Dual Uncertainty-Aware 3DGS SLAM in the Wild Authors: Kumaran Karthik, Pramat Shastri Jois, Suresh Sundaram Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14634v1 Recently, 3D Gaussian Splatting SLAM (3DGS-SLAM) has gained significant momentum in simultaneous localization and 3DGS scene reconstruction. In real-world scenarios with rapid camera motion and cluttered dynamic environments, existing methods rely on the stability of the underlying scene reconstruction to model uncertainty. This leads to a circular dependency between camera tracking accuracy and reconstruction quality: reconstruction instabilities degrade uncertainty modeling, which affects accurate camera tracking and static scene reconstruction. To address this, the paper proposes SCOUT-SLAM, a structurally-coupled dual-uncertainty framework in which both uncertainties are estimated from a shared base network. A low-rank adaptation of this network, trained on multi-view feature consistency, estimates a tracking uncertainty that does not depend solely on the reconstruction quality. A spatially-adaptive prior modulates the network's training objective so that reconstruction instability does not inflate uncertainty on static regions, keeping the shared representation intact for both branches. Evaluations on dynamic benchmarks (TUM RGB-D, Bonn Dynamic, Wild-SLAM MoCap) demonstrate that SCOUT-SLAM achieves state-of-the-art camera tracking accuracy and artifact-free static scene reconstruction. --- ### TTDF: A Two-Stage Framework for Reliable Surgical Phase Transition Detection Authors: Yushi Guo, Pietro Valdastri, Duygu Sarikaya Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14624v1 Reliable workflow transition detection is important for context-aware surgical assistance and downstream decision support. However, online surgical phase recognizers primarily focus on frame-wise accuracy and temporal consistency, rather than the reliability of workflow transition events. Directly converting phase changes into events is unreliable: temporal jitter and workflow-illegal switches produce false or duplicate events, while persistent, workflow-consistent candidates may remain incorrect. To address this limitation, we formulate reliable workflow transition detection as a distinct event-level task operating on outputs of a frozen online phase recognizer. We propose the Two-Stage Transition Detection Framework (TTDF), a causal framework that progressively filters transition candidates. Transition Candidate Extraction (TCE) first applies a minimum-duration requirement and a workflow-graph constraint to remove false candidates caused by temporal jitter and phase transitions not allowed by the workflow graph. Specifically, a candidate is retained only if the predicted target phase persists for a minimum duration and the ordered phase pair belongs to the workflow graph's allowed transition set. TCE thereby produces a high-recall candidate set without additional training. Transition Candidate Verification (TCV) suppresses remaining false candidates using phase-posterior shifts and visual-change cues from frozen DINOv2 features. Events are assessed using a phase-pair-aware one-to-one matching protocol. Experiments on Cholec80 show that TTDF reduces false transition emissions while preserving recall and controlling decision delay. --- ### ESAFusion: LiDAR--4-D Radar Fusion via Local Geometric Complementation and Multiscale Adaptive Interaction for 3-D Object Detection Authors: Gang Ma, Senjie Hu, Junjie Liu, Chao Wang, Hui Wei Published: 2026-09-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.14619v2 LiDAR--4-D radar fusion combines accurate spatial geometry with motion and reflectivity cues from radar, offering a promising solution for 3-D object detection in complex driving environments. However, sparse radar observations and differences in spatial sampling between the two modalities complicate reliable cross-modal complementation. Moreover, the relative importance of modalities and feature scales varies across spatial regions, making adaptive fusion challenging. To address these challenges, we propose ESAFusion, an evidence-aware and scale-adaptive framework that combines local geometric complementation with multiscale adaptive interaction. Specifically, we introduce an Evidence-Aware Radar Selection (ERS) module to suppress radar clutter using motion and observation-quality evidence while retaining foreground confidence for subsequent fusion. Then, the Pillar-Level Complementary Encoder (PCE) improves cross-modal complementation under mismatched spatial sampling using local geometric support from neighboring LiDAR pillars. We further design an Intra- and Inter-Scale Adaptive Fusion (ISAF) module to adaptively adjust the contributions of different modalities and feature scales in bird's-eye-view (BEV) space. Extensive experiments on the View-of-Delft (VoD) dataset show that ESAFusion achieves the highest mean average precision (mAP) among the compared methods, reaching 74.60% in the Entire Annotated Area and 88.89% in the Driving Corridor. It also attains the highest average precision (AP) for Cyclist among these methods in both regions while running at 19.23 FPS. Evaluations on VoD-Fog further demonstrate robustness under progressively degraded LiDAR observations. The source code will be made publicly available at https://github.com/SenJieHu549/ESAFusion. --- ### Channel-Adaptive Region Adjacency Graph Carriers for Semantic Image Communication Authors: Karim Abdallah, Maria Slim, Mariette Awad, Hadi Sarieddeen Published: 2026-09-13 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.14616v1 Semantic image communication seeks to preserve task-relevant scene structure under limited channel resources, but carriers are often dense latent tensors or grid-aligned semantic layouts that do not explicitly encode region-level relations. This work introduces a segmentation-derived region adjacency graph (RAG) carrier, termed channel-adaptive RAG (CA-RAG), for joint source-channel coding-style image communication. Nodes store interpretable region attributes, edges preserve adjacency, channel-adaptive graph simplification (CGS) controls the node budget, and semantic belief propagation refines noisy graph embeddings before diffusion-based reconstruction. On Cityscapes, pre-channel RAG payloads are several times smaller than compressed class-index layouts in a 2,000-image study. Under additive white Gaussian noise at signal-to-noise ratios from 0 to 15 dB, CA-RAG reports higher semantic consistency than deep joint source-channel coding and a same-decoder layout baseline, with comparable perceptual quality. At 10 dB, the full-budget rate-sweep point reaches mean intersection over union (mIoU) = 0.329 at approximately 3.3 x 10^3 channel uses, while the default adaptive-CGS setting reports mIoU = 0.294 at approximately 2.6 x 10^3 channel uses. --- ### Open-UniMo: Towards Unified Motion-Language Understanding and Generation in the Open World Authors: Guocun Wang, Kenkun Liu, Guorui Song, Jing Lin, Zhe Huang, Luyuan Zhang, Dake Zhong, Choo Sin Wai, Xiaoguang Han, Haoqian Wang Published: 2026-09-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.14615v1 Unified motion generation and understanding is crucial for embodied AI systems that can both synthesize and interpret human actions in open-world environments. Existing motion-language models often treat motion as an auxiliary modality of a language model, leading to text-dominated representations and limited cross-modal interaction. Moreover, the next-token prediction paradigm is not naturally suited to long motion sequences, where autoregressive generation may accumulate prediction errors. To address these challenges, we propose Open-UniMo, a unified Large Motion-Language Model (LMLM) trained on million-scale open-world motion-language data. Open-UniMo promotes modality parity by extending Qwen's vocabulary of about 150K text tokens with 64K motion tokens, enabling motion and language to share a unified token space. We further introduce motion-consistent Chain-of-Thought reasoning as an intermediate representation to bridge language semantics and motion dynamics. Open-UniMo is trained with a two-stage pipeline, where supervised fine-tuning establishes CoT-guided bidirectional motion-language mapping and Group Relative Policy Optimization (GRPO) improves semantic alignment while mitigating cumulative errors in autoregressive motion-token generation. To support comprehensive evaluation, we propose Open-MoBench, a VLM-guided benchmark for assessing text-to-motion (T2M) generation, motion-to-text (M2T) understanding, and bidirectional consistency. Extensive experiments show that Open-UniMo achieves state-of-the-art performance on both conventional metrics and Open-MoBench. Furthermore, ablation studies reveal that M2T understanding is not primarily limited by motion-token vocabulary size; instead, coupling M2T with the learnable T2M generation path yields stronger cross-modal representations, demonstrating that generation can facilitate understanding in AR-based motion-language modeling. --- ### SH-WRNN: Implicit Spherical Harmonics Weight Field Routing Neural Networks for Asymmetric Edge Intelligence Authors: Zhibin Jiao, Xiangjing An Published: 2026-09-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.14614v1 Deep learning architectures remain rigidly built upon traditional fully connected layers. While networks scale up, few challenge this foundational root. In this work, we reshape this paradigm by transforming the core synapse weight matrix from static, discrete parameters into a differentiable, continuous field governed by spherical harmonics functions. We introduce the Implicit Spherical Harmonics Weight Field Routing Neural Network (SH-WRNN), which constrains weight matrices within a continuous parametric field instead of optimizing millions of localized discrete weights. When retrieving the weight matrix of the current layer, connection parameters are localized using latitude and longitude on a rectangular plane mapped from the continuous field. The latitudinal coordinate is specified by activated neurons from the previous layer, while the longitudinal coordinate is determined by keys generated from previous layer activations via matrix multiplication. By evaluating intersections on this map, the network dynamically extracts its connection weights on-the-fly. Empirical validation on MNIST demonstrates that under compact configurations of (32, 10, 10) and (32, 3, 10), SH-WRNN achieves robust accuracies of 91.05% and 81.54% within a single training epoch. Furthermore, we propose an asymmetric Surface Baking scheme. Upon convergence, the continuous weight field is baked once into a static parametric surface. By eliminating analytical spherical harmonics calculations during inference and reducing dynamic matrix extraction to high-speed localized memory slicing, this scheme achieves asymmetric algorithmic acceleration with negligible accuracy degradation. This paradigm shift bypasses GPU memory-bandwidth monopolies, opening a novel path to reshape the advantages of CPU computing. Code is available at https://github.com/jzb1111/SphericalHarmonyRoutedNeuralNetWork. --- ### A note on goal-based hierarchical RL Authors: Kevin Murphy Published: 2026-09-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.14605v1 The agent-centric general value function (ACGVF) construction of \citet{tasse2026goal} lets the agent make two decisions that are normally imposed by the environment or agent designer: which goal to pursue and when to declare a goal as finished (in addition to choosing the action). This is a very general framework that subsumes almost all prior work on reinforcement learning, control and planning, as well as more general formalisms proposed in the cognitive sciences. However, it assumes the environment is fully observed, i.e., that the observation is a sufficient statistic. In \citet{murphy2025rl}, a general agent design was proposed where the policy is based on an internal belief state $z_t$ and an internal goal; however, the goals were assumed to be externally provided. In this note, we unify and extend these two approaches using the formalism of hierarchical hidden Markov models (HHMM) \citep{murphy2001hhmm}. --- ### Direct Conditional Transition Sampling for Diffusion Inverse Problems Authors: Qi Yu, Hanlin Wu, Xiaohui Sun Published: 2026-09-13 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2609.14596v1 Training-free diffusion inverse solvers typically choose between local measurement guidance and costly clean-space posterior updates. Independent posterior refresh can improve global correction by sampling a clean conditional and re-noising it, but its practical realization requires probability-flow ODE integration and clean-space Markov chain Monte Carlo (MCMC). We propose Direct Conditional Transition Sampling (DCTS), a direct stochastic-flow approximation to the same ideal refresh target. Rather than explicitly drawing a clean sample, DCTS estimates the measurement-conditioned clean mean along a short inner path and transports Gaussian source noise directly to the next noisy state. A denoiser-compatible sufficient statistic and a covariance-scaled operator update enable this conditional-mean estimation. Experiments on four inverse problems demonstrate that DCTS achieves competitive reconstruction quality with up to $16.8\times$ speedups over competing methods. --- ### Diagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum Description Length Authors: Sebastian Buschjäger, Michael Frichert, Daniel Kuhe, Jian-Jia Chen Published: 2026-09-13 Categories: cs.LG, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2609.14595v1 Multichannel time-series classification commonly assumes synchronized sensor streams, although latency, clock drift, and preprocessing can introduce relative delays during data collection or after deployment. Existing synchronization solutions are often hardware-specific and difficult to apply retrospectively. Consequently, synchronization problems may remain undetected while classification performance is suboptimal. We introduce a classifier- and label-free diagnostic based on minimum description length (MDL). Our method applies candidate temporal shifts to sensor groups and measures how efficiently one group can be encoded through a representation of the remaining channels. An increased codelength indicates that the shift destroys shared temporal structure, whereas the minimum identifies the alignment most strongly supported by the data. Unlike learned synchronization methods, the diagnostic requires neither retraining nor a trusted aligned reference and can therefore test both training and deployment data for misalignments. Experiments on two controlled synthetic tasks and nine real-world datasets show that the metric exposes alignment structure and can recover accuracy under induced deployment drift. A whole-dataset audit further identifies stable nonzero MDL optima in established benchmarks including FordChallenge, Opportunity, PAMAP2, and UCIActivity, revealing potential systematic offsets that conventional model evaluation does not expose. Our method thus provides a general-purpose tool for detecting, understanding, and correcting temporal misalignment throughout the time-series learning pipeline. Our code is available under https://github.com/sbuschjaeger/mdl-temporal-misalignment. ---