# Research Papers — 2026-03 · bundle page 101 of 243 > Full-text markdown of papers #5001–5050 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/101 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/100.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/102.md) ### A Creative Agent is Worth a 64-Token Template Authors: Ruixiao Shi, Fu Feng, Yucheng Xie, Xu Yang, Jing Wang, Xin Geng Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17895v1 Text-to-image (T2I) models have substantially improved image fidelity and prompt adherence, yet their creativity remains constrained by reliance on discrete natural language prompts. When presented with fuzzy prompts such as ``a creative vinyl record-inspired skyscraper'', these models often fail to infer the underlying creative intent, leaving creative ideation and prompt design largely to human users. Recent reasoning- or agent-driven approaches iteratively augment prompts but incur high computational and monetary costs, as their instance-specific generation makes ``creativity'' costly and non-reusable, requiring repeated queries or reasoning for subsequent generations. To address this, we introduce \textbf{CAT}, a framework for \textbf{C}reative \textbf{A}gent \textbf{T}okenization that encapsulates agents' intrinsic understanding of ``creativity'' through a \textit{Creative Tokenizer}. Given the embeddings of fuzzy prompts, the tokenizer generates a reusable token template that can be directly concatenated with them to inject creative semantics into T2I models without repeated reasoning or prompt augmentation. To enable this, the tokenizer is trained via creative semantic disentanglement, leveraging relations among partially overlapping concept pairs to capture the agent's latent creative representations. Extensive experiments on \textbf{\textit{Architecture Design}}, \textbf{\textit{Furniture Design}}, and \textbf{\textit{Nature Mixture}} tasks demonstrate that CAT provides a scalable and effective paradigm for enhancing creativity in T2I generation, achieving a $3.7\times$ speedup and a $4.8\times$ reduction in computational cost, while producing images with superior human preference and text-image alignment compared to state-of-the-art T2I models and creative generation methods. --- ### scicode-lint: Detecting Methodology Bugs in Scientific Python Code with LLM-Generated Patterns Authors: Sergey V. Samsonau Published: 2026-03-18 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17893v2 Methodology bugs in scientific Python code produce plausible but incorrect results that traditional linters and static analysis tools cannot detect. Several research groups have built ML-specific linters, demonstrating that detection is feasible. Yet these tools share a sustainability problem: dependency on specific pylint or Python versions, limited packaging, and reliance on manual engineering for every new pattern. As AI-generated code increases the volume of scientific software, the need for automated methodology checking (such as detecting data leakage, incorrect cross-validation, and missing random seeds) grows. We present scicode-lint, whose two-tier architecture separates pattern design (frontier models at build time) from execution (small local model at runtime). Patterns are generated, not hand-coded; adapting to new library versions costs tokens, not engineering hours. On Kaggle notebooks with human-labeled ground truth, preprocessing leakage detection reaches 65% precision at 100% recall; on 38 published scientific papers applying AI/ML, precision is 62% (LLM-judged) with substantial variation across pattern categories; on a held-out paper set, precision is 54%. On controlled tests, scicode-lint achieves 97.7% accuracy across 66 patterns. --- ### RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference Authors: Arpit Singh Gautam, Saurabh Jha Published: 2026-03-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17891v1 Post training quantization is essential for deploying large language models (LLMs) on resource constrained hardware, yet state of the art methods enforce uniform bit widths across layers, yielding suboptimal accuracy efficiency trade offs. We present RAMP (Reinforcement Adaptive Mixed Precision), an off policy Soft Actor Critic framework that learns per layer bit width assignments to minimize perplexity under a global bit budget. The policy conditions on an 11 dimensional embedding of activation statistics, weight properties, and structural descriptors, enabling zero shot transfer across model families and scales. To enable stable sub 4 bit quantization, we introduce Scale Folding, a preconditioning technique that migrates activation outliers into weights via per channel scaling and normalization layer compensation. A quality prioritized reward with asymmetric penalties and budget cliffs drives rapid convergence. On Llama 2 7B, RAMP achieves 5.54 perplexity at 3.68GB (3.65 effective bits), outperforming uniform 4 bit AWQ (5.60 at 3.90 GB) and GPTQ by 6% in size and 1% to3% in quality. Critically, a policy trained only on Llama 2 7B generalizes zero shot to Llama 2 13B and Mistral 7B, often surpassing target specific training, supporting the hypothesis that quantization sensitivity is primarily architectural. The HALO pipeline exports allocations to GGUF format for kernel free inference on CPUs, GPUs, and edge devices, retaining 99.5% of FP16 commonsense reasoning performance. --- ### Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation Authors: Qin Chen, Yingjie Chen, Shilun Lin, Cai Xing, Binxin Yang, Long Zhou, Qixin Yan, Wenjing Wang, Dingming Liu, Hao Liu, Chen Li, Jing Lyu Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17889v4 Recent advances in video synthesis have enabled realistic integration of real individuals, driving demand for identity-aware generation. While emerging methods support joint appearance and voice injection in audio-visual models, they primarily focus on single-subject settings. Multimodal identity integration across multiple subjects remains limited, and precise alignment between visual and vocal identities in multi-subject scenarios remains underexplored. We present Identity-as-Presence, a unified framework for joint personalized audio-video generation. An automated data curation pipeline constructs identity-labeled audio-visual pairs for single- and multi-subject scenes. A unified identity injection mechanism then binds paired appearance and voice through shared cross-modal identity binding and subject-anchored captions. A multi-stage training strategy further leverages large-scale unimodal data alongside scarce paired clips to mitigate modality imbalance. Experiments show superior audio quality, video fidelity, and audio-visual consistency, with stronger multi-subject binding than the compared methods. For more details and qualitative results, please refer to our webpage: \href{https://chen-yingjie.github.io/projects/Identity-as-Presence}{Identity-as-Presence}. --- ### Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation Authors: Yingjie Chen, Shilun Lin, Cai Xing, Binxin Yang, Long Zhou, Qixin Yan, Wenjing Wang, Dingming Liu, Hao Liu, Chen Li, Jing Lyu Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17889v3 Recent advances have demonstrated compelling capabilities in synthesizing real individuals into generated videos, reflecting the growing demand for identity-aware content creation. Nevertheless, an openly accessible framework enabling fine-grained control over facial appearance and voice timbre across multiple identities remains unavailable. In this work, we present a unified and scalable framework for identity-aware joint audio-video generation, enabling high-fidelity and consistent personalization. Specifically, we introduce a data curation pipeline that automatically extracts identity-bearing information with paired annotations across audio and visual modalities, covering diverse scenarios from single-subject to multi-subject interactions. We further propose a flexible and scalable identity injection mechanism for single- and multi-subject scenarios, in which both facial appearance and vocal timbre act as identity-bearing control signals. Moreover, in light of modality disparity, we design a multi-stage training strategy to accelerate convergence and enforce cross-modal coherence. Experiments demonstrate the superiority of the proposed framework. For more details and qualitative results, please refer to our webpage: \href{https://chen-yingjie.github.io/projects/Identity-as-Presence}{Identity-as-Presence}. --- ### AI-Assisted Goal Setting Improves Goal Progress Through Social Accountability Authors: Michel Schimpf, Julian Voigt, Thomas Bohné Published: 2026-03-18 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.17887v1 Helping people identify and pursue personally meaningful career goals at scale remains a key challenge in applied psychology. Career coaching can improve goal quality and attainment, but its cost and limited availability restrict access. Large language model (LLM)-based chatbots offer a scalable alternative, yet the psychological mechanisms by which they might support goal pursuit remain untested. Here we report a preregistered three-arm randomised controlled trial (N = 517) comparing an AI career coach ("Leon," powered by Claude Sonnet), a matched structured written questionnaire covering closely matched reflective topics, and a no-support control on goal progress at a two-week follow-up. The AI chatbot produced significantly higher goal progress than the control (d = 0.33, p = .016). Compared with the written-reflection condition, the AI did not significantly improve overall goal progress, but it increased perceived social accountability. In the preregistered mediation model, perceived accountability mediated the AI-over-questionnaire effect on goal progress (indirect effect = 0.15, 95% CI (0.04, 0.31)), whereas self-concordance did not. These findings suggest that AI-assisted goal setting can improve short-term goal progress, and that its clearest added value over structured self-reflection lies in increasing felt accountability. --- ### DebugLM: Learning Traceable Training Data Provenance for LLMs Authors: Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Wenxuan Zhou, Zhe Zhao, Muhao Chen Published: 2026-03-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.17884v1 Large language models (LLMs) are trained through multi-stage pipelines over heterogeneous data sources, yet developers lack a principled way to pinpoint the specific data responsible for an observed behavior. This lack of observability reduces debugging to reactive patching and makes failures prone to recur under distribution shift or subsequent model updates. To address this limitation, we propose DebugLM, a framework that equips LLMs with built-in data provenance, enabling them to explicitly trace the origins of their behaviors to specific training data sources. Specifically, the model learns to associate its responses with unique provenance tags that indicate the responsible dataset, empowering developers to precisely identify where undesirable behaviors are learned. Building on this capability, DebugLM further supports targeted test-time remediation, enabling developers to selectively trigger targeted refusal for specified data sources without retraining or modifying model parameters. Experiments demonstrate that DebugLM provides accurate behavior tracing in multi-stage training pipelines and effective test-time remediation while preserving the general utility of the model. --- ### Anatomy-Guided Vision-Language Learning with Angular Prototype Separation for Multi-Label Video Capsule Endoscopy Classification Under Class Imbalance Authors: Podakanti Satyajith Chary, Nagarajan Ganapathy Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17879v2 This work presents a multi-label temporal event detection framework for video capsule endoscopy (VCE) that addresses the extreme class imbalance inherent in the Galar dataset by combining two principal contributions: an Angular Separation Loss on class prototypes and a Biological State Machine temporal decoder. The backbone remains BiomedCLIP, a biomedical vision-language foundation model. Three consecutive frames are fused through a Local Differencing Attention module that amplifies transient pathological signals by suppressing static temporal redundancy. An Anatomy Context Head then conditions pathological predictions on soft anatomical activations, exploiting the known spatial co-occurrence structure of GI findings. Learnable text-feature prompts and prototype-based logit augmentation are trained alongside an Angular Separation Loss that penalizes off-diagonal cosine similarity between class prototypes, preventing the prototype collapse that afflicts rare classes under extreme imbalance. To counteract the skewed label distribution, the training regime combines asymmetric focal loss, inverse-frequency weighted sampling, temporal Mixup, Exponential Moving Average, and per-class threshold calibration. The Biological State Machine decoder replaces naive gap merging with a physiologically grounded forward-only state transition over anatomy labels, eliminating the fragmentation artefact that produced hundreds of spurious anatomy events per video in the prior approach and reducing per-video anatomy output to 2--3 clinically realistic events. On the held-out RARE-VISION test set comprising three NaviCam examinations (161,025 frames), the updated pipeline achieves an overall temporal mAP@0.5 of 0.3597 and mAP@0.95 of 0.3399, representing a relative improvement of 46% and 44% respectively over the prior submission, with total inference completed in approximately 21 minutes on a single GPU. --- ### Edit Spillover as a Probe: Do Image Editing Models Implicitly Understand World Relations? Authors: Guandong Li, Zhaobin Chu Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17876v1 Instruction-following image editing models are expected to modify only the specified region while keeping the rest of the image unchanged. However, in practice, we observe a pervasive phenomenon -- edit spillover: models alter semantically related but unspecified content outside the edit region. This raises a fundamental question -- does spillover reflect genuine implicit world understanding, or is it merely attention leakage? We propose EditSpilloverProbe, a systematic framework that repurposes edit spillover as a natural probe for world knowledge in image editing models. We introduce a spillover taxonomy (spatial, semantic, mixed, random), an automated detection-and-classification pipeline, and a benchmark dataset constructed from real-world Chinese text editing tasks, EditSpilloverBench. Systematic evaluation of 5 representative editing models reveals three core findings: (1) spillover rates vary dramatically across architectures, from 3.49% to 11.46%, with a 3.3x ratio; (2) absolute semantic spillover quantity reveals models' world understanding capability -- nano_banana produces the most semantic spillover (27.8 per image), while qwen_2511 has the most precise editing control but lower semantic spillover (16.3 per image), revealing a trade-off between editing control and world understanding; (3) spatial decay analysis shows spillover area density decays exponentially with distance, but the proportion of semantically relevant spillover remains constant (40%-58%), providing direct evidence that semantic spillover reflects genuine world understanding rather than spatial diffusion. --- ### Operator-Theoretic Foundations and Policy Gradient Methods for General MDPs with Unbounded Costs Authors: Abhishek Gupta, Aditya Mahajan Published: 2026-03-18 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.17875v3 Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs, which differs from the existence result derived previously in the literature. Using the well-established perturbation theory of linear operators, policy difference lemma is established for general MDPs and the Gauteaux derivative of the objective function as a function of the policy operator is derived. By upper bounding the policy difference via the theory of integral probability metric, a new majorization-minimization type policy gradient algorithm for general MDPs is derived. This leads to generalization of many well-known algorithms in reinforcement learning to cases with general state and action spaces. Further, by taking the integral probability metric as maximum mean discrepancy, a low-complexity policy gradient algorithm is derived for finite MDPs. The new algorithm, called MM-RKHS, appears to be superior to PPO algorithm due to low computational complexity, low sample complexity, and faster convergence. --- ### Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval Authors: Md. Asraful Haque, Aasar Mehdi, Maaz Mahboob, Tamkeen Fatima Published: 2026-03-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.17872v2 Large Language Models (LLMs) have achieved unprecedented fluency but remain susceptible to "hallucinations" - the generation of factually incorrect or ungrounded content. This limitation is particularly critical in high-stakes domains where reliability is paramount. We propose a domain-grounded tiered retrieval and verification architecture designed to systematically intercept factual inaccuracies by shifting LLMs from stochastic pattern-matchers to verified truth-seekers. The proposed framework utilizes a four-phase, self-regulating pipeline implemented via LangGraph: (I) Intrinsic Verification with Early-Exit logic to optimize compute, (II) Adaptive Search Routing utilizing a Domain Detector to target subject-specific archives, (III) Refined Context Filtering (RCF) to eliminate non-essential or distracting information, and (IV) Extrinsic Regeneration followed by atomic claim-level verification. The system was evaluated across 650 queries from five diverse benchmarks: TimeQA v2, FreshQA v2, HaluEval General, MMLU Global Facts, and TruthfulQA. Empirical results demonstrate that the pipeline consistently outperforms zero-shot baselines across all environments. Win rates peaked at 83.7% in TimeQA v2 and 78.0% in MMLU Global Facts, confirming high efficacy in domains requiring granular temporal and numerical precision. Groundedness scores remained robustly stable between 78.8% and 86.4% across factual-answer rows. While the architecture provides a robust fail-safe for misinformation, a persistent failure mode of "False-Premise Overclaiming" was identified. These findings provide a detailed empirical characterization of multi-stage RAG behavior and suggest that future work should prioritize pre-retrieval "answerability" nodes to further bridge the reliability gap in conversational AI. --- ### RHYME-XT: A Neural Operator for Spatiotemporal Control Systems Authors: Marijn Ruiter, Miguel Aguiar, Jake Rap, Karl H. Johansson, Amritam Das Published: 2026-03-18 Categories: cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2603.17867v1 We propose RHYME-XT, an operator-learning framework for surrogate modeling of spatiotemporal control systems governed by input-affine nonlinear partial integro-differential equations (PIDEs) with localized rhythmic behavior. RHYME-XT uses a Galerkin projection to approximate the infinite-dimensional PIDE on a learned finite-dimensional subspace with spatial basis functions parameterized by a neural network. This yields a projected system of ODEs driven by projected inputs. Instead of integrating this non-autonomous system, we directly learn its flow map using an architecture for learning flow functions, avoiding costly computations while obtaining a continuous-time and discretization-invariant representation. Experiments on a neural field PIDE show that RHYME-XT outperforms a state-of-the-art neural operator and is able to transfer knowledge effectively across models trained on different datasets, through a fine-tuning process. --- ### DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning Authors: Alexander D. Goldie, Zilin Wang, Adrian Hayler, Deepak Nathani, Edan Toledo, Ken Thampiratwong, Aleksandra Kalisz, Michael Beukman, Hannah Erlebach, Alistair Letcher, Shashank Reddy, Clarisse Wibault et al. Published: 2026-03-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17863v2 Automating the development of machine learning algorithms has the potential to unlock new breakthroughs. However, our ability to improve and evaluate algorithm discovery systems has thus far been limited by existing task suites. They suffer from many issues, such as: poor evaluation methodologies; data contamination; and containing saturated or very similar problems. Here, we introduce DiscoGen, a procedural generator of algorithm discovery tasks for machine learning, such as developing optimisers for reinforcement learning or loss functions for image classification. Motivated by the success of procedural generation in reinforcement learning, DiscoGen spans billions of tasks of varying difficulty and complexity from a range of machine learning fields. These tasks are specified by a small number of configuration parameters and can be used to optimise algorithm discovery agents (ADAs). We present DiscoBench, a fixed, small subset of DiscoGen tasks for principled evaluation of ADAs. Finally, we propose a number of ambitious, impactful research directions enabled by DiscoGen, and demonstrate its use for ADA optimisation through scaling experiments for automated prompt tuning. DiscoGen is released open-source at https://github.com/AlexGoldie/discogen. --- ### VISER: Visually-Informed System for Enhanced Robustness in Iris Presentation Attack Detection Authors: Byron Dowling, Jacob Piland, Eleanor Frederick, Christopher Sweet, Adam Czajka Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17859v3 Human perceptual priors have shown promise in saliency-guided deep learning training, particularly in the domain of iris presentation attack detection (PAD). Common saliency approaches include hand annotations obtained via mouse clicks and eye gaze heatmaps derived from eye tracking data. However, the most effective form of human saliency for raising generalization to unknown attack classes in iris PAD remains under-explored. In this paper, we conduct a series of experiments comparing hand annotations, eye tracking heatmaps, segmentation masks, and foundation model embeddings to a state-of-the-art deep learning-based baseline on the task of unknown attack type classification for iris PAD. Results in a leave-one-attack-type out paradigm indicate that denoised eye tracking heatmaps show the best generalization improvement over cross entropy in Attack Presentation Classification Error Rate (APCER) at Bona Fide Presentation Classification Error Rate (BPCER) of 1%. Along with this paper, we offer trained models, code, and saliency maps for reproducibility and to facilitate follow-up research efforts. --- ### VISER: Visually-Informed System for Enhanced Robustness in Open-Set Iris Presentation Attack Detection Authors: Byron Dowling, Jacob Piland, Eleanor Frederick, Christopher Sweet, Adam Czajka Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17859v2 Human perceptual priors have shown promise in saliency-guided deep learning training, particularly in the domain of iris presentation attack detection (PAD). Common saliency approaches include hand annotations obtained via mouse clicks and eye gaze heatmaps derived from eye tracking data. However, the most effective form of human saliency for open-set iris PAD remains under-explored. In this paper, we conduct a series of experiments comparing hand annotations, eye tracking heatmaps, segmentation masks, and foundation model embeddings to a state-of-the-art deep learning-based baseline on the task of open-set iris PAD. Results for open-set PAD in a leave-one-attack-type out paradigm indicate that denoised eye tracking heatmaps show the best generalization improvement over cross entropy in Attack Presentation Classification Error Rate (APCER) at Bona Fide Presentation Classification Error Rate (BPCER) of 1%. Along with this paper, we offer trained models, code, and saliency maps for reproducibility and to facilitate follow-up research efforts. --- ### Physics-Aware Machine Learning for Seismic and Volcanic Signal Interpretation Authors: William Thorossian Published: 2026-03-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17855v1 Modern seismic and volcanic monitoring is increasingly shaped by continuous, multi-sensor observations and by the need to extract actionable information from nonstationary, noisy wavefields. In this context, machine learning has moved from a research curiosity to a practical ingredient of processing chains for detection, phase picking, classification, denoising, and anomaly tracking. However, improved accuracy on a fixed dataset is not sufficient for operational use. Models must remain reliable under domain shift (new stations, changing noise, evolving volcanic activity), provide uncertainty that supports decision-making, and connect their outputs to physically meaningful constraints. This paper surveys and organizes recent ML approaches for seismic and volcanic signal analysis, highlighting where classical signal processing provides indispensable inductive bias, how self-supervision and generative modeling can reduce dependence on labels, and which evaluation protocols best reflect transfer across regions. We conclude with open challenges for robust, interpretable, and maintainable AI-assisted monitoring. --- ### Revisiting foundation models for cell instance segmentation Authors: Anwai Archit, Constantin Pape Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17845v1 Cell segmentation is a fundamental task in microscopy image analysis. Several foundation models for cell segmentation have been introduced, virtually all of them are extensions of Segment Anything Model (SAM), improving it for microscopy data. Recently, SAM2 and SAM3 have been published, further improving and extending the capabilities of general-purpose segmentation foundation models. Here, we comprehensively evaluate foundation models for cell segmentation (CellPoseSAM, CellSAM, $μ$SAM) and for general-purpose segmentation (SAM, SAM2, SAM3) on a diverse set of (light) microscopy datasets, for tasks including cell, nucleus and organoid segmentation. Furthermore, we introduce a new instance segmentation strategy called automatic prompt generation (APG) that can be used to further improve SAM-based microscopy foundation models. APG consistently improves segmentation results for $μ$SAM, which is used as the base model, and is competitive with the state-of-the-art model CellPoseSAM. Moreover, our work provides important lessons for adaptation strategies of SAM-style models to microscopy and provides a strategy for creating even more powerful microscopy foundation models. Our code is publicly available at https://github.com/computational-cell-analytics/micro-sam. --- ### Omni-3DEdit: Generalized Versatile 3D Editing in One-Pass Authors: Chen Liyi, Wang Pengfei, Zhang Guowen, Ma Zhiyuan, Zhang Lei Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17841v1 Most instruction-driven 3D editing methods rely on 2D models to guide the explicit and iterative optimization of 3D representations. This paradigm, however, suffers from two primary drawbacks. First, it lacks a universal design of different 3D editing tasks because the explicit manipulation of 3D geometry necessitates task-dependent rules, e.g., 3D appearance editing demands inherent source 3D geometry, while 3D removal alters source geometry. Second, the iterative optimization process is highly time-consuming, often requiring thousands of invocations of 2D/3D updating. We present Omni-3DEdit, a unified, learning-based model that generalizes various 3D editing tasks implicitly. One key challenge to achieve our goal is the scarcity of paired source-edited multi-view assets for training. To address this issue, we construct a data pipeline, synthesizing a relatively rich number of high-quality paired multi-view editing samples. Subsequently, we adapt the pre-trained generative model SEVA as our backbone by concatenating source view latents along with conditional tokens in sequence space. A dual-stream LoRA module is proposed to disentangle different view cues, largely enhancing our model's representational learning capability. As a learning-based model, our model is free of the time-consuming online optimization, and it can complete various 3D editing tasks in one forward pass, reducing the inference time from tens of minutes to approximately two minutes. Extensive experiments demonstrate the effectiveness and efficiency of Omni-3DEdit. --- ### Video Understanding: From Geometry and Semantics to Unified Models Authors: Zhaochong An, Zirui Li, Mingqiao Ye, Feng Qiao, Jiaang Li, Zongwei Wu, Vishal Thengane, Chengzu Li, Lei Li, Luc Van Gool, Guolei Sun, Serge Belongie Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17840v1 Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently requires modeling temporal dynamics and evolving visual context, placing stronger demands on spatiotemporal reasoning and making it a foundational problem in computer vision. In this survey, we present a structured overview of video understanding by organizing the literature into three complementary perspectives: low-level video geometry understanding, high-level semantic understanding, and unified video understanding models. We further highlight a broader shift from isolated, task-specific pipelines toward unified modeling paradigms that can be adapted to diverse downstream objectives, enabling a more systematic view of recent progress. By consolidating these perspectives, this survey provides a coherent map of the evolving video understanding landscape, summarizes key modeling trends and design principles, and outlines open challenges toward building robust, scalable, and unified video foundation models. --- ### How do LLMs Compute Verbal Confidence Authors: Dharshan Kumaran, Arthur Conmy, Federico Barbero, Simon Osindero, Viorica Patraucean, Petar Veličković Published: 2026-03-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17839v4 Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address two questions: first, when confidence is computed -- just-in-time when requested, or automatically during answer generation and cached for later retrieval; and second, what verbal confidence represents -- token log-probabilities, or a richer evaluation of answer quality? Focusing on Gemma 3 27B (across TriviaQA, BigMath, and MMLU), Qwen 2.5 7B, and the reasoning model Magistral Small 24B, we provide convergent evidence for cached retrieval. Activation steering, patching, noising, and swap experiments reveal that confidence representations emerge at answer-adjacent positions before appearing at the verbalization site. Attention blocking pinpoints the information flow: confidence is gathered from answer tokens, cached at the first post-answer position, then retrieved for output. Critically, linear probing and variance partitioning reveal that these cached representations explain substantial variance in verbal confidence beyond token log-probabilities, suggesting a richer answer-quality evaluation rather than a simple fluency readout. These findings demonstrate that verbal confidence reflects automatic, sophisticated self-evaluation -- not post-hoc reconstruction -- with implications for understanding metacognition in LLMs and improving calibration. --- ### How do LLMs Compute Verbal Confidence Authors: Dharshan Kumaran, Arthur Conmy, Federico Barbero, Simon Osindero, Viorica Patraucean, Petar Veličković Published: 2026-03-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17839v3 Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address two questions: first, when confidence is computed -- just-in-time when requested, or automatically during answer generation and cached for later retrieval; and second, what verbal confidence represents -- token log-probabilities, or a richer evaluation of answer quality? Focusing on Gemma 3 27B (across TriviaQA, BigMath, and MMLU), Qwen 2.5 7B, and the reasoning model Magistral Small 24B, we provide convergent evidence for cached retrieval. Activation steering, patching, noising, and swap experiments reveal that confidence representations emerge at answer-adjacent positions before appearing at the verbalization site. Attention blocking pinpoints the information flow: confidence is gathered from answer tokens, cached at the first post-answer position, then retrieved for output. Critically, linear probing and variance partitioning reveal that these cached representations explain substantial variance in verbal confidence beyond token log-probabilities, suggesting a richer answer-quality evaluation rather than a simple fluency readout. These findings demonstrate that verbal confidence reflects automatic, sophisticated self-evaluation -- not post-hoc reconstruction -- with implications for understanding metacognition in LLMs and improving calibration. --- ### Event-Centric Human Value Understanding in News-Domain Texts: An Actor-Conditioned, Multi-Granularity Benchmark Authors: Yao Wang, Xin Liu, Zhuochen Liu, Jiankang Chen, Adam Jatowt, Kyoungsook Kim, Noriko Kando, Haitao Yu Published: 2026-03-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.17838v1 Existing human value datasets do not directly support value understanding in factual news: many are actor-agnostic, rely on isolated utterances or synthetic scenarios, and lack explicit event structure or value direction. We present \textbf{NEVU} (\textbf{N}ews \textbf{E}vent-centric \textbf{V}alue \textbf{U}nderstanding), a benchmark for \emph{actor-conditioned}, \emph{event-centric}, and \emph{direction-aware} human value recognition in factual news. NEVU evaluates whether models can identify value cues, attribute them to the correct actor, and determine value direction from grounded evidence. Built from 2{,}865 English news articles, NEVU organizes annotations at four semantic unit levels (\textbf{Subevent}, \textbf{behavior-based composite event}, \textbf{story-based composite event}, and \textbf{Article}) and labels \mbox{(unit, actor)} pairs for fine-grained evaluation across local and composite contexts. The annotations are produced through an LLM-assisted pipeline with staged verification and targeted human auditing. Using a hierarchical value space with \textbf{54} fine-grained values and \textbf{20} coarse-grained categories, NEVU covers 45{,}793 unit--actor pairs and 168{,}061 directed value instances. We provide unified baselines for proprietary and open-source LLMs, and find that lightweight adaptation (LoRA) consistently improves open-source models, showing that although NEVU is designed primarily as a benchmark, it also supports supervised adaptation beyond prompting-only evaluation. Data availability is described in Appendix~\ref{app:data_code_availability}. --- ### The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning Authors: Donghang Wu, Tianyu Zhang, Yuxin Li, Hexin Liu, Chen Chen, Eng Siong Chng, Yoshua Bengio Published: 2026-03-18 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2603.17837v5 During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always manifest as explicit linguistic structures, it is instrumental in formulating high-quality responses. Inspired by this cognitive phenomenon, we propose a novel Full-duplex LAtent and Internal Reasoning method named FLAIR that conducts latent thinking simultaneously with speech perception. Unlike conventional "thinking" mechanisms in NLP, which require post-hoc generation, our approach aligns seamlessly with spoken dialogue systems: during the user's speaking phase, it recursively feeds the latent embedding output from the previous step into the next step, enabling continuous reasoning that strictly adheres to causality without introducing additional latency. To enable this latent reasoning, we design an Evidence Lower Bound-based objective that supports efficient supervised finetuning via teacher forcing, circumventing the need for explicit reasoning annotations. Experiments demonstrate the effectiveness of this think-while-listening design, which achieves competitive results on a range of speech benchmarks. Furthermore, FLAIR robustly handles conversational dynamics and attains competitive performance on full-duplex interaction metrics. --- ### Verification and Validation of Physics-Informed Surrogate Component Models for Dynamic Power-System Simulation Authors: Petros Ellinas, Indrajit Chaudhuri, Johanna Vorwerk, Spyros Chatzivasileiadis Published: 2026-03-18 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2603.17836v1 Physics-informed machine learning surrogates are increasingly explored to accelerate dynamic simulation of generators, converters, and other power grid components. The key question, however, is not only whether a surrogate matches a stand-alone component model on average, but whether it remains accurate after insertion into a differential-algebraic simulator, where the surrogate outputs enter the algebraic equations coupling the component to the rest of the system. This paper formulates that in-simulator use as a verification and validation (V\&V) problem. A finite-horizon bound is derived that links allowable component-output error to algebraic-coupling sensitivity, dynamic error amplification, and the simulation horizon. Two complementary settings are then studied: model-based verification against a reference component solver, and data-based validation through conformal calibration of the component-output variables exchanged with the simulator. The framework is general, but the case study focuses on physics-informed neural-network surrogates of second-, fourth-, and sixth-order synchronous-machine models. Results show that good stand-alone surrogate accuracy does not by itself guarantee accurate in-simulator behavior, that the largest discrepancies concentrate in stressed operating regions, and that small equation residuals do not necessarily imply small state-trajectory errors. --- ### Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control Authors: Zunzhe Zhang, Runhan Huang, Yicheng Liu, Shaoting Zhu, Linzhan Mou, Hang Zhao Published: 2026-03-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.17834v2 Diffusion models and flow matching have become a cornerstone of robotic imitation learning, yet they suffer from a structural inefficiency where inference is often bound to a fixed integration schedule that is agnostic to state complexity. This paradigm forces the policy to expend the same computational budget on trivial motions as it does on complex tasks. We introduce Generative Control as Optimization (GeCO), a time-unconditional framework that transforms action synthesis from trajectory integration into iterative optimization. GeCO learns a stationary velocity field in the action-sequence space where expert behaviors form stable attractors. Consequently, test-time inference becomes an adaptive process that allocates computation based on convergence--exiting early for simple states while refining longer for difficult ones. Furthermore, this stationary geometry yields an intrinsic, training-free safety signal, as the field norm at the optimized action serves as a robust out-of-distribution (OOD) detector, remaining low for in-distribution states while significantly increasing for anomalies. We validate GeCO on standard simulation benchmarks and demonstrate seamless scaling to pi0-series Vision-Language-Action (VLA) models. As a plug-and-play replacement for standard flow-matching heads, GeCO improves success rates and efficiency with an optimization-native mechanism for safe deployment. Video and code can be found at https://hrh6666.github.io/GeCO/ --- ### Text-to-Stage: Spatial Layouts from Long-form Narratives Authors: Jefferson Hernandez, Swarnadeep Saha, Chenxi Whitehouse, Sanjeel Parekh, Calvin Murdock, Yuliang Li, W. Owen Brimijoin, Vamsi Krishna Ithapu, Ishwarya Ananthabhotla Published: 2026-03-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17832v1 In this work, we probe the ability of a language model to demonstrate spatial reasoning from unstructured text, mimicking human capabilities and automating a process that benefits many downstream media applications. Concretely, we study the narrative-to-play task: inferring stage-play layouts (scenes, speaker positions, movements, and room types) from text that lacks explicit spatial, positional, or relational cues. We then introduce a dramaturgy-inspired deterministic evaluation suite and, finally, a training and inference recipe that combines rejection SFT using Best-of-N sampling with RL from verifiable rewards via GRPO. Experiments on a text-only corpus of classical English literature demonstrate improvements over vanilla models across multiple metrics (character attribution, spatial plausibility, and movement economy), as well as alignment with an LLM-as-a-judge and subjective human preferences. --- ### RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy Authors: Zhenhang Yuan, Shenghai Yuan, Lihua Xie Published: 2026-03-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.17831v1 LLM agents often fail in closed-world embodied environments because actions must satisfy strict preconditions -- such as location, inventory, and container states -- and failure feedback is sparse. We identify two structurally coupled failure modes: (P1) invalid action generation and (P2) state drift, each amplifying the other in a degenerative cycle. We present RPMS, a conflict-managed architecture that enforces action feasibility via structured rule retrieval, gates memory applicability via a lightweight belief state, and resolves conflicts between the two sources via rules-first arbitration. On ALFWorld (134 unseen tasks), RPMS achieves 59.7% single-trial success with Llama 3.1 8B (+23.9 pp over baseline) and 98.5% with Claude Sonnet 4.5 (+11.9 pp); of the 8B gain, rule retrieval alone contributes +14.9 pp (statistically significant), making it the dominant factor. A key finding is that episodic memory is conditionally useful: it harms performance on some task types when used without grounding, but becomes a stable net positive once filtered by current state and constrained by explicit action rules. Adapting RPMS to ScienceWorld with GPT-4 yields consistent gains across all ablation conditions (avg. score 54.0 vs. 44.9 for the ReAct baseline), providing transfer evidence that the core mechanisms hold across structurally distinct environments. --- ### CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents Authors: Lintang Sutawika, Aditya Bharat Soni, Bharath Sriraam R R, Apurva Gandhi, Taha Yassine, Sanidhya Vijayvargiya, Yuchen Li, Xuhui Zhou, Yilin Zhang, Leander Melroy Maben, Graham Neubig Published: 2026-03-18 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.17829v1 A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using embedding-based retrieval approaches such as vector search, recent work has focused on developing agents to localize relevant code either as a standalone precursor to or interleaved with performing actual work. Most prior methods on agentic code search equip the agent with complex, specialized tools, such as repository graphs derived from static analysis. In this paper, we demonstrate that, with an effective reinforcement learning recipe, a coding agent equipped with nothing more than a standard Unix terminal can be trained to achieve strong results. Our experiments on three benchmarks (SWE-Bench Verified, Pro, and Lite) reveal that our models consistently achieve superior or competitive performance over 2-18x larger base and post-trained LLMs and sometimes approach performance provided by closed models like Claude Sonnet, even when using specialized scaffolds. Our work particularly focuses on techniques for re-purposing existing coding agent environments for code search, reward design, and RL optimization. We release the resulting model family, CodeScout, along with all our code and data for the community to build upon. --- ### TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models Authors: Qianlong Xiang, Miao Zhang, Haoyu Zhang, Kun Wang, Junhui Hou, Liqiang Nie Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17828v1 Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful content. This has fostered a dynamic interplay between the development of erasure defenses and the adversarial probes designed to bypass them, and this co-evolution has progressively enhanced the efficacy of erasure methods. However, this adversarial co-evolution has converged on a narrow, text-centric paradigm that equates erasure with severing the text-to-image mapping, ignoring that the underlying visual knowledge related to undesired concepts still persist. To substantiate this claim, we investigate from a visual perspective, leveraging DDIM inversion to probe whether a generative pathway for the erased concept can still be found. However, identifying such a visual generative pathway is challenging because standard text-guided DDIM inversion is actively resisted by text-centric defenses within the erased model. To address this, we introduce TINA, a novel Text-free INversion Attack, which enforces this visual-only probe by operating under a null-text condition, thereby avoiding existing text-centric defenses. Moreover, TINA integrates an optimization procedure to overcome the accumulating approximation errors that arise when standard inversion operates without its usual textual guidance. Our experiments demonstrate that TINA regenerates erased concepts from models treated with state-of-the-art unlearning. The success of TINA proves that current methods merely obscure concepts, highlighting an urgent need for paradigms that operate directly on internal visual knowledge. --- ### FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair Authors: Ruize Ma, Yilei Jiang, Shilin Zhang, Zheng Ma, Yi Feng, Vincent Ng, Zhi Wang, Xiangyu Yue, Chuanyi Li, Lewei Lu Published: 2026-03-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.17826v1 Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifacts such as GUI screenshots. While recent LLM-based repair systems have shown promising results, existing approaches face several limitations: rigid workflow pipelines restrict exploration during debugging, visual reasoning is often performed over full-page screenshots without localized grounding, and failed repair attempts are rarely transformed into reusable knowledge. To address these challenges, we propose FailureMem, a multimodal repair framework that integrates three key mechanisms: a hybrid workflow-agent architecture that balances structured localization with flexible reasoning, active perception tools that enable region-level visual grounding, and a Failure Memory Bank that converts past repair attempts into reusable guidance. Experiments on SWE-bench Multimodal demonstrate FailureMem improves the resolved rate over GUIRepair by 3.7%. --- ### Steering Video Diffusion Transformers with Massive Activations Authors: Xianhang Cheng, Yujian Zheng, Zhenyu Xie, Tingting Liao, Hao Li Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17825v2 In this work, we study the role of Massive Activations (MAs), which are rare, high-magnitude spikes confined to a few fixed hidden dimensions in video diffusion transformers (DiTs). We uncover a structured positional hierarchy: MA magnitudes peak at first-frame tokens and recur at the spatial boundary tokens of latent frames, with this pattern being most pronounced during early denoising. We trace this organization to an encoding asymmetry of the video VAEs, whose causal temporal padding and zero spatial padding cause the first latent frame and frame borders to carry reduced content load. Elevated MAs consistently align with these lower-content structural positions. To understand their function, we analyze intermediate representations and find that MAs act as implicit rescalers of residual computation: enlarging MAs suppresses the corresponding self-attention and feed-forward updates, while erasing them amplifies these updates. Together, these observations suggest that MAs serves as a token-level rescaler of residual computation, which video DiTs deploy unevenly, placing the strongest damping at the encoding-asymmetric structural positions. Motivated by this native rescaling behavior, we propose Structured Activation Steering (STAS), a training-free technique that steers MAs at the observed structural positions toward a scaled, model-derived reference during early denoising. STAS requires no additional forward passes and consistently improves video quality and temporal coherence across text-to-video models with negligible overhead. --- ### Steering Video Diffusion Transformers with Massive Activations Authors: Xianhang Cheng, Yujian Zheng, Zhenyu Xie, Tingting Liao, Hao Li Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17825v1 Despite rapid progress in video diffusion transformers, how their internal model signals can be leveraged with minimal overhead to enhance video generation quality remains underexplored. In this work, we study the role of Massive Activations (MAs), which are rare, high-magnitude hidden state spikes in video diffusion transformers. We observed that MAs emerge consistently across all visual tokens, with a clear magnitude hierarchy: first-frame tokens exhibit the largest MA magnitudes, latent-frame boundary tokens (the head and tail portions of each temporal chunk in the latent space) show elevated but slightly lower MA magnitudes than the first frame, and interior tokens within each latent frame remain elevated, yet are comparatively moderate in magnitude. This structured pattern suggests that the model implicitly prioritizes token positions aligned with the temporal chunking in the latent space. Based on this observation, we propose Structured Activation Steering (STAS), a training-free self-guidance-like method that steers MA values at first-frame and boundary tokens toward a scaled global maximum reference magnitude. STAS achieves consistent improvements in terms of video quality and temporal coherence across different text-to-video models, while introducing negligible computational overhead. --- ### Symmetry-Reduced Physics-Informed Learning of Tensegrity Dynamics Authors: Jing Qin, Muhao Chen Published: 2026-03-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17824v1 Tensegrity structures possess intrinsic geometric symmetries that govern their dynamic behavior. However, most existing physics-informed neural network (PINN) approaches for tensegrity dynamics do not explicitly exploit these symmetries, leading to high computational complexity and unstable optimization. In this work, we propose a symmetry-reduced physics-informed neural network (SymPINN) framework that embeds group-theory-based symmetry directly into both the solution expression and the neural network architecture to predict tensegrity dynamics. By decomposing nodes into symmetry orbits and representing free nodal coordinates using a symmetry basis, the proposed method constructs a reduced coordinate representation that preserves geometric symmetry of the structure. The full coordinates are then recovered via symmetry transformations of the reduced solution learned by the network, ensuring that the predicted configurations automatically satisfy the symmetry constraints. In this framework, equivariance is enforced through orbit-based coordinate generation, symmetry-consistent message passing, and physics residual constraints. In addition, SymPINN improves training effectiveness by encoding initial conditions as hard constraints, incorporating Fourier feature encoding to enhance the representation of dynamic motions, and employing a two-stage optimization strategy. Extensive numerical experiments on symmetric T-bars and lander structures demonstrate significantly improved prediction accuracy and computational efficiency compared to standard physics-informed models, indicating the great potential of symmetry-aware learning for structure-preserving modeling of tensegrity dynamics. --- ### Discovering Decoupled Functional Modules in Large Language Models Authors: Yanke Yu, Jin Li, Ying Sun, Ping Li, Zhefeng Wang, Yi Zheng Published: 2026-03-18 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2603.17823v1 Understanding the internal functional organization of Large Language Models (LLMs) is crucial for improving their trustworthiness and performance. However, how LLMs organize different functions into modules remains highly unexplored. To bridge this gap, we formulate a functional module discovery problem and propose an Unsupervised LLM Cross-layer MOdule Discovery (ULCMOD) framework that simultaneously disentangles the large set of neurons in the entire LLM into modules while discovering the topics of input samples related to these modules. Our framework introduces a novel objective function and an efficient Iterative Decoupling (IterD) algorithm. Extensive experiments show that our method discovers high-quality, disentangled modules that capture more meaningful semantic information and achieve superior performance in various downstream tasks. Moreover, our qualitative analysis reveals that the discovered modules show semantic coherence, correspond to interpretable specializations, and a clear spatial and hierarchical organization within the LLM. Our work provides a novel tool for interpreting the functional modules of LLMs, filling a critical blank in LLM's interpretability research. --- ### Multi-Source Evidence Fusion for Audio Question Answering Authors: Aivo Olev, Tanel Alumäe Published: 2026-03-18 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2603.17822v1 Large audio language models (LALMs) can answer questions about speech, music, and environmental sounds, yet their internal reasoning is largely opaque and difficult to validate. We describe TalTech's solution to the Agent Track of the Interspeech 2026 Audio Reasoning Challenge, in which systems are evaluated on reasoning process quality, specifically the factual accuracy, logical soundness, and completeness of their reasoning chains. Our multi-source ensemble pipeline uses two LALMs that generate independent observations, while a separate text-only reasoning model cross-checks these against outputs from 25 acoustic tools organized into reliability tiers. By grounding every inference step in explicit, reliability-tagged evidence, the system produces dense, verifiable reasoning chains. Our system ranked first in the challenge, outperforming all competing systems by a wide margin in challenge's reasoning quality metric. --- ### Federated Distributional Reinforcement Learning with Distributional Critic Regularization Authors: David Millard, Cecilia Alm, Rashid Ali, Pengcheng Shi, Ali Baheri Published: 2026-03-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17820v1 Federated reinforcement learning typically aggregates value functions or policies by parameter averaging, which emphasizes expected return and can obscure statistical multimodality and tail behavior that matter in safety-critical settings. We formalize federated distributional reinforcement learning (FedDistRL), where clients parametrize quantile value function critics and federate these networks only. We also propose TR-FedDistRL, which builds a per client, risk-aware Wasserstein barycenter over a temporal buffer. This local barycenter provides a reference region to constrain the parameter averaged critic, ensuring necessary distributional information is not averaged out during the federation process. The distributional trust region is implemented as a shrink-squash step around this reference. Under fixed-policy evaluation, the feasibility map is nonexpansive and the update is contractive in a probe-set Wasserstein metric under evaluation. Experiments on a bandit, multi-agent gridworld, and continuous highway environment show reduced mean-smearing, improved safety proxies (catastrophe/accident rate), and lower critic/policy drift versus mean-oriented and non-federated baselines. --- ### Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gain Authors: Corentin Royer, Debarun Bhattacharjya, Gaetano Rossiello, Andrea Giovannini, Mennatallah El-Assady Published: 2026-03-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.17815v1 Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by scoring each step individually, enabling fine-grained supervision and improved reliability. Existing methods for training PRMs rely on costly human annotations or computationally intensive automatic labeling. We propose a novel approach to automatically generate step-level labels using Information Theory. Our method estimates how each reasoning step affects the likelihood of the correct answer, providing a signal of step quality. Importantly, it reduces computational complexity to $\mathcal{O}(N)$, improving over the previous $\mathcal{O}(N \log N)$ methods. We demonstrate that these labels enable effective chain-of-thought selection in best-of-$K$ evaluation settings across diverse reasoning benchmarks, including mathematics, Python programming, SQL, and scientific question answering. This work enables scalable and efficient supervision of LLM reasoning, particularly for tasks where error propagation is critical. --- ### M2P: Improving Visual Foundation Models with Mask-to-Point Weakly-Supervised Learning for Dense Point Tracking Authors: Qiangqiang Wu, Tianyu Yang, Bo Fang, Jia Wan, Matias Di Martino, Guillermo Sapiro, Antoni B. Chan Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17813v1 Tracking Any Point (TAP) has emerged as a fundamental tool for video understanding. Current approaches adapt Vision Foundation Models (VFMs) like DINOv2 via offline finetuning or test-time optimization. However, these VFMs rely on static image pre-training, which is inherently sub-optimal for capturing dense temporal correspondence in videos. To address this, we propose Mask-to-Point (M2P) learning, which leverages rich video object segmentation (VOS) mask annotations to improve VFMs for dense point tracking. Our M2P introduces three new mask-based constraints for weakly-supervised representation learning. First, we propose a local structure consistency loss, which leverages Procrustes analysis to model the cohesive motion of points lying within a local structure, achieving more reliable point-to-point matching learning. Second, we propose a mask label consistency (MLC) loss, which enforces that sampled foreground points strictly match foreground regions across frames. The proposed MLC loss can be regarded as a regularization, which stabilizes training and prevents convergence to trivial solutions. Finally, mask boundary constrain is applied to explicitly supervise boundary points. We show that our weaklysupervised M2P models significantly outperform baseline VFMs with efficient training by using only 3.6K VOS training videos. Notably, M2P achieves 12.8% and 14.6% performance gains over DINOv2-B/14 and DINOv3-B/16 on the TAP-Vid-DAVIS benchmark, respectively. Moreover, the proposed M2P models are used as pre-trained backbones for both test-time optimized and offline fine-tuned TAP tasks, demonstrating its potential to serve as general pre-trained models for point tracking. Code will be made publicly available upon acceptance. --- ### ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation Authors: Dmitriy Rivkin, Parker Ewen, Lili Gao, Julian Ost, Stefanie Walz, Rasika Kangutkar, Mario Bijelic, Felix Heide Published: 2026-03-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17812v2 Recent video diffusion models achieve high-quality generation through recurrent frame processing where each frame generation depends on previous frames. However, this recurrent mechanism means that training such models in the pixel domain incurs prohibitive memory costs, as activations accumulate across the entire video sequence. This fundamental limitation also makes fine-tuning these models with pixel-wise losses computationally intractable for long or high-resolution videos. This paper introduces ChopGrad, a truncated backpropagation scheme for video decoding, limiting gradient computation to local frame windows while maintaining global consistency. We provide a theoretical analysis of this approximation and show that it enables efficient fine-tuning with frame-wise losses. ChopGrad reduces training memory from scaling linearly with the number of video frames (full backpropagation) to constant memory, and compares favorably to existing state-of-the-art video diffusion models across a suite of conditional video generation tasks with pixel-wise losses, including video super-resolution, video inpainting, video enhancement of neural-rendered scenes, and controlled driving video generation. --- ### Dropout Robustness and Cognitive Profiling of Transformer Models via Stochastic Inference Authors: Antônio Junior Alves Caiado, Michael Hahsler Published: 2026-03-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17811v1 Transformer-based language models are widely deployed for reasoning, yet their behavior under inference-time stochasticity remains underexplored. While dropout is common during training, its inference-time effects via Monte Carlo sampling lack systematic evaluation across architectures, limiting understanding of model reliability in uncertainty-aware applications. This work analyzes dropout-induced variability across 19 transformer models using MC Dropout with 100 stochastic forward passes per sample. Dropout robustness is defined as maintaining high accuracy and stable predictions under stochastic inference, measured by standard deviation of per-run accuracies. A cognitive decomposition framework disentangles performance into memory and reasoning components. Experiments span five dropout configurations yielding 95 unique evaluations on 1,000 samples. Results reveal substantial architectural variation. Smaller models demonstrate perfect prediction stability while medium-sized models exhibit notable volatility. Mid-sized models achieve the best overall performance; larger models excel at memory tasks. Critically, 53% of models suffer severe accuracy degradation under baseline MC Dropout, with task-specialized models losing up to 24 percentage points, indicating unsuitability for uncertainty quantification in these architectures. Asymmetric effects emerge: high dropout reduces memory accuracy by 27 percentage points while reasoning degrades only 1 point, suggesting memory tasks rely on stable representations that dropout disrupts. 84% of models demonstrate memory-biased performance. This provides the first comprehensive MC Dropout benchmark for transformers, revealing dropout robustness is architecture-dependent and uncorrelated with scale. The cognitive profiling framework offers actionable guidance for model selection in uncertainty-aware applications. --- ### Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients Authors: Ziwei Xiang, Fanhu Zeng, Hongjian Fang, Rui-Qi Wang, Renxing Chen, Yanan Zhu, Yi Chen, Peipei Yang, Xu-Yao Zhang Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17809v1 Large Vision Language Models (LVLMs) have achieved remarkable success in a range of downstream tasks that require multimodal interaction, but their capabilities come with substantial computational and memory overhead, which hinders practical deployment. Among numerous acceleration techniques, post-training quantization is a popular and effective strategy for reducing memory cost and accelerating inference. However, existing LVLM quantization methods typically measure token sensitivity at the modality level, which fails to capture the complex cross-token interactions and falls short in quantitatively measuring the quantization error at the token level. As tokens interact within the model, the distinction between modalities gradually diminishes, suggesting the need for fine-grained calibration. Inspired by axiomatic attribution in mechanistic interpretability, we introduce a fine-grained quantization strategy on Quantization-aware Integrated Gradients (QIG), which leverages integrated gradients to quantitatively evaluate token sensitivity and push the granularity from modality level to token level, reflecting both inter-modality and intra-modality dynamics. Extensive experiments on multiple LVLMs under both W4A8 and W3A16 settings show that our method improves accuracy across models and benchmarks with negligible latency overhead. For example, under 3-bit weight-only quantization, our method improves the average accuracy of LLaVA-onevision-7B by 1.60%, reducing the gap to its full-precision counterpart to only 1.33%. The code is available at https://github.com/ucas-xiang/QIG. --- ### EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards Authors: Ruixiang Wang, Qingming Liu, Yueci Deng, Guiliang Liu, Zhen Liu, Kui Jia Published: 2026-03-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.17808v2 Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the generated frames into executable robot actions. However, current video world models lack explicit executability constraints. As a result, visually coherent rollouts may still violate rigid-body and kinematic consistency, producing unstable or infeasible control commands when decoded by an IDM. We refer to this mismatch between visual generation and physically executable control as the executability gap. While this gap can be mitigated at inference time using techniques such as rejection sampling, such approaches are inefficient due to the high cost of video generation. In this paper, we leverage the executability gap as a training signal and introduce Executable Video Alignment (EVA), a reinforcement-learning post-training framework for aligning video world models. EVA trains an inverse dynamics model on real robot trajectories and repurposes it as a reward model that evaluates generated videos through the action sequences they induce, encouraging smooth motions measured by velocity, acceleration, and jerk while penalizing actions that violate embodiment constraints. Importantly, the reward remains informative even when generated videos contain severe visual artifacts, since such artifacts typically translate into unstable or out-of-bound actions. Experiments on the RoboTwin benchmark and a real bimanual robot show that EVA reduces embodiment-specific artifacts in generated rollouts and improves downstream task execution success. --- ### RangeAD: Fast On-Model Anomaly Detection Authors: Luca Hinkamp, Simon Klüttermann, Emmanuel Müller Published: 2026-03-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17795v1 In practice, machine learning methods commonly require anomaly detection (AD) to filter inputs or detect distributional shifts. Typically, this is implemented by running a separate AD model alongside the primary model. However, this separation ignores the fact that the primary model already encodes substantial information about the target distribution. In this paper, we introduce On-Model AD, a setting for anomaly detection that explicitly leverages access to a related machine learning model. Within this setting, we propose RangeAD, an algorithm that utilizes neuron-wise output ranges derived from the primary model. RangeAD achieves superior performance even on high-dimensional tasks while incurring substantially lower inference costs. Our results demonstrate the potential of the On-Model AD setting as a practical framework for efficient anomaly detection. --- ### The Convergence Frontier: Integrating Machine Learning and High Performance Quantum Computing for Next-Generation Drug Discovery Authors: Narjes Ansari, César Feniou, Nicolaï Gouraud, Daniele Loco, Siwar Badreddine, Baptiste Claudon, Félix Aviat, Marharyta Blazhynska, Kevin Gasperich, Guillaume Michel, Diata Traore, Corentin Villot et al. Published: 2026-03-18 Categories: quant-ph, cs.LG, physics.chem-ph arXiv: https://arxiv.org/abs/2603.17790v3 Integrating quantum mechanics into drug discovery marks a decisive shift from empirical trial-and-error toward quantitative precision. However, the prohibitive cost of ab initio molecular dynamics has historically forced a compromise between chemical accuracy and computational scalability. This paper identifies the convergence of High-Performance Computing (HPC), Machine Learning (ML), and Quantum Computing (QC) as the definitive solution to this bottleneck. While ML foundation models, such as FeNNix-Bio1, enable quantum-accurate simulations, they remain tethered to the inherent limits of classical data generation. We detail how High-Performance Quantum Computing (HPQC), utilizing hybrid QPU-GPU architectures, will serve as the ultimate accelerator for quantum chemistry data. By leveraging Hilbert space mapping, these systems can achieve true chemical accuracy while bypassing the heuristics of classical approximations. We show how this tripartite convergence optimizes the drug discovery pipeline, spanning from initial system preparation to ML-driven, high-fidelity simulations. Finally, we position quantum-enhanced sampling as the beyond GPU frontier for modeling reactive cellular systems and pioneering next-generation materials. --- ### Governed Memory: A Production Architecture for Multi-Agent Workflows Authors: Hamed Taheri Published: 2026-03-18 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2603.17787v1 Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory silos across agent workflows; governance fragmentation across teams and tools; unstructured memories unusable by downstream systems; redundant context delivery in autonomous multi-step executions; and silent quality degradation without feedback loops. We present Governed Memory, a shared memory and governance layer addressing this gap through four mechanisms: a dual memory model combining open-set atomic facts with schema-enforced typed properties; tiered governance routing with progressive context delivery; reflection-bounded retrieval with entity-scoped isolation; and a closed-loop schema lifecycle with AI-assisted authoring and automated per-property refinement. We validate each mechanism through controlled experiments (N=250, five content types): 99.6% fact recall with complementary dual-modality coverage; 92% governance routing precision; 50% token reduction from progressive delivery; zero cross-entity leakage across 500 adversarial queries; 100% adversarial governance compliance; and output quality saturation at approximately seven governed memories per entity. On the LoCoMo benchmark, the architecture achieves 74.8% overall accuracy, confirming that governance and schema enforcement impose no retrieval quality penalty. The system is in production at Personize.ai. --- ### A Dual Certificate Approach to Sparsity in Infinite-Width Shallow Neural Networks Authors: Leonardo Del Grande, Christoph Brune, Marcello Carioni Published: 2026-03-18 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2603.17785v1 In this paper, we study total variation (TV)-regularized training of infinite-width shallow ReLU neural networks, formulated as a convex optimization problem over measures on the unit sphere. Our approach leverages the duality theory of TV-regularized optimization problems to establish rigorous guarantees on the sparsity of the solutions to the training problem. Our analysis further characterizes how and when this sparsity persists in a low noise regime and for small regularization parameter. The key observation that motivates our analysis is that, for ReLU activations, the associated dual certificate is piecewise linear in the weight space. Its linearity regions, which we name dual regions, are determined by the activation patterns of the data via the induced hyperplane arrangement. Taking advantage of this structure, we prove that, on each dual region, the dual certificate admits at most one extreme value. As a consequence, the support of any minimizer is finite, and its cardinality can be bounded from above by a constant depending only on the geometry of the data-induced hyperplane arrangement. Then, we further investigate sufficient conditions ensuring uniqueness of such sparse solution. Finally, under a suitable non-degeneracy condition on the dual certificate along the boundaries of the dual regions, we prove that in the presence of low label noise and for small regularization parameter, solutions to the training problem remain sparse with the same number of Dirac deltas. Additionally, their location and the amplitudes converge, and, in case the locations lie in the interior of a dual region, the convergence happens with a rate that depends linearly on the noise and the regularization parameter. --- ### ResNet-50 with Class Reweighting and Anatomy-Guided Temporal Decoding for Gastrointestinal Video Analysis Authors: Romil Imtiaz, Dimitris K. Iakovidis Published: 2026-03-18 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.17784v2 We developed a multi-label gastrointestinal video analysis pipeline based on a ResNet-50 frame classifier followed by anatomy-guided temporal event decoding. The system predicts 17 labels, including 5 anatomy classes and 12 pathology classes, from frames resized to 336x336. A major challenge was severe class imbalance, particularly for rare pathology labels. To address this, we used clipped class-wise positive weighting in the training loss, which improved rare-class learning while maintaining stable optimization. At the temporal stage, we found that direct frame-to-event conversion produced fragmented mismatches with the official ground truth. The final submission therefore combined GT-style framewise event composition, anatomy vote smoothing, and anatomy-based pathology gating with a conservative hysteresis decoder. This design improved the final temporal mAP from 0.3801 to 0.4303 on the challenge test set. --- ### Exploring parameter-efficient fine-tuning (PEFT) of billion-parameter vision models with QLoRA and DoRA: insights into generalization for limited-data image classification under a 98:1 test-to-train regime Authors: Haiyu Yang, Sumit Sharma, Enhong Liu, Miel Hostens Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17782v1 Automated behavior classification is essential for precision livestock farming but faces challenges of high computational costs and limited labeled data. This study systematically compared three approaches: training from scratch (ResNet-18, ViT-Small), frozen feature extraction, and parameter-efficient fine-tuning (PEFT) of the DINOv3 foundation model (6.7 billion parameters). We evaluated QLoRA and DoRA across multiple configurations varying rank (8, 16, 64) and target modules (q_proj versus all-linear layers). With 2,160 verified training images, we assessed generalization of our model on 211,800 test samples, which is essentially a 98:1 test-to-train ratio. Results demonstrated that PEFT substantially outperformed alternatives, where the best QLoRA configuration (all-linear layers and rank=64) achieved 83.16% test accuracy with only 2.72% parameters (183.0M) in 5.8 hours, compared to 72.87% for ResNet-18 (16.8 hours), 61.91% for ViT-Small (18.7 hours), and 76.56% for frozen DINOv3 (17.5 hours). DoRA achieved comparable accuracy (83.14%) but with longer training time (11.0 hours). Notably, increasing adapter capacity consistently improved generalization while simultaneously not causing overfitting: reducing rank from 16 to 8 decreased test accuracy from 78.38% to 77.17%, while expanding from q_proj-only to all-linear layers with rank=64 improved accuracy from 78.38% to 83.16%. This suggests underfitting, instead of overfitting, is the primary challenge when adapting foundation models to agricultural imagery. Our findings provide guidelines for deploying billion-parameter vision models with PEFT in agricultural livestock applications. --- ### Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory Authors: Oliver Zahn, Simran Chana Published: 2026-03-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.17781v1 Large language models increasingly serve as persistent knowledge workers, with in-context memory - facts stored in the prompt - as the default strategy. We benchmark in-context memory against Knowledge Objects (KOs), discrete hash-addressed tuples with O(1) retrieval. Within the context window, Claude Sonnet 4.5 achieves 100% exact-match accuracy from 10 to 7,000 facts (97.5% of its 200K window). However, production deployment reveals three failure modes: capacity limits (prompts overflow at 8,000 facts), compaction loss (summarization destroys 60% of facts), and goal drift (cascading compaction erodes 54% of project constraints while the model continues with full confidence). KOs achieve 100% accuracy across all conditions at 252x lower cost. On multi-hop reasoning, KOs reach 78.9% versus 31.6% for in-context. Cross-model replication across four frontier models confirms compaction loss is architectural, not model-specific. We additionally show that embedding retrieval fails on adversarial facts (20% precision at 1) and that neural memory (Titans) stores facts but fails to retrieve them on demand. We introduce density-adaptive retrieval as a switching mechanism and release the benchmark suite. --- ### CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image Authors: Yizheng Song, Yiyu Zhuang, Qipeng Xu, Haixiang Wang, Jiahe Zhu, Jing Tian, Siyu Zhu, Hao Zhu Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17779v2 Single-view 3D human reconstruction has garnered significant attention in recent years. Despite numerous advancements, prior research has concentrated on reconstructing 3D models from clear, close-up images of individual subjects, often yielding subpar results in the more prevalent multi-person scenarios. Reconstructing 3D human crowd models is a highly intricate task, laden with challenges such as: 1) extensive occlusions, 2) low clarity, and 3) numerous and various appearances. To address this task, we propose CrowdGaussian, a unified framework that directly reconstructs multi-person 3D Gaussian Splatting (3DGS) representations from single-image inputs. To handle occlusions, we devise a self-supervised adaptation pipeline that enables the pretrained large human model to reconstruct complete 3D humans with plausible geometry and appearance from heavily occluded inputs. Furthermore, we introduce Self-Calibrated Learning (SCL). This training strategy enables single-step diffusion models to adaptively refine coarse renderings to optimal quality by blending identity-preserving samples with clean/corrupted image pairs. The outputs can be distilled back to enhance the quality of multi-person 3DGS representations. Extensive experiments demonstrate that CrowdGaussian generates photorealistic, geometrically coherent reconstructions of multi-person scenes. ---