# Research Papers — 2026-09 · bundle page 169 of 266 > Full-text markdown of papers #8401–8450 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/169 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/168.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/170.md) ### Robust Multi-Model Fitting through Learning Neighbor Regions Authors: Chang Nie, Guangming Wang, Zhe Liu, Hesheng Wang Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15348v1 Multi-model fitting involves fitting multiple models accurately in a noisy environment. It is the basis for computer vision tasks such as scene reconstruction and mixed reality. However, its performance is often limited by insufficient feature utilization, inefficient optimization, model overlap, and the non-differentiable pipelines. To overcome these limitations, we introduce a robust coarse-to-fine framework called Learning Neighbor Regions (LNR). Recognizing that substantial computational resources are wasted on numerous bad minimum sets, we propose the coarse-level module. This module utilizes a neural network to extract and analyze geometric feature of both local point-wise relationships and global contextual information in minimum sets, outputting confidence to pre-select a small number of good minimum sets, thereby enhancing overall efficiency before solving hypotheses. To address model overlap, LNR encodes neighbor region features for each hypothesis in its fine-level module. These region features consist of geometric features of neighboring data points, which can be used by multiple regions simultaneously. This design allows the neural network to individually refine and score each hypothesis. Importantly, LNR is trained to learn directly from data point features rather than from the hypothesis parameters, thus avoiding differentiating the sampling process and the model solvers. Extensive experiments on four classic multi-model fitting tasks demonstrate that LNR achieves state-of-the-art performance. The analysis suggests that LNR can be easily adapted to various robust multi-model fitting tasks. --- ### Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series Forecasting Authors: Tamanna Kumavat, Georg Brunner, Kyriakos Flouris Published: 2026-09-14 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.15344v1 We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework, with the goal of understanding which design choices drive effective cross-modal transfer. While language models operate on discrete textual tokens, time series consist of continuous numerical observations with temporal dependencies. To bridge this modality gap, we project fixed-length time-series patches directly into the embedding space of a pretrained GPT-2 backbone, bypassing textual tokenization and treating the Transformer as a generic sequence encoder. Through controlled ablation studies on seven benchmark datasets spanning energy, weather, traffic, and finance, we analyze the effects of (i)~representation strategy (continuous embeddings versus textual serialisation), (ii)~adaptation regime (frozen backbone versus partial or full fine-tuning), (iii)~architectural components such as adapters, pooling strategies, and prediction heads, and (iv)~input context length. Continuous patch-based embeddings consistently outperform textual prompting and randomly initialised backbones. The adapted pipeline attains MASE within the range of specialised forecasting architectures while updating less than 1\% of total model parameters. Results further indicate that freezing the pretrained backbone and training lightweight projection and adapter modules provides a favourable accuracy--efficiency trade-off with stable behaviour across varying context lengths. --- ### A Memristive Synapse for Online STDP Learning and Inference in SNNs Authors: Elia Mateu-Barriendos, Álvaro Gómez-Pau, Daniel Arumí, Rosa Rodríguez-Montañés, Salvador Manich Published: 2026-09-14 Categories: cs.NE, cs.AR, cs.ET arXiv: https://arxiv.org/abs/2609.15339v1 This work presents a fully analog memristive synaptic circuit for online spike-timing-dependent plasticity (STDP) learning in spiking neural networks (SNNs). The proposed synapse integrates a local STDP circuit generating gradual timing-dependent conductance updates directly from pre- and post-synaptic spikes. Learning occurs during normal network operation without requiring external digital control or explicit STDP waveform synthesis. Post-layout simulations of the memristive synapse implemented in a 130 nm CMOS technology show spike-timing-dependent conductance adaptation during SNN operation. A 2x2 SNN simulation further illustrates online neuron specialization through unsupervised learning. --- ### Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models Authors: Peipei Li, Dongsen Zhang, Yuchen Liu, Wenjun Xu Published: 2026-09-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.15338v1 Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational efficiency. In this paper, we propose a Dynamic Semantic Extraction and Inference (DSEI) framework, which achieves segment-level inference within the latent space through a two-stage training strategy. First, we construct a Dynamic Semantic Autoencoder (DSAE) via self-supervised learning. DSAE dynamically extracts segment-level semantics and compresses them into compact latent representations via adaptive semantic weighting and gated fusion. Subsequently, we integrate the DSAE into the LLM architecture and train the model to infer over dense latent space. DSEI substantially reduces both input and generation sequences and significantly enhances inference efficiency. Extensive experiments conducted on the Wanjuan dataset demonstrate that DSEI reduces perplexity by 48% compared to static sentence-level latent inference baseline. Furthermore, compared to standard LLMs using token-level inference, DSEI accelerates inference speed by 2.5$\times$ and reduces memory overhead by 90%. --- ### Query-Conditioned Spherical Centroid Aggregation for Multimodal Retrieval Authors: Ambuj Mehrish, Anindya Nag, Sebastiano Vascon Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15335v1 Multimodal retrieval integrates video, audio, subtitles, and text; however, recent geometric aggregators, such as Gramian volumes, hyperbolic volumes, and spectral objectives, treat all modalities symmetrically. Under a unified evaluation protocol, their joint scores frequently lag behind the strongest single-modality pathway by 1.9 to 27.6 R@1. Controlled analyses attribute this outcome to uniform modality influence. This work introduces Spherical Centroid Aggregation with Learned Adaptive Relevance (SCALAR), a query-conditioned aggregator that assigns relevance-based weights to each available modality before computing a spherical centroid. SCALAR accommodates arbitrary modality subsets and is trained on masked, reduced-arity views using rank-8 LoRA adapters. Across five benchmarks, SCALAR achieves positive aggregation gain on four, reaching +4.0 R@1, while none of the evaluated prior aggregators is positive on more than one. A uniform-weight ablation reproduces the degradation observed with symmetric aggregation. With only 4.8 million trainable parameters, SCALAR attains the highest text-to-video R@1 on three and performs within seed variation of the best result on a fourth. Under test-time modality dropout, SCALAR's representation-stage score surpasses the released GRAM checkpoint at every evaluated masking rate and benchmark by 3.2 to 10.9 R@1. Finally, as modalities are removed, rerankers trained exclusively on complete modality sets increasingly converge toward their video-only pathways, diminishing these representation-level gains and underscoring a limitation of standard two-stage retrieval pipelines. --- ### Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation Authors: Xinyue Xu, Hongbin Lin, Juangui Xu, Hualiang Wang, Lehan Wang, Lijie Hu, Weiyang Liu, Adrian Weller, Xiaomeng Li Published: 2026-09-14 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.15334v1 Medical imaging modalities such as ultrasound and X-ray are widely used in clinical practice, where diagnosis follows a structured, evidence-driven workflow aligned with standardized criteria. While multimodal large language models (MLLMs) show promise for automated medical report generation, most existing systems rely on end-to-end multimodal fusion without modeling clinically defined intermediate attributes, leading to limited grounding and interpretability. To address this issue, we propose CORAL (COncept-grounded ReAsoning with Localization), a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process. CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module. The resulting textual concept tokens are combined with mask-modulated visual features within an MLLM to enable structured report generation and diagnostic prediction. Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs, indicating that concept-grounded reasoning better aligns generation with clinical decision processes. --- ### Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs Authors: Changxin Lu, Xiaoliang Meng, Yu Wu, Rui Huang, Honglin Li, Tao Chen, Kaixuan Zhou, Yadong Shao Published: 2026-09-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.15322v3 Pretrained driving vision-language models (VLMs) integrate visual, route, language, and driving context into rich driving priors, yet their representation objectives remain separated from continuous driving planning. Existing methods typically begin trajectory generation only after the VLM has formed a final condition, leaving depth-wise condition computation outside the stepwise formation of trajectory state. We introduce DiffAdapterVLA, which realizes Planning in the Backbone: it injects explicit trajectory tokens into selected VLM late layers, bringing trajectory state into backbone forward computation, where it co-evolves with driving conditions at different depths. Lightweight layer-wise DiffAdapters organize this computation into recursive trajectory refinement, while asymmetric joint attention preserves directed guidance from the condition stream to trajectory planning. By placing planning within existing backbone computation rather than relying on an independent trajectory planner, DiffAdapterVLA adapts only lightweight trajectory modules to turn existing driving priors into efficient continuous planning capability. NAVSIM results show that it achieves high-quality closed-loop planning with low end-to-end latency using few trainable parameters, and demonstrate that jointly evolving trajectory state and depth-wise driving conditions in VLM late-layer computation effectively realizes continuous trajectory planning. --- ### Hypergraph-Regularized Gramian Volumes for Multimodal Retrieval Authors: Anindya Nag, Ambuj Mehrish, Sebastiano Vascon Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15320v1 Volume-based multimodal retrieval jointly scores a text query with a candidate's video, audio, and subtitle embeddings. While this approach captures higher-order within-candidate alignment, the score remains candidate-local, and semantically related training samples primarily serve as contrastive negatives. This work introduces Hypergraph-Regularized Gramian Volumes (HyVol), a training-time module that incorporates these semantic relations prior to evaluating the original volume loss. Document hyperedges connect the observed modalities of each candidate, whereas semantic hyperedges link candidates whose detached captions are mutual top-k neighbors. A shallow gated hyper-graph network applies residual corrections to the modality embeddings. Presence masks exclude unavailable streams from message passing, and identity padding preserves the determinant of the observed Gram submatrix without feature imputation. As refinement operates on embeddings rather than scores, the same construction applies to both Gram and HyperGram. We remove the hypergraph after training, leaving the backbone-only architecture, original scoring function, and retrieval cost unchanged. We train both backbones on a 150K-clip subset of VAST-27M and evaluate zero-shot performance on six benchmarks. Under the paired protocol, HyVol improves R@1 across all five retrieval benchmarks, with video-to-text gains reaching +8.3 on MSR-VTT and +7.6 on VATEX. Under missing-modality masking, the V2T margin remains positive in all experimental settings, although the T2V margin becomes slightly negative in four. --- ### Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA Authors: Luis M. Sánchez Published: 2026-09-14 Categories: cs.IR, cs.AI, cs.CL, q-fin.GN arXiv: https://arxiv.org/abs/2609.15319v1 Frontier models score well on shallow document/chart reading tasks. In a controlled data-room audit, moving evidence into buried conditions reduced accuracy, increased forced declarations, increased tool calls, and increased cost per correct answer. Confidence and benchmark calibration did not fully capture wrong answers; a documented production incident shows fabricated structural claims can be mixed with accurate numeric tables. Agentic evaluations need claim-level receipts (statement-level provenance, not answer-level scores), condition-aware scoring, and human-adversarial verification - an auditing discipline, not a leaderboard. The setting we measure is financial due diligence; the setting we are building toward next is defense staff work, where the same buried-evidence shape appears. In both, the model is not a party to the consequences; the person who signs is. In plain terms: in the documented cases we examine, agents can pair accurate numbers with confident fabricated explanations, and the burden of proof must therefore move from the model to the evidence trail. --- ### Evaluation Metrics for Safe Reinforcement Learning Authors: Lindsay Spoor, Aske Plaat, Thomas Moerland Published: 2026-09-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.15315v1 Safe reinforcement learning (RL) is commonly formalized as a Constrained Markov Decision Process (CMDP), in which an agent maximizes expected reward while keeping its expected cumulative cost below a specified safety bound. Existing safe RL benchmarks predominantly report whether an algorithm is safe on average, following this expectation-based guarantee. We argue that this convention is insufficient to reliably characterize an algorithm's true safety: it fails to capture how often and how severely the safety bound is violated, whether this holds consistently across tasks and safety bounds, and whether training-time behavior is representative of behavior of the final converged policy. Therefore, we introduce (i) evaluation metrics for safe RL that address each of these concerns and in addition allow for aggregation across tasks and safety bounds. We furthermore define (ii) a safety tier system to systematically categorize and compare algorithms in terms of safety and reliability at both training and for a final policy. Using this framework, we provide (iii) an empirical safety evaluation across multiple safety navigation tasks. Our results show that aggregate metrics, distributional reporting, and task- and safety bound-specific results each reveal information the other metrics cannot. We therefore recommend reporting all three jointly, rather than compressing this information into a single value, as is common practice. We provide SafeRLEval, an open-source evaluation suite to support the reliable characterization of safety in future safe RL research. --- ### The Universe of Universes: Benefit Yield Functions, Implosion Thresholds, and Infrastructure-Aware Optimization in Multi-LLM Systems Authors: Danielle Franklin, Vasu Raj Jain Published: 2026-09-14 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.15314v1 We introduce the Universe of Universes (UoU) framework, which treats the full ecosystem of major large language models (LLMs) as a structured retrieval corpus and proposes a compositional Automated Reasoning (AR) and Machine Learning (ML) architecture for cross-model retrieval-augmented generation. The central contribution is the formal characterization of the Benefit Yield Function (BYF), the marginal performance gain per additional model added to an ensemble, and the identification of the implosion threshold θ*: the ensemble size at which BYF crosses zero and aggregate performance begins to degrade. Existing LLM ensemble and mixture-of-agents systems treat models as responders and aggregate outputs, but do not study performance as a function of ensemble size N across the full model universe. Benchmark research confirms performance plateaus at the individual model level; model collapse literature establishes that iterative training on AI-generated outputs degrades individual model distributions. Neither body of work formalizes the ensemble-level implosion threshold, models Epistemic Hereditary Drift (EHD) at the ecosystem level, or treats AI manufacturing velocity as a co-variable of θ*. The framework has direct implications for DoD multi-model AI acquisition policy and the emerging science of testing AI-enabled systems. --- ### Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation Authors: Daxin Tan, Dehua Tao, Chengxi Deng, Hanlin Zhang, Xiao Chen Published: 2026-09-14 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.15313v1 Autoregressive generation of interleaved text and acoustic tokens is a common approach to spoken-response generation in speech large language models. Although this design enables streaming generation with explicit textual guidance, generated acoustic tokens become part of the context for subsequent text predictions. Given identical speech inputs, we observe markedly lower answer accuracy for the internal text generated in speech-to-text-and-speech (S2TS) mode than for speech-to-text (S2T) responses. We term this discrepancy the \emph{output-mode gap} (OMG). To reduce OMG, we propose \emph{Joint-Output On-Policy Distillation} (JO-OPD), which distills the model's stronger S2T policy into joint generation using student-generated S2TS trajectories. At each text position, the S2T teacher provides soft targets from a text-only projection of the student's preceding outputs, while the student predicts from the corresponding full interleaved history. A preservation objective further regularizes native non-text predictions. Experiments on Step-Audio-2-mini and Baichuan-Audio-Instruct reveal OMG across two interleaved generation architectures. On Step-Audio-2-mini, JO-OPD reduces OMG from 42.87 to 16.26 percentage points on Spoken-MQA and from 29.72 to 13.04 points on speech-rendered GSM8K, with little change in S2T accuracy and substantially larger reductions than matched SFT baselines. ASR-based evaluation further shows a 7.49-point improvement in spoken-answer accuracy on Spoken-MQA. --- ### When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis Authors: Kaiyuan Liu, Qiuyang Mang, Bo Peng, Wenhao Chai, Hanchen Li, Shreyas Pimpalgaonkar, Luke Zettlemoyer, Alex Dimakis, Alvin Cheung Published: 2026-09-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.15309v1 Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to stop. This test-time strategy makes it difficult to measure how agent performance scales. We study open-ended tasks that provide continuous scores for intermediate submissions, making progress observable throughout long trajectories. We propose Elo-per-token analysis, which tracks the best solution found at each token budget and uses a Bradley-Terry model to aggregate within-task orderings into Elo ratings across tasks with different score scales. We apply it to four general-purpose agents on four open-ended benchmarks, with sessions of up to 100M tokens, and to three feedback-driven LLM optimization harnesses in controlled single-task interventions. Independent sampling provides a theoretically characterized reference, for which Elo grows linearly with log compute. Against this reference, agents can initially convert tokens into Elo faster than independent sampling, but their marginal gains diminish and eventually fall below the reference. In contrast, the strongest historical human contestants improve superlinearly over contest time on shared AtCoder Heuristic Contest tasks, providing evidence of continual learning and substantial headroom after agents slow down. We define the scaling inflection point as the per-session budget where marginal Elo gains match the independent-sampling reference. Using this point as the per-session budget, we split 100M tokens across parallel sessions on FrontierCS Polyomino Packing, gaining +264 Elo over one long session and +355 over ten short sessions. --- ### Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding Authors: Yizhou Liu, Fei Tang, Yuchen Yan, Zhengxi Lu, Songqin Nong, Tao Jiang, Wenhao Xu, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15307v1 Graphical User Interface (GUI) grounding is essential for autonomous agents to map natural language instructions to precise screen coordinates. However, existing supervised fine-tuning and reinforcement learning methods are constrained by the high cost of annotation, creating a scalability bottleneck. In this paper, we introduce a label-free test-time training paradigm driven by two key insights: (1) confidence patterns in coordinate tokens are a better indicator than full-sequence confidence, and (2) in sparse GUI coordinate spaces, negative samples offer more reliable learning signals than potentially noisy positive ones. We first propose Confidence-Anchored Learning (CAL), which utilizes coordinate-token confidence to filter pseudo-labels and assign distance-based binary rewards. Building on this, we develop Confidence-Anchored Negative Learning (CANL), which exclusively optimizes the model using negative samples to bypass the risks of incorrect positive samples. Experimental results demonstrate that CANL-7B achieves 92.1% on ScreenSpot-V2. On more challenging ScreenSpot-Pro, CANL-7B reaches 33.8%, an 8.9% absolute improvement over the base model. Our findings establish coordinate-token confidence as a powerful alternative to manual annotations for scalable GUI agent development. --- ### When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning Authors: Sean Bin Yang, Ying Sun, Zongyi Xu, Tung Kieu, Jilin Hu, Bin Yang, Kristian Torp, Hua Lu, Torben Bach Pedersen Published: 2026-09-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.15305v1 Urban region representation learning commonly combines heterogeneous data sources, such as mobility flows, points of interest, and land-use information, to support tasks including mobility analysis, public safety forecasting, and service demand estimation. Existing multi-view methods typically improve region embeddings by strengthening interactions across views. However, such methods often overlook view-specific regional structures and may propagate correlations induced by shared latent factors, which can reduce the stability of downstream predictions. To overcome this major limitation, we propose CURE, a confounder-aware framework for multi-view urban region representation learning. CURE first encodes each view with its regional graph structure, estimates a shared latent component, and then reduces its projected influence before cross-view interaction. A hierarchical graph-aware fusion module subsequently aggregates the residual view representations using local and global regional contexts Experiments on three real-world cities show that CURE improves predictive performance, remains robust under missing and noisy input views, and provides reliable cross-view integration through shared component separation and context-dependent view weighting. --- ### Admissable: Training Reinforcement Learning Agents against Adversarial Missingness Authors: Paul Stahlhofen, Luca Hermes, Tim Kochs, Markus Vieth, Barbara Hammer Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15297v1 In order to make Reinforcement Learning algorithms applicable in real world scenarios, safety must be ensured even under adverse operating conditions. In this work, we consider the challenge of adversarial feature missingness: a scenario in which an adversary occludes features from the agent's observation in order to reduce performance as much as possible. We formally define adversarial missingness for Reinforcement Learning and compare it to the related concepts of $\ell_\infty$-norm bounded adversarial perturbations and learning with missing data. We develop an adversarial training algorithm and show its effectiveness in increasing robustness against adversarial missingness on three MuJoCo benchmark environments. Compared to a baseline trained with random uniform missingness, our method achieves better robustness on all three tasks. --- ### Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings Authors: Mingzhou Jiang, Peixi Wu, Hang Cheng, Yunhao Zhou, Biao Yang, Wei Yuan, Yun Li, Fan Yang, Wenwu Ou, Honghui He Published: 2026-09-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.15296v2 Universal multimodal embedding (UME) maps multimodal inputs into a shared embedding space for diverse retrieval tasks. Recent methods improve embeddings through Chain-of-Thought (CoT) reasoning optimized with GRPO using retrieval rewards. However, existing methods overlook the mismatch bettween candidate-aware retrieval supervision and input-only CoT generation: (1)trajectory-level rewards convey retrieval outcomes without explicitly identifying the input-supported evidence that distinguishes the positive from hard negatives; (2) input-only generation cannot directly assess whether further reasoning improves retrieval, potentially producing redundant CoTs with substantial latency. To bridge this gap, we propose Reason What Matters (ReWAM), a retrieval-grounded framework that aligns candidate-aware supervision with input-only generation. Specifically, we introduce Retrieval-Aware Self-Distillation (RASD), which extracts privileged guidance from input-supported facts and evidence distinguishing the positive from hard negatives. Conditioned on this guidance, an on-policy self-teacher provides token-level feedback to refine credit assignment, directing policy updates toward retrieval-relevant reasoning grounded in the input. We further propose Retrieval-Adaptive Inference (RAI), which learns a retrieval-aware stopping criterion from prefix-level retrieval feedback. It stops redundant reasoning without candidate access and uses speculative decoding to further reduce CoT latency. Extensive experiments on MMEB-V2 and MRMR demonstrate that ReWAM achieves state-of-the-art retrieval performance while delivering up to 5x the inference throughput of competitive explicit-CoT UME methods. ReWAM thus enables high-quality retrieval through efficient input-only reasoning, making explicit CoT practical for corpus-scale multimodal retrieval. The code will be publicly available. --- ### Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures Authors: Yuhang Wang Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15293v3 Binding the audit flag in Reflexion-style agents --- without changing the auditor --- reduces attack success rate substantially, reaching near zero on models whose flags parse cleanly. This single control-flow change exposes the \textbf{enforcement gap}: the controller receives a safety flag and executes anyway. Separating detection probability $p_d$ from enforcement probability $p_e$ establishes that $p_e \approx 0$ by default across every framework we tested, making detection quality \emph{formally irrelevant} to security when enforcement is absent --- a finding consistent with the spontaneous collapses recorded in unsupervised frontier-agent deployments~\citep{emergence2026}. Residual attack success concentrates where flags are unparseable or auditors leak; an RL-trained enforcement controller handles hedged and malformed verdicts that rule-based parsing cannot, cutting ambiguous-critique failure to a fraction of the rule-based baseline. Concurrent filtering and information-flow defenses address detection, not enforcement, leaving the binding constraint untouched. The Audit Enforcement Specification (AES) packages three concrete requirements that close each residue independently; each primitive is adoptable without redesigning the host framework, and no deployed framework currently implements any of them. --- ### ProIQA: A Process-Based Framework for Fine-Grained Math Item Quality Assessment Authors: Junkai Tong, Mingjia Li, Haoran Chen, Yaoyu Jiang, Hanjie Ge, Yixuan Wang, Hong Qian Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15292v2 Automatic Item Generation (AIG) is pivotal for personalized education, yet guaranteeing the pedagogical value of generated items remains a bottleneck. Existing Item Quality Assessment (IQA) methods typically rely on unscalable manual reviews or shallow stem-based metrics, failing to capture the reasoning process required for mathematical problem-solving. To bridge this gap, this paper proposes Process-based Item Quality Assessment (ProIQA), a process-aware framework for fine-grained quality assessment of math items. We first formulate IQA across three heterogeneous dimensions, including knowledge concepts, difficulty, and disciplinary competencies, under a unified process-aware perspective. Based on this formulation, we construct a process-enhanced IQA resource by augmenting original item data with structured reasoning trees derived from raw solutions. Technically, ProIQA leverages Large Language Modelsto construct hierarchical reasoning trees and employs Graph Neural Networks (GNN) to encode their topological dependencies and procedural semantics. The resulting solving representation is fused with stem semantics through a dual-view (``Stem + Solving'') architecture, enabling comprehensive assessment across learning objectives. Extensive experiments on K12 mathematical datasets show that ProIQA effectively captures process-oriented features, offering a scalable data-driven solution for evaluating AIG outputs in intelligent education systems. --- ### Math for AI safety: an invitation for mathematicians Authors: Lionel Levine Published: 2026-09-14 Categories: math.HO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.15289v1 Artificial intelligence threatens to outrun human understanding and control. New mathematics is needed to design AI that is legible, steerable, and cooperative with humanity. I organize this invitation by mathematical field, so you can turn straight to your own: logic and game theory for cooperation; probability for agency and world-models; algebra and representation theory for learned features; analysis and geometry for generalization and training dynamics. Each section ends with an open problem that is accessible to a working mathematician with no prior experience in AI safety. --- ### AlignUS: MRI-Guided Ultrasound Representation Learning for ALS Classification from Tongue Images Authors: Kadija Abdel Ghader, Emani Babe, Lorenzo Pettinari, Meya Haroune, Sidaty El Hadramy Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15285v1 Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease in which early assessment remains challenging, particularly in low-resource settings where MRI is often unavailable. High-resolution ultrasound (HRUS) of the tongue offers a portable and low-cost alternative for evaluating bulbar involvement, but learning reliable diagnostic models is limited by small datasets and the difficulty of extracting robust representations from ultrasound alone. We propose AlignUS, a cross-modal knowledge distillation framework that transfers anatomical knowledge from MRI to a HRUS-based classifier while requiring only HRUS at inference time. The model combines classification loss, supervised contrastive learning, and feature-level distillation to align HRUS representations with MRI embeddings. AlignUS achieves a patient-level balanced accuracy of 0.958, macro-F1 of 0.963, and ROC-AUC of 0.990, aggregated across four patient-level cross-validation folds, with consistent improvements over HRUS baselines and cross-modal alternatives. These results demonstrate that MRI-derived supervision can substantially improve ultrasound-based ALS assessment while preserving low-cost, inference-time independence from MRI. --- ### Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data Imputation Authors: Sergei Kholkin, Kirill Sokolov, Dmitry Baranchuk, Evgeny Burnaev, Alexander Korotin Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15284v1 Missing values are ubiquitous in heterogeneous data mining, where numerical, categorical, and binary variables often coexist. Many imputation methods, especially diffusion-based ones, treat discrete variables through continuous surrogates such as one-hot relaxations rather than modeling them natively. This creates a mismatch between the model state space and the mixed discrete and continuous structure of the data. We propose Impute-EM, an Expectation Maximization style framework that alternates between imputing missing entries with the current model and refitting a diffusion backbone on completed data. We instantiate Impute-EM with native mixed-state diffusion backbones for heterogeneous data, combining Gaussian and masked categorical components without one-hot relaxations. In exact settings, we characterize the update and show that the observed mask-indexed marginals match the targets at the limit, while making explicit that the full data distribution is generally non-identifiable from incomplete observations alone. Empirically, Impute-EM delivers the best distributional fidelity on mixed-type tabular imputation, on which downstream modeling relies, with text imputation serving as a controlled validation of the native discrete backbone. --- ### Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs) Authors: Christian Fisch, Angela Altmeier, Martin Obschonka, Michal Kosinski, Pin Ni Published: 2026-09-14 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.15277v1 Entrepreneurial cognition is a foundation of entrepreneurship research. Yet the growing involvement of large language models (LLMs) in entrepreneurial work extends the cognition question beyond human actors to systems whose internal representations remain largely unexplored. We introduce artificial entrepreneurial cognition, the functional organisation of entrepreneurship-relevant representations and computations inside artificial intelligence (AI) systems. We bring mechanistic interpretability into entrepreneurship research through representation engineering. Focusing on opportunity recognition (OR), we construct 636 matched OR-present and OR-absent scenario pairs and recover an OR direction in Llama 3.1 8B-Instruct. Rather than infer the construct from outputs, we intervene directly on this direction, steering the model up and down along what we call the opportunity recognition dial, and its opportunity judgments shift with it. To our knowledge, this is the first causal intervention on an internal representation of an entrepreneurship construct inside an LLM. Held-out tests, lexical and topical controls, behavioural ablation, and geometric comparisons show that the direction is recoverable, consequential, and distinct from the opportunity evaluation and exploitation directions, although steering it also shifts judgments about these neighbouring stages. Recovery, signed steering, and geometric separation hold across four additional LLMs spanning different scales and families. These results give the contested distinction between opportunity recognition and evaluation a concrete representational form inside AI systems. More broadly, they establish internal representations as a new object of entrepreneurship inquiry and show how entrepreneurship theory can guide their identification, causal manipulation, and interpretation. --- ### Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks Authors: Masoud Ataei, Mohammad Javad Khojasteh, Vikas Dhiman Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15274v1 Kolmogorov-Arnold Networks (KANs) with spline activations have recently shown promise for interpretable function approximation. Distance-Aware Error for Kolmogorov Networks (DAREK) introduces a computationally efficient bottom-up approach to uncertainty quantification by equipping KANs with distance-aware error bounds; yet, in high-dimensional settings, the theoretical guarantees can be weakened by the emergence of fictitious knots. Inspired by the Kolmogorov-Arnold representation theorem, DAREK adopts a componentwise formulation in which each input dimension is treated separately; as a result, induced knot locations may appear in the combined input space without corresponding to actual training data. These fictitious knots mislead the DAREK uncertainty estimator into reporting low uncertainty far from any real observation, violating the distance-awareness guarantee. We identify this failure mode precisely, characterize its geometric structure, and propose a drainage uncertainty mechanism that restores distance-awareness by constructing a monotonically decreasing uncertainty path from any fictitious knot region toward the nearest real knot. The proposed drainage method provides a practical heuristic correction that mitigates the fictitious-knot failure mode while restoring theoretical distance-awareness in high-dimensional settings. Experiments on a 2D synthetic benchmark and a 100-dimensional face dataset show that drainage raises sampled distance-awareness (SDA) from 85% to 98-99%, matching Gaussian processes at lower computational cost. --- ### Learning CNF Formulas from Uniform Random Solutions: Near-Tight Sample Complexity for Valiant's Algorithm Authors: Weiming Feng, Yixiao Yu, Yiyao Zhang Published: 2026-09-14 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2609.15268v1 We revisit Valiant's algorithm (Commun. ACM'84) for learning $n$-variable CNF formulas with clause size $k$ and variable degree $d$ from i.i.d. uniform random solutions in the local lemma regime. For fixed $t\geq1$, under $k\gtrsim(1+1/t)\log d$, Valiant's algorithm achieves total variation error $\varepsilon$ with $\widetilde{O}(n^{\lceil t \rceil}/\varepsilon)$ sample complexity. For $t>1$, we prove a matching lower bound for Valiant's algorithm. At $t=1$ (covering $0<t<1$), we show Valiant's algorithm has optimal sample complexity up to logarithmic factors by an information-theoretic lower bound $\widetildeΩ(n/\varepsilon)$. --- ### Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities Authors: Jun-Hyun Kim, Ahmet Alacaoglu Published: 2026-09-14 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2609.15257v2 We analyze a stochastic algorithm with Halpern-type anchoring for constrained convex-concave problems and monotone variational inequalities. This single-loop and single-call algorithm uses one unbiased sample of the gradient operator at every iteration, to be applicable to monotone games with noisy feedback. With $t$ denoting the iteration counter, we prove an anytime last-iterate convergence rate of $O(t^{-1/4})$ for both the gradient-mapping norm and restricted gap, bypassing the $O(t^{-1/5})$ constrained-anytime bottleneck in the literature. Specializing then to multi-point oracles, we use variance reduction to achieve the $O(t^{-1/2})$ rate with an anytime single-loop algorithm using $2$ samples per iteration. Our results allow constrained problems with a potentially unbounded feasible set; as well as a structured class of stochastic oracles whose variance need not be uniformly bounded. --- ### BioDCASE: Active Learning for Bioacoustics Authors: Ben McEwen, Rupa Kurinchi-Vendhan, Shiqi Zhang, Lukas Rauch, Marek Herde, Sara Beery Published: 2026-09-14 Categories: cs.LG, cs.SD arXiv: https://arxiv.org/abs/2609.15255v1 Ecological monitoring increasingly relies on machine learning models, whose performance depends on the quality and quantity of labelled data. However, obtaining these labels is costly, particularly in passive acoustic monitoring, where vast amounts of data are collected but only a small proportion can feasibly be annotated. Active learning addresses this bottleneck by prioritizing which samples should be labelled. However, progress is difficult to measure, because published methods are evaluated under different models, budgets, evaluation metrics and datasets. To address this challenge, we present the 2026 Active Learning for Bioacoustics BioDCASE challenge: a systematic evaluation of sampling methods designed to identify effective AL strategies. Participant methods were evaluated across four subsets composed of terrestrial and marine data. Across ten proposed sampling methods from seven teams, the top-ranked method achieved an area under the learning curve 26.4 % higher than random sampling at the same annotation budget, averaged over four data subsets. Significant variation in performance was observed across subsets, with the top-performing submission achieving a 67.1 % gain for the HSN subset over random sampling and a gain of 8 % for the ATBFL subset. Top-ranking submissions combined multiple acquisition signals, and diversity-based selection outperformed pure uncertainty sampling. Furthermore, there is evidence that transitioning from diversity-based to uncertainty-based selection and explicitly reducing redundancy within acquisition batches improve model training. There is also initial evidence that larger acquisition batch sizes may be increasingly beneficial later in the labelling process. --- ### Conformal Individual Treatment Effect Estimation under Networked Interference Authors: Matteo Zecchin, Osvaldo Simeone Published: 2026-09-14 Categories: stat.ML, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2609.15254v1 Conformal counterfactual prediction constructs prediction sets with finite-sample coverage guarantees for counterfactual outcomes and individual treatment effects under the no-interference assumption. In this work, we relax this assumption by allowing each unit's potential outcomes to depend on other units' treatments and covariates. In this setting, propensity-score reweighting does not restore weighted exchangeability, and existing methods may fail to achieve valid coverage. To address this issue, we develop interference-adjusted weighted conformal prediction that accounts for interference by constructing an observable upper bound on the ideal and unobserved conformal $p$-value under the target intervention. The resulting prediction sets provide finite-sample marginal coverage guarantees for counterfactual outcomes and individual treatment effects in both transductive and inductive settings. We also derive a sharper construction when intervention-induced changes in nonconformity scores are bounded. Numerical experiments show that our methods preserve nominal coverage, whereas existing methods may not. --- ### Bandits with Probing: Optimal Regret and the Limits of Winner Feedback Authors: Yongjie Guan Published: 2026-09-14 Categories: cs.LG, cs.DS, stat.ML arXiv: https://arxiv.org/abs/2609.15248v1 A learner probes at most $k$ of $n$ arms each round, receives the maximum of their rewards in $(0,1)$, and competes with the best fixed arm. When does the probing advantage pay for learning? We determine two minimax laws. Under independent stochastic rewards with winner feedback (the maximum and a winning label), or on arbitrary fixed sequences given a single signed contrast between block maxima, the minimax regret has order $Φ_{n,k}(T)=\min\{\frac{n-k}{n}T,\frac{n-k}{k}\}$, $2\le k<n$. Under winner feedback, both arbitrary joint i.i.d. rewards and fixed sequences have minimax regret of order $R_{n,k}(T)=\frac{n-k}{n}\min\{T,\frac{n+T}{k},\sqrt{\frac{nT}{k}}\}$. Both laws have universal constants and anytime upper bounds. The first reduces regret to a pure coverage cost: same-round contrasts absorb the stability cost, and independence permits exact resampling whose gains fund sample advancement. The second adds a learning cost that becomes comparable to coverage at horizon $n$; beyond $nk$, numerical maxima improve over labels alone. The lower bound allows every adaptive action size. --- ### Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain Authors: Motaz Saad, Anna Borrelli, Ivan Gentile, Kianna Kazemi, Francesco Piccialli, Antonella Longo Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15242v1 Environmental, Social, and Governance (ESG) reporting is critical for corporate accountability, with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) offering strong potential to automate KPI extraction. However, open-source LLM performance in domain-specific ESG tasks remains insufficiently understood. This paper evaluates open-source LLMs in ESG contexts using a structured framework and evaluation resource based on 498 real-world ESG reports from EU-listed companies (2010-2024). We evaluate seven open-source models (2B to 30B parameters) -- glm-4.7-flash, nemotron-3-nano:4b, qwen3:4b-instruct, gemma3:4b, gemma4:e4b, gemma4:e2b, and ministral-3:8b -- using 100 persona-based synthetic QA pairs covering ESG information needs. System performance is assessed via RAGAS metrics, including contextual recall, precision, relevance, faithfulness, answer relevancy, and factual correctness. Results show notable performance variations across architectures. Retrieval performance is strong across models (context recall around 0.58-0.61, context precision around 0.78-0.81, context relevance 0.965-0.985). Generation diverges most on faithfulness (0.607-0.822) and least on answer relevancy (0.760-0.881): glm-4.7-flash leads in faithfulness (0.822), qwen3 in factual correctness (0.449), and ministral-3 in answer relevancy (0.881). Low overall factual correctness (0.387-0.449) highlights the need for domain-specific fine-tuning. This work provides data-driven guidance for deploying open-source models in ESG reporting. --- ### A 25-$μ$s/inf Event-driven Graph Neural Network Processor with Spatiotemporal Caching and Spline Convolution for Ultra-low-latency AI at the Edge Authors: Adrian Kneip, Martin Lefebvre, Daniel Gehrig, Victoria Catalán Pastor, Davide Scaramuzza, Marian Verhelst, Charlotte Frenkel Published: 2026-09-14 Categories: cs.CV, cs.AR arXiv: https://arxiv.org/abs/2609.15241v1 Dynamic-vision-sensor (DVS) cameras generate events on a per-pixel basis with a $μ$s-level temporal resolution, calling for new algorithm-hardware co-design approaches compared to standard frame-based vision. While event-driven graph neural networks (EV-GNNs) emerge as a promising algorithmic solution, they raise new HW challenges by mixing dense-regular compute operations and sparse-irregular memory accesses. We present ETHEREAL, the first EV-GNN accelerator that scales to 640$\times$480 resolutions, thanks to a neighbor-parallel spline convolution engine and a 2D/3D-split memory hierarchy with a novel region-of-interest spatiotemporal caching mechanism. Measurement results demonstrate end-to-end inference with 25.6$μ$s latency and 1.7$μ$J energy per event on state-of-the-art workloads --- ### ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation Authors: Salvatore Romano, Marco Grassia, Pietro Liò, Giuseppe Mangioni Published: 2026-09-14 Categories: cs.LG, cs.AI, physics.soc-ph arXiv: https://arxiv.org/abs/2609.15239v1 Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the conditioning mechanism to the trained model. Classifier guidance avoids this coupling in continuous domains by steering a frozen model with a classifier's gradient, but discrete graph diffusion samples discrete edge states, so gradients cannot propagate through the sampled graph. We introduce ProtoGuide, a post-hoc, backbone-agnostic framework that recovers an analogous mechanism. At each reverse step the denoiser's per-edge output is relaxed into a differentiable soft adjacency, embedded by a frozen Siamese graph neural network, and scored against a target-class prototype and its nearest competitor; the resulting per-edge gradient, damped by a cosine schedule, is injected back into the denoiser output. All components stay frozen, so guidance is retargeted by supplying a different prototype. On five classes of real-world networks and two architecturally different backbones, EDGE and DiGress, ProtoGuide raises macro classification accuracy from 50.7% to 73.5% and from 73.6% to 83.8%, and outperforms DiGress's built-in conditional training under our configuration. Gains are largest where the unguided models are weakest, and are not uniform across classes. Per-graph coverage remains high in most settings, while distributional effects are class-dependent. A Best-of-N selection baseline matches this accuracy given enough oversampling, but at a substantial cost in graph diversity. An independently initialized classifier, a directionality test, and a few-shot analysis support target-directed steering and robustness to very small support sets. --- ### CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning Ability Authors: Keuntae Kim, Eunhye Jeong, Yong Suk Choi Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15234v1 Recently, Large Language Models (LLMs) have gained significant attention due to their strong language understanding and generation capabilities, demonstrating impressive reasoning abilities as well as effective utilization of external knowledge. Many studies have proposed methods that specialize in improving performance for individual tasks. However, ironically, only a limited number of attempts have explored general-purpose, task-agnostic methods. In this work, we present a unified framework integrating reasoning and Retrieval-Augmented Generation (RAG) tasks. We further propose Controllable White-Box Meta-Prompting (CWM), a low-cost white-box method for adaptive RAG tasks previously dominated by black-box approaches, without requiring external decision modules or multi-sampling. CWM achieves state-of-the-art performance on three adaptive RAG benchmarks across recent LLMs, including GPT-oss-20b, Qwen3-14b, and Llama3.1-8b, while also demonstrating strong generality by extending to reasoning tasks. In addition, CWM provides controllability by enabling retrieval decisions to be regulated through the manipulation of internal model signals. Our code is available at https://github.com/JeongEunhye00/CWM. --- ### Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders Authors: Qingtao Xia, Jiahua Bao, Siyao Cheng, Jie Liu Published: 2026-09-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.15229v1 We propose a pre-fine-tuning probing method for Parameter-Efficient Fine-Tuning (PEFT) layer selection, aiming to obtain more stable and higher gains with fewer trainable parameters when adapting large vision--language models (VLMs). Unlike the common practice of applying LoRA and other adapters to all layers at once---where layer selection often relies on heuristic rules---we focus on the vision encoder and directly evaluate the "adaptability'' of each Transformer layer. Specifically, we characterize each layer from two perspectives: (i) the statistical properties of its Q/K/V projection weights (e.g., norms and condition numbers); (ii) robustness under controlled parameter perturbations. We then systematically compare these indicators with the downstream performance gains brought by applying PEFT to a single layer. Across experiments covering seven benchmarks and five PEFT variants, we observe a consistent correlation: layers (or matrices) with larger weight norms and higher condition numbers are usually more robust to perturbations and are more likely to yield larger fine-tuning gains. These results show that distribution-statistics analysis and perturbation tests before fine-tuning can provide practical signals for adaptation-layer selection, thereby maintaining or improving performance while reducing trainable parameters. --- ### Unsupervised Point Cloud Registration via Training-Time Semantic Guidance Authors: Kezheng Xiong, Shiyun Xu, Sheng Ao, Siqi Shen, Cheng Wang, Chenglu Wen Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15228v1 Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrades pseudo-label quality and leads to suboptimal convergence, particularly for sparse, low-resolution scans such as those from nuScenes. We reveal that registration models intrinsically encode semantic awareness that strongly correlates with registration accuracy, albeit without explicit semantic supervision. However, this native awareness is fragile: noisy supervision arising from geometric ambiguity in unsupervised settings rapidly erodes the learned semantic structure, causing performance collapse. To this end, we propose CAESAR, a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training. We observe that potential inlier matches are often buried just beneath a few spurious neighbors in the noisy feature space, motivating Dual-Cue Guided Re-Matching to recover them through reselection rather than simply rejecting. Building on this, a train-only Semantic-Geometric Label Mining performs lightweight, batch-specific teacher refinement and mines reliable pseudo-labels under semantic guidance. We further introduce Semantic Predictive Distillation to consolidate the student's semantic awareness in the feature space. Extensive experiments on KITTI and nuScenes demonstrate state-of-the-art performance, with pronounced gains on the challenging nuScenes benchmark. Crucially, CAESAR incurs zero inference overhead and requires no semantic annotations on the registration data. Code will be released. --- ### Closed-form Bayesian homography estimation from noisy point correspondences Authors: Hanne Beuter, Sebastian Dorn Published: 2026-09-14 Categories: cs.CV, stat.ME arXiv: https://arxiv.org/abs/2609.15227v1 While homographies are fundamental to many computer vision tasks, the majority of conventional estimation techniques provide only point estimates without directly quantifying uncertainty introduced by noisy observations. Uncertainty, though, propagates to subsequent processing steps such as camera calibration and 3D reconstruction and is particularly relevant in safety-critical and socially relevant fields including medical imaging, autonomous driving, and defense. We present a fast Bayesian formulation for homography estimation from point correspondences that explicitly incorporates measurement uncertainty and prior knowledge while providing a posterior distribution over the homography parameters. A closed-form solution of the posterior mean of the homography is derived in homogeneous coordinates and supplemented by an iterative Bayesian approach to handle non-linearities. Synthetic experiments demonstrate the applicability to projective transformations and show improved estimation accuracy over DLT under varying noise conditions. Image stitching experiments further demonstrate applicability to real image correspondences while additionally providing uncertainty information. --- ### Deep Learning-based Intelligent Diagnosis of Congenital Uterine Anomalies in 3D Ultrasound Authors: Yueyue Xu, Yuhao Huang, Jiaxiao Deng, Yuanji Zhang, Haoming Zhang, Jiajia Qu, Shiying Zheng, Xiaomei Tang, Haining Chen, Chengcai Chen, Yiyi Wu, Xin Yang et al. Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15225v2 Objective: To develop an intelligent framework, termed CUA-Net, for the automated classification of congenital uterine anomalies (CUA) without requiring coronal plane reconstruction, and to evaluate its clinical applicability. Methods: CUA-Net was built on 3D ResNet-18, equipped with a dynamic data resampling strategy to mitigate the data imbalance issue and a hard sample mining technique to fully learn from the difficult cases by loss adjustment. We further proposed the self-supervised reconstruction to comprehensively explore the volumes and the online data augmentation to refine the wrong predictions and enhance the model's generalization. We compared the CUA-Net with different deep-learning methods and junior/senior sonographers in the testing set. The evaluation metrics included accuracy, precision, recall, F1-score, micro-AUC, and macro-AUC. Results: The proposed CUA-Net exhibited satisfactory performance in both internal and external test sets. In the internal cohort, the model achieved accuracy of 93.88%, precision of 87.01%, recall of 95.92%, F1-score of 88.09%, and micro-AUC of 0.9982 and macro-AUC of 0.9997. In the external set, it maintained good performance with accuracy of 91.52%, precision of 83.27%, recall of 88.63%, F1-score of 81.49%, micro-AUC of 0.9945 and macro-AUC of 0.9990. Our CUA-Net outperformed the junior sonographers across all performance indicators and achieved performance comparable to that of the senior sonographers across most metrics. Conclusion: The CUA-Net demonstrates favorable accuracy and generalizability in classifying common CUA categories, while showing preliminary potential for recognizing less prevalent anomalies. These capabilities may help optimize clinical workflows and support more standardized diagnosis. --- ### Long-to-Short Video Evidence Reasoning for Grounded Question Answering Authors: Kaiyan Chen, Junbin Xiao, Xun Yang Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15224v1 We present LOVER, a \underline{L}ong to sh\underline{O}rt \underline{V}ideo \underline{E}vidence \underline{R}einforced model for grounded question answering (GQA). LOVER highlights three innovations over existing reinforcement-learning (RL) based video reasoning models: (1) \textbf{Long-to-short Video Evidence Curriculum Learning}, which organizes RL training according to evidence duration and progressively adapts the model from long-range grounding to short-term reasoning; (2) \textbf{GQA Rewards}, which underscore the benefit of IoP reward over IoU for evidence spotting rather than strict temporal span overlap; (3) \textbf{Adaptive Timestamp Rendering}, which adaptively renders timestamps onto video frames using background-aware position and color selection to enhance temporal observability. The three designs are model-agnostic and reciprocal. They effectively improve QA, grounding, and grounded QA performance over different backbones. Notably, LOVER built on Time-R1 achieves new state-of-the-art (SOTA) results among open-source models on popular GQA benchmarks: NExT-GQA and ReXTime. Comprehensive ablation studies further validate the effectiveness of our three innovative components. --- ### MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training Authors: Tianyi Xu, Daniel Pimentel-Alarcón, Zuzana Buřivalová, Claudia Solís-Lemus Published: 2026-09-14 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2609.15221v1 Passive acoustic monitoring can measure biodiversity at larger scales, but time--frequency annotation of animal vocalizations is expensive, site-specific, and difficult to sustain at scale. We present a label-efficient sound detection framework that combines masked audio pretraining with a lightweight detector on mel spectrograms, then further improves robustness through iterative self-training on unlabeled audio. We first pretrain a ViT-based encoder on unlabeled recordings via masked reconstruction and transfer the encoder to a detection backbone. To better separate animal sounds from confounding background, we add a box-level contrastive loss that pulls matched event regions together while pushing noisy negatives apart. We then apply a two-stage pseudo-labeling curriculum to exploit large unlabeled pools without additional annotation. We evaluate the performance on two ecologically distinct domains: tropical rainforest soundscapes (Indonesia) and bird vocalizations in Mediterranean habitats (Spain). On both domains, masked audio pretraining and contrastive learning consistently improve time--frequency detection under temporal and cross-site distribution shift, and self-training yields further gains in out-of-distribution performance. On the rainforest domain, MAST with self-training achieves +0.22 mAP and +0.24 F1 over the strongest baseline under cross-site shift. On the bird domain, self-training achieves +0.12 mAP and +0.10 F1 over the strongest baseline under cross-site shift. Overall, our results show that MAST can effectively extend self-supervised audio representations from clip-level tasks to robust box-level localization across diverse bioacoustic settings, providing a practical path for biodiversity monitoring with limited labels. --- ### From Ideas to Actions: A Public-Data Decision-Support Toolchain Across the Venture Lifecycle Authors: Lei Qu Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.15219v1 Founders face two linked decisions: whether to pursue an idea before founding, and which operating actions and capital partners fit afterward. We present a public-data decision-support toolchain combining time-bounded proposal profiling, market and moat checks, and deterministic aggregation with auditable investor-company event chains for retrospective analysis. Pre-founding: (a) After threshold selection on 198 development companies, the frozen pipeline achieves F0.5=0.5357 (0.412, 0.655) on an independent, row-disjoint 198-company validation sample. On the combined 396 rows, the Full Pipeline scores 0.6301 versus 0.2734 for a paired Raw LLM baseline. Post-stratification of 1,027 completed cases in a separate scale cohort yields 0.6506 (0.598, 0.707); the run remains incomplete. A 377-row composition-matched check yields 0.6573. (b) The AI-inference study identifies distribution-layer businesses as a replicable path to independent profitability with a limited revenue ceiling, and frontier-model ownership as a path to capital-market upside at exceptional capital cost. Post-founding: (a) Public sources support auditable event-chain analysis. (b) In the chip-company study, sustained product, customer, and supply-chain progress is associated with better observed outcomes; financing alone does not establish operating progress. (c) Financing comprises 79% of confirmed visible post-investment actions. Evidence tentatively favors acquisition-experienced strategic corporate investors for acquisition-oriented founders and financing-led institutional VCs with fewer observed control events for independence-oriented founders. Findings are developmental and observational, not causal guarantees or investment advice. We release shared ontology, provenance-bearing EventChain data, schemas, benchmarks, and executable skills for audit, reuse, and extension. --- ### Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception Authors: Yanfeng Shi, Yan Song, Junhui Li, Tinggan Huang, Wu Guo, Haoyu Song, Ian McLoughlin Published: 2026-09-14 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.15215v1 Large Audio-Language Models (LALMs) have substantially advanced general audio understanding, yet they remain limited in fine-grained temporal perception, particularly in precise event localization. Existing approaches primarily post-train LALMs to predict event boundaries as timestamp tokens. However, this generative formulation lacks explicit correspondence between the timestamp predictions and fine-grained acoustic evidence, limiting the precision and reliability of temporal localization. To address this issue, we augment the LALM with a dedicated frame-level grounding model while leveraging its semantic modeling capability to represent the event query. Specifically, the frozen LALM encodes the event query with audio as context, and the grounding model combines these query representations with fine-grained audio features to localize the target event at the frame level. Extensive experiments across diverse temporal grounding benchmarks demonstrate strong and consistent improvements over existing methods. Further evaluation shows that the grounding model can provide temporal evidence to support downstream reasoning. --- ### Failure-Guided Co-Evolution of Prompts and Training Data Authors: Tianyu Yuan, Zhuzhong Qian Published: 2026-09-14 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.15209v1 Automatic prompt optimization (APO) improves language-model programs by revising prompts from task feedback, yet it typically holds its training data fixed. Repeatedly optimizing against the same instances confines feedback to weaknesses already represented in those data, leaving related failure conditions unexplored. We therefore view each failure as a dual signal: it indicates both how the prompt should be revised and what new training evidence should be synthesized. We introduce FORGE, a failure-guided framework that co-evolves prompts and training data. FORGE abstracts imperfect executions into reusable failure modes and synthesizes new training data through four complementary mutation strategies. Verified instances are fed back into prompt search, allowing updated prompts to expose the next data needs. Across eight heterogeneous benchmarks, FORGE improves the aggregate score over the unoptimized baseline by 16.52 percentage points and outperforms all evaluated APO baselines. The synthesized data also transfer beyond FORGE: in a transfer study, they improve all nine APO comparisons by 2--9 points and all three GRPO comparisons by 4--8 points under matched optimization budgets. These results establish failures as a shared interface between prompt optimization and data synthesis, and show the benefit of jointly adapting what a model is instructed to do and what it learns from. --- ### Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election Authors: Bastiaan Bruinsma, Annika Fredén, Paul Röttger, Moa Johansson, Asad Sayeed Published: 2026-09-14 Categories: cs.AI, cs.CY, stat.AP arXiv: https://arxiv.org/abs/2609.15207v2 Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before elections. With growing evidence that they influence users' opinions, it is increasingly important to understand the views and positions of these tools. To better understand these views, we examine the stances supplied by six LLMs on a variety of Swedish-language writing tasks ahead of the 2026 Swedish parliamentary election. We cross 107 policy propositions with 77 writing templates and neutral, positive, and negative prompt framings, producing 24,717 prompts per model and 148,302 responses. To study these, we look at the models' default stance tendencies, compare how they respond to similar issues, and compare their responses with those of each of Sweden's eight parliamentary parties on the same issue. We find that Claude, DeepSeek, Gemini, and Mistral have similar profiles; ChatGPT more often supplies neutral or ambivalent text; and Grok differs most on topics such as migration, crime, and gender. When comparing the political parties, we find that the Social Democrats are closest to all six models. Still, after correcting for multiple comparisons, none of the within-model differences in party distances remains significant. Overall, we find that no model has a clear preference, nor a clear preference for a party, but that this depends on the specific issue or task the user asks about. --- ### TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models Authors: Tong Li, Shuye Ding, Jiachuan Wang, Yongqi Zhang, Shuangyin Li, Lei Chen, Bo Li Published: 2026-09-14 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2609.15205v1 Table extraction from texts is an important task for information systems, and recent approaches that prompt large language models (LLMs) with instructions have drawn great attention for their strong performance. Existing works have assumed the input texts to be table descriptions or specialized documents. However, these efforts have largely overlooked another prevalent category of texts, commonly found in news reports and social media: naturally occurring texts. Extracting tabular information from such texts poses two distinct challenges. First, high variability and the absence of explicit structural cues make fixed heuristic LLM prompts limited in precisely delineating extraction boundaries. Second, manually predefined schemas cannot capture open-ended, unseen attributes in naturally occurring text. In this paper, we propose a framework, TEAR, to address these challenges. It comprises two synergistic workflows: a Table Extraction Workflow that dynamically adapts instructions to overcome the limitation of heuristic instructions, and an Attribute Recommendation Workflow that discovers new attributes from texts to complement the heuristic schema. To our knowledge, TEAR is the first framework that supports automated text-driven attribute recommendation, enabling exploratory schema design for table extraction. To evaluate TEAR, we establish the benchmark for table extraction and attribute recommendation on naturally occurring texts, including two real-world datasets, manual annotations, appropriate metrics, and baseline comparisons. Experiments show that TEAR achieves state-of-the-art performance on both tasks, and the recommended attributes effectively enhance extraction performance in exploratory scenarios. --- ### Interpreting hierarchical organisation of speaker embeddings Authors: Yanze Xu, Wenwu Wang, Mark D. Plumbley Published: 2026-09-14 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2609.15203v2 Speaker recognition neural networks recognise speaker identities from input utterances by learning latent representations (i.e. speaker embeddings). However, these networks' internal mechanisms remain largely opaque, motivating research in explainable artificial intelligence (XAI) to understand them. Existing studies have analysed how speaker embeddings are organised, but rarely frame these analyses within XAI. This work proposes to explain and interpret the organisation of speaker embeddings from an XAI perspective. To this end, we apply a hierarchical clustering algorithm, Single-Linkage Clustering (SLINK), to analyse whether our prepared speaker embeddings naturally form clusters with hierarchical relationships. The resulting hierarchical organisation (i.e. hierarchical clusters) is evaluated using the Cluster-Class Matching (CCM) method. Moreover, we propose a new method, termed Hierarchical Cluster-Class Matching (HCCM), to identify which hierarchical clusters best match individual semantic classes like male and conjunctive semantic classes like UK & male, thereby interpreting the clusters using their matched classes. We quantify the matching degree with a new metric called the L-score, which makes imperfect matches diagnosable. HCCM's results reveal that the hierarchical clusters analysed by SLINK are well interpreted using classes related to speaker identity, gender, and nationality, showing the semantics inside the hierarchical organisation of the examined speaker embeddings. --- ### Semiotic Relations and Proof Methods: A Cross-Genre Study of Argument Structure with Large Language Models Authors: Edirlei Soares de Lima, Marco A. Casanova, Antonio L. Furtado Published: 2026-09-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.15194v1 When a direct proof of a statement $S$ seems hard or even impossible to obtain, there may exist another statement (or set of statements) $S^{*}$, somehow related to $S$, on the basis of which $S$ can be proved. In order to investigate what options can be used to move from $S$ to $S^{*}$, four kinds of semiotic relations inspired by the four master tropes of semiotic research are briefly reviewed. Specifically, our syntagmatic, paradigmatic, antithetic and meronymic relations correspond, respectively, to metonymy, metaphor, irony and synecdoche. It is suggested that these four semiotic relations determine the options to move from $S$ to $S^{*}$, leading to proof by inference, proof by analogy, proof by contradiction, and proof by case analysis. To examine how the four relations are actually used across different kinds of argument, we complement the framework with an empirical study. We turn the four relations into explicit operational definitions and apply them to a cross-genre corpus of mathematical, legal, and everyday argument using a panel of large language models. We find that the relations are used very unevenly across genres: mathematical proofs draw on all four, whereas legal and everyday reasoning rely almost entirely on inference. --- ### Convergence rates for generative drifting flows: fixed-scale obstructions and multihead acceleration Authors: Arthur Stéphanovitch, Eddie Aamari Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.15193v1 Drifting models offer a promising route to faster generative AI: they perform gradual transport during training, while generating new samples in a single step. This paper asks whether the underlying drifting process can converge rapidly to a target distribution under ideal conditions, before finite-data or optimization effects are introduced. We show that its convergence rate depends critically on how it handles spatial scale. With a single fixed resolution, fine-scale features of the target can become nearly invisible, leading to extremely slow convergence. We introduce a multihead approach that combines scale-normalized information across a continuum of resolutions. We prove that this multihead approach restores exponential convergence near standard reference distributions. These results identify fixed resolution as a key bottleneck and provide a simple route to faster one-step generative models. --- ### What Limits Us? Analyzing Self-Reported Limitations in NLP Research Authors: Tawan Thaepprasit, Peeranuth Kehasukcharoen, Ding Wang, Remi Denton, Peerapon Vateekul, Piyawat Lertvittayakumjorn Published: 2026-09-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.15191v1 Since late 2022, a Limitations section has become mandatory at many top-tier NLP conferences. The growing number of accepted papers at these venues has resulted in a vast corpus of self-reported limitations that cannot all be manually reviewed, yet remains systematically unanalyzed. Therefore, in this paper, we conduct a large-scale analysis of the Limitations sections from ACL and EMNLP papers published between 2020 and 2025 to understand what researchers disclose about their own work. To do so, we implement a novel human-AI framework for iterative hybrid qualitative coding. This framework enables us to investigate trends in self-reported limitations over time, their correlations with specific paper attributes, and the writing patterns that recur around these disclosures. Our findings offer a critical reflection on the diverse reported challenges as well as the self-reporting practices of researchers in the NLP community. --- ### Reconstructing Is Not Acting: Action-Centric Latent Dynamics Modeling Authors: Dingjie Fu, Dianxing Shi, Yangyang Xu, Jun Yu Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.15189v1 Latent action models (LAMs) learn action representations from unlabeled videos by inferring latent actions from visual transitions and reconstructing future states. However, we identify a fundamental $\textbf{reconstruction-action mismatch}$: lower reconstruction error does not necessarily yield better latent dynamics or downstream performance. We attribute this mismatch to two underconstrained aspects of reconstruction-based latent dynamics modeling: (i) the inverse dynamics model (IDM) is not explicitly encouraged to distinguish action-related transitions from nuisance appearance, and (ii) the forward dynamics model (FDM) can underutilize the inferred latent action by exploiting predictive shortcuts from the current state. To address both limitations, we propose $\textbf{ACT-LAM}$, a lightweight action-centric framework that strengthens both action extraction and action utilization. Specifically, its Action Query IDM (AQ-IDM) employs learnable action queries and gated aggregation to selectively extract rich action-related transition cues without strong information bottlenecks. And its Action Token FDM (AT-FDM) projects latent actions into action tokens that progressively interact with evolving state representations, enabling continuous state-aware action conditioning. ACT-LAM further streamlines feature processing to concentrate model capacity on latent dynamics modeling. Extensive experiments on several robotic datasets and the VP$^2$ benchmark demonstrate stronger latent action consistency, forward dynamics, and downstream visual planning performance with fewer trainable parameters and lower computational overhead. In particular, ACT-LAM surpasses the previous state of the art by $\textbf{7.6%}$ on the aggregated VP$^2$ success rate. Codes at $\href{https://github.com/DingjieFu/ACT-LAM}{url}$. --- ### MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing Authors: Jianxiang Ma, Xiaocui Yang, Daling Wang, Yuesong Hou, Mingfu Zhang, Yichen Gao, Junzhao Huang Published: 2026-09-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.15188v3 LLMs have been able to generate fluent prose, but high-quality stories also require coordinated decisions about plot, character, and language across planning, drafting, and revision. We formulate Vibe Narrativizing as turning natural-language writing requirements into a finished story. MUSE, a Theory-Harnessed Story Engine, addresses two bottlenecks: rule quality and sustained rule realization. Story theory supplies the rules, and a practical agent harness puts them to work. Knowledge engineering organizes Robert McKee's theory through rule atomization, semantic consolidation, mechanism abstraction, a single source of truth, and layered disclosure; typical examples clarify judgments that depend on context and aesthetic purpose. The harness preserves story decisions in intermediate deliverables across design, character performance, scene composition, and revision. Context engineering supplies each role with relevant guidance and decisions; a masterwork corpus provides inspiration and prose references. A worked example follows a requested object from its thematic role to climactic actions. Across four base models, MUSE improves WritingBench by 1.1 to 6.2 points over zero-shot generation; it is the only multi-stage system in our comparison to do so. It also raises LongStoryEval by more than ten points on three of the four models. ConStory-Bench consistency error density remains in the low single digits for all four models, below every reproduced story-system baseline on three of the four models. Ablations locate the largest quality contribution in structural design, voice-specific effects in the character path, and further gains in revision. ---