# Research Papers — 2026-03 · bundle page 47 of 243 > Full-text markdown of papers #2301–2350 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/47 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/46.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/48.md) ### Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction Authors: Haresh Rengaraj Rajamohan, Xiang Gao, Weicheng Zhu, Shih-Lun Huang, Long Chen, Gabe Schulman, Huizhen Jin, Shengduo Li, Yixuan Wang, Huidi Yang, Kyunghyun Cho, Cem M. Deniz et al. Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.24562v2 While large-scale pretraining has revolutionized language modeling, its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present RAVEN, a novel generative pretraining strategy for sequential EHR data based on Recurrence-Aware next-Visit EveNt prediction. Leveraging a dataset of over one million unique individuals, our model learns to autoregressively generate tokenized clinical events for the next visit conditioned on patient history. We introduce regularization on predicting repeated events and highlight a key pitfall in EHR-based foundation model evaluations: repeated event tokens can inflate performance metrics when new onsets are not distinguished from subsequent occurrences. Furthermore, we empirically investigate the scaling behaviors in a data-constrained, compute-saturated regime, showing that simply increasing model size is suboptimal without commensurate increases in data volume. We evaluate our model via zero-shot prediction for forecasting the incidence of a diverse set of diseases, where it rivals fully fine-tuned representation-based Transformer models and outperforms both standard simulation-based next-token approaches and a prompted medical large language model baseline. Finally, without additional parameter updates, we show that RAVEN can generalize to an external patient cohort under lossy clinical code mappings and feature coverage gaps. --- ### The Free-Market Algorithm: Self-Organizing Optimization for Open-Ended Complex Systems Authors: Martin Jaraiz Published: 2026-03-25 Categories: cs.NE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.24559v1 We introduce the Free-Market Algorithm (FMA), a novel metaheuristic inspired by free-market economics. Unlike Genetic Algorithms, Particle Swarm Optimization, and Simulated Annealing -- which require prescribed fitness functions and fixed search spaces -- FMA uses distributed supply-and-demand dynamics where fitness is emergent, the search space is open-ended, and solutions take the form of hierarchical pathway networks. Autonomous agents discover rules, trade goods, open and close firms, and compete for demand with no centralized controller. FMA operates through a three-layer architecture: a universal market mechanism (supply, demand, competition, selection), pluggable domain-specific behavioral rules, and domain-specific observation. The market mechanism is identical across applications; only the behavioral rules change. Validated in two unrelated domains. In prebiotic chemistry, starting from 900 bare atoms (C, H, O, N), FMA discovers all 12 feasible amino acid formulas, all 5 nucleobases, the formose sugar chain, and Krebs cycle intermediates in under 5 minutes on a laptop -- with up to 240 independent synthesis routes per product. In macroeconomic forecasting, reading a single input-output table with zero estimated parameters, FMA achieves Mean Absolute Error of 0.42 percentage points for non-crisis GDP prediction, comparable to professional forecasters, portable to 33 countries. Assembly Theory alignment shows that FMA provides the first explicit, tunable mechanism for the selection signatures described by Sharma et al. (Nature, 2023). The event-driven assembly dynamics resonate with foundational programs in physics -- causal set theory, relational quantum mechanics, constructor theory -- suggesting that Darwinian market dynamics may reflect a deeper organizational principle that lead to the unfolding of Nature itself. --- ### LensWalk: Agentic Video Understanding by Planning How You See in Videos Authors: Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.24558v1 The dense, temporal nature of video presents a profound challenge for automated analysis. Despite the use of powerful Vision-Language Models, prevailing methods for video understanding are limited by the inherent disconnect between reasoning and perception: they rely on static, pre-processed information and cannot actively seek raw evidence from video as their understanding evolves. To address this, we introduce LensWalk, a flexible agentic framework that empowers a Large Language Model reasoner to control its own visual observation actively. LensWalk establishes a tight reason-plan-observe loop where the agent dynamically specifies, at each step, the temporal scope and sampling density of the video it observes. Using a suite of versatile, Vision-Language Model based tools parameterized by these specifications, the agent can perform broad scans for cues, focus on specific segments for fact extraction, and stitch evidence from multiple moments for holistic verification. This design allows for progressive, on-demand evidence gathering that directly serves the agent's evolving chain of thought. Without requiring any model fine-tuning, LensWalk delivers substantial, plug-and-play performance gains on multiple model recipes, boosting their accuracy by over 5\% on challenging long-video benchmarks like LVBench and Video-MME. Our analysis reveals that enabling an agent to control how it sees is key to unlocking more accurate, robust, and interpretable video reasoning. --- ### Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents Authors: Samuel Taiwo, Mohd Amaluddin Yusoff Published: 2026-03-25 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.24556v1 Retrieval-Augmented Generation (RAG) has emerged as a framework to address the constraints of Large Language Models (LLMs). Yet, its effectiveness fundamentally hinges on document chunking - an often-overlooked determinant of its quality. This paper presents an empirical study quantifying performance differences across four chunking strategies: fixed-size sliding window, recursive, breakpoint-based semantic, and structure-aware. We evaluated these methods using a proprietary corpus of oil and gas enterprise documents, including text-heavy manuals, table-heavy specifications, and piping and instrumentation diagrams (P and IDs). Our findings show that structure-aware chunking yields higher overall retrieval effectiveness, particularly in top-K metrics, and incurs significantly lower computational costs than semantic or baseline strategies. Crucially, all four methods demonstrated limited effectiveness on P and IDs, underscoring a core limitation of purely text-based RAG within visually and spatially encoded documents. We conclude that while explicit structure preservation is essential for specialised domains, future work must integrate multimodal models to overcome current limitations. --- ### The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series Authors: Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mirela Tulbure, Patrick Hostert, Stefan Erasmi Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24552v1 Organic farming is a key element in achieving more sustainable agriculture. For a better understanding of the development and impact of organic farming, comprehensive, spatially explicit information is needed. This study presents an approach for the discrimination of organic and conventional farming systems using intra-annual Sentinel-2 time series. In addition, it examines two factors influencing this discrimination: the joint learning of crop type information in a concurrent task and the role of spatial context. A Vision Transformer model based on the Temporo-Spatial Vision Transformer (TSViT) architecture was used to construct a classification model for the two farming systems. The model was extended for simultaneous learning of the crop type, creating a multitask learning setting. By varying the patch size presented to the model, we tested the influence of spatial context on the classification accuracy of both tasks. We show that discrimination between organic and conventional farming systems using multispectral remote sensing data is feasible. However, classification performance varies substantially across crop types. For several crops, such as winter rye, winter wheat, and winter oat, F1 scores of 0.8 or higher can be achieved. In contrast, other agricultural land use classes, such as permanent grassland, orchards, grapevines, and hops, cannot be reliably distinguished, with F1 scores for the organic management class of 0.4 or lower. Joint learning of farming system and crop type provides only limited additional benefits over single-task learning. In contrast, incorporating wider spatial context improves the performance of both farming system and crop type classification. Overall, we demonstrate that a classification of agricultural farming systems is possible in a diverse agricultural region using multispectral remote sensing data. --- ### A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English Authors: Dana Serditova, Kevin Tang Published: 2026-03-25 Categories: cs.CL, cs.AI, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2603.24549v1 Automatic Speech Recognition (ASR) systems are widely used in everyday communication, education, healthcare, and industry, yet their performance remains uneven across speakers, particularly when dialectal variation diverges from the mainstream accents represented in training data. This study investigates ASR bias through a sociolinguistic analysis of Newcastle English, a regional variety of North-East England that has been shown to challenge current speech recognition technologies. Using spontaneous speech from the Diachronic Electronic Corpus of Tyneside English (DECTE), we evaluate the output of a state-of-the-art commercial ASR system and conduct a fine-grained analysis of more than 3,000 transcription errors. Errors are classified by linguistic domain and examined in relation to social variables including gender, age, and socioeconomic status. In addition, an acoustic case study of selected vowel features demonstrates how gradient phonetic variation contributes directly to misrecognition. The results show that phonological variation accounts for the majority of errors, with recurrent failures linked to dialect-specific features like vowel quality and glottalisation, as well as local vocabulary and non-standard grammatical forms. Error rates also vary across social groups, with higher error frequencies observed for men and for speakers at the extremes of the age spectrum. These findings indicate that ASR errors are not random but socially patterned and can be explained from a sociolinguistic perspective. Thus, the study demonstrates the importance of incorporating sociolinguistic expertise into the evaluation and development of speech technologies and argues that more equitable ASR systems require explicit attention to dialectal variation and community-based speech data. --- ### Detection of local geometry in random graphs: information-theoretic and computational limits Authors: Jinho Bok, Shuangping Li, Sophie H. Yu Published: 2026-03-25 Categories: math.ST, cs.CC, cs.DS, math.PR, stat.ML arXiv: https://arxiv.org/abs/2603.24545v1 We study the problem of detecting local geometry in random graphs. We introduce a model $\mathcal{G}(n, p, d, k)$, where a hidden community of average size $k$ has edges drawn as a random geometric graph on $\mathbb{S}^{d-1}$, while all remaining edges follow the Erdős--Rényi model $\mathcal{G}(n, p)$. The random geometric graph is generated by thresholding inner products of latent vectors on $\mathbb{S}^{d-1}$, with each edge having marginal probability equal to $p$. This implies that $\mathcal{G}(n, p, d, k)$ and $\mathcal{G}(n, p)$ are indistinguishable at the level of the marginals, and the signal lies entirely in the edge dependencies induced by the local geometry. We investigate both the information-theoretic and computational limits of detection. On the information-theoretic side, our upper bounds follow from three tests based on signed triangle counts: a global test, a scan test, and a constrained scan test; our lower bounds follow from two complementary methods: truncated second moment via Wishart--GOE comparison, and tensorization of KL divergence. These results together settle the detection threshold at $d = \widetildeΘ(k^2 \vee k^6/n^3)$ for fixed $p$, and extend the state-of-the-art bounds from the full model (i.e., $k = n$) for vanishing $p$. On the computational side, we identify a computational--statistical gap and provide evidence via the low-degree polynomial framework, as well as the suboptimality of signed cycle counts of length $\ell \geq 4$. --- ### Analysing the Safety Pitfalls of Steering Vectors Authors: Yuxiao Li, Alina Fastowski, Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci Published: 2026-03-25 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2603.24543v1 Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work, we present a systematic safety audit of steering vectors obtained with Contrastive Activation Addition (CAA), a widely used steering approach, under a unified evaluation protocol. Using JailbreakBench as benchmark, we show that steering vectors consistently influence the success rate of jailbreak attacks, with stronger amplification under simple template-based attacks. Across LLM families and sizes, steering the model in specific directions can drastically increase (up to 57%) or decrease (up to 50%) its attack success rate (ASR), depending on the targeted behavior. We attribute this phenomenon to the overlap between the steering vectors and the latent directions of refusal behavior. Thus, we offer a traceable explanation for this discovery. Together, our findings reveal the previously unobserved origin of this safety gap in LLMs, highlighting a trade-off between controllability and safety. --- ### SEGAR: Selective Enhancement for Generative Augmented Reality Authors: Fanjun Bu, Chenyang Yuan, Hiroshi Yasuda Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.24541v1 Generative world models offer a compelling foundation for augmented-reality (AR) applications: by predicting future image sequences that incorporate deliberate visual edits, they enable temporally coherent, augmented future frames that can be computed ahead of time and cached, avoiding per-frame rendering from scratch in real time. In this work, we present SEGAR, a preliminary framework that combines a diffusion-based world model with a selective correction stage to support this vision. The world model generates augmented future frames with region-specific edits while preserving others, and the correction stage subsequently aligns safety-critical regions with real-world observations while preserving intended augmentations elsewhere. We demonstrate this pipeline in driving scenarios as a representative setting where semantic region structure is well defined and real-world feedback is readily available. We view this as an early step toward generative world models as practical AR infrastructure, where future frames can be generated, cached, and selectively corrected on demand. --- ### CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition Authors: Florian Stilz, Vinkle Srivastav, Nassir Navab, Nicolas Padoy Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.24539v1 Video-language foundation models have proven to be highly effective in zero-shot applications across a wide range of tasks. A particularly challenging area is the intraoperative surgical procedure domain, where labeled data is scarce, and precise temporal understanding is often required for complex downstream tasks. To address this challenge, we introduce CliPPER (Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition), a novel video-language pretraining framework trained on surgical lecture videos. Our method is designed for fine-grained temporal video-text recognition and introduces several novel pretraining strategies to improve multimodal alignment in long-form surgical videos. Specifically, we propose Contextual Video-Text Contrastive Learning (VTC_CTX) and Clip Order Prediction (COP) pretraining objectives, both of which leverage temporal and contextual dependencies to enhance local video understanding. In addition, we incorporate a Cycle-Consistency Alignment over video-text matches within the same surgical video to enforce bidirectional consistency and improve overall representation coherence. Moreover, we introduce a more refined alignment loss, Frame-Text Matching (FTM), to improve the alignment between video frames and text. As a result, our model establishes a new state-of-the-art across multiple public surgical benchmarks, including zero-shot recognition of phases, steps, instruments, and triplets. The source code and pretraining captions can be found at https://github.com/CAMMA-public/CliPPER. --- ### Robust Multilingual Text-to-Pictogram Mapping for Scalable Reading Rehabilitation Authors: Soufiane Jhilal, Martina Galletti Published: 2026-03-25 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2603.24536v2 Reading comprehension presents a significant challenge for children with Special Educational Needs and Disabilities (SEND), often requiring intensive one-on-one reading support. To assist therapists in scaling this support, we developed a multilingual, AI-powered interface that automatically enhances text with visual scaffolding. This system dynamically identifies key concepts and maps them to contextually relevant pictograms, supporting learners across languages. We evaluated the system across five typologically diverse languages (English, French, Italian, Spanish, and Arabic), through multilingual coverage analysis, expert clinical review by speech therapists and special education professionals, and latency assessment. Evaluation results indicate high pictogram coverage and visual scaffolding density across the five languages. Expert audits suggested that automatically selected pictograms were semantically appropriate, with combined correct and acceptable ratings exceeding 95% for the four European languages and approximately 90% for Arabic despite reduced pictogram repository coverage. System latency remained within interactive thresholds suitable for real-time educational use. These findings support the technical viability, semantic safety, and acceptability of automated multimodal scaffolding to improve accessibility for neurodiverse learners. --- ### Representation Learning to Study Temporal Dynamics in Tutorial Scaffolding Authors: Conrad Borchers, Jiayi Zhang, Ashish Gurung Published: 2026-03-25 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.24535v1 Adaptive scaffolding enhances learning, yet the field lacks robust methods for measuring it within authentic tutoring dialogue. This gap has become more pressing with the rise of remote human tutoring and large language model-based systems. We introduce an embedding-based approach that analyzes scaffolding dynamics by aligning the semantics of dialogue turns, problem statements, and correct solutions. Specifically, we operationalize alignment by computing cosine similarity between tutor and student contributions and task-relevant content. We apply this framework to 1,576 real-world mathematics tutoring dialogues from the Eedi Question Anchored Tutoring Dialogues dataset. The analysis reveals systematic differences in task alignment and distinct temporal patterns in how participants ground their contributions in problem and solution content. Further, mixed-effects models show that role-specific semantic alignment predicts tutorial progression beyond baseline features such as message order and length. Tutor contributions exhibited stronger grounding in problem content early in interactions. In contrast, student solution alignment was modestly positively associated with progression. These findings support scaffolding as a continuous, role-sensitive process grounded in task semantics. By capturing role-specific alignment over time, this approach provides a principled method for analyzing instructional dialogue and evaluating conversational tutoring systems. --- ### UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience Authors: Zichuan Lin, Feiyu Liu, Yijun Yang, Jiafei Lyu, Yiming Gao, Yicheng Liu, Zhicong Lu, Yangbin Yu, Mingyu Yang, Junyou Li, Deheng Ye, Jie Jiang Published: 2026-03-25 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.24533v1 Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second stage introduces Group Relative Self-Distillation (GRSD), which identifies critical fork points in group rollouts and constructs dense step-level supervision from successful trajectories to correct failed ones. Extensive experiments on AndroidWorld show that our 4B model achieves an 81.0% Pass@1 success rate, outperforming numerous recent baselines and exceeding human-level performance. Ablation and case studies further verify the effectiveness of GRSD. Our method represents a significant leap toward efficient, self-evolving, and high-performance mobile GUI automation without expensive manual data annotation. --- ### Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification Authors: Dipam Goswami, Simone Magistri, Gido M. van de Ven, Bartłomiej Twardowski, Andrew D. Bagdanov, Tinne Tuytelaars, Joost van de Weijer Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24528v1 Vision-language models (VLMs) like CLIP are trained with the objective of aligning text and image pairs. To improve CLIP-based few-shot image classification, recent works have observed that, along with text embeddings, image embeddings from the training set are an important source of information. In this work we investigate the impact of directly mixing image and text prototypes for few-shot classification and analyze this from a bias-variance perspective. We show that mixing prototypes acts like a shrinkage estimator. Although mixed prototypes improve classification performance, the image prototypes still add some noise in the form of instance-specific background or context information. In order to capture only information from the image space relevant to the given classification task, we propose projecting image prototypes onto the principal directions of the semantic text embedding space to obtain a text-aligned semantic image subspace. These text-aligned image prototypes, when mixed with text embeddings, further improve classification. However, for downstream datasets with poor cross-modal alignment in CLIP, semantic alignment might be suboptimal. We show that the image subspace can still be leveraged by modeling the anisotropy using class covariances. We demonstrate that combining a text-aligned mixed prototype classifier and an image-specific LDA classifier outperforms existing methods across few-shot classification benchmarks. --- ### From Liar Paradox to Incongruent Sets: A Normal Form for Self-Reference Authors: Shalender Singh, Vishnu Priya Singh Parmar Published: 2026-03-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.24527v1 We introduce incongruent normal form (INF), a structural representation for self-referential semantic sentences. An INF replaces a self-referential sentence with a finite family of non-self-referential sentences that are individually satisfiable but not jointly satisfiable. This transformation isolates the semantic obstruction created by self-reference while preserving classical semantics locally and is accompanied by correctness theorems characterizing when global inconsistency arises from locally compatible commitments. We then study the role of incongruence as a structural source of semantic informativeness. Using a minimal model-theoretic notion of informativeness-understood as the ability of sentences to distinguish among admissible models-we show that semantic completeness precludes informativeness, while incongruence preserves it. Moreover, incongruence is not confined to paradoxical constructions: any consistent incomplete first-order theory admits finite incongruent families arising from incompatible complete extensions. In this sense, incompleteness manifests structurally as locally realizable but globally incompatible semantic commitments, providing a minimal formal basis for semantic knowledge. Finally, we introduce a quantitative semantic framework. In a canonical finite semantic-state setting, we model semantic commitments as Boolean functions and define a Fourier-analytic notion of semantic energy based on total influence. We derive uncertainty-style bounds relating semantic determinacy, informativeness, and spectral simplicity, and establish a matrix inequality bounding aggregate semantic variance by total semantic energy. These results show quantitatively that semantic informativeness cannot collapse into a single determinate state without unbounded energy cost, identifying incongruence as a fundamental structural and quantitative feature of semantic representation. --- ### No Single Metric Tells the Whole Story: A Multi-Dimensional Evaluation Framework for Uncertainty Attributions Authors: Emily Schiller, Teodor Chiaburu, Marco Zullich, Luca Longo Published: 2026-03-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.24524v1 Research on explainable AI (XAI) has frequently focused on explaining model predictions. More recently, methods have been proposed to explain prediction uncertainty by attributing it to input features (uncertainty attributions). However, the evaluation of these methods remains inconsistent as studies rely on heterogeneous proxy tasks and metrics, hindering comparability. We address this by aligning uncertainty attributions with the well-established Co-12 framework for XAI evaluation. We propose concrete implementations for the correctness, consistency, continuity, and compactness properties. Additionally, we introduce conveyance, a property tailored to uncertainty attributions that evaluates whether controlled increases in epistemic uncertainty reliably propagate to feature-level attributions. We demonstrate our evaluation framework with eight metrics across combinations of uncertainty quantification and feature attribution methods on tabular and image data. Our experiments show that gradient-based methods consistently outperform perturbation-based approaches in consistency and conveyance, while Monte-Carlo dropconnect outperforms Monte-Carlo dropout in most metrics. Although most metrics rank the methods consistently across samples, inter-method agreement remains low. This suggests no single metric sufficiently evaluates uncertainty attribution quality. The proposed evaluation framework contributes to the body of knowledge by establishing a foundation for systematic comparison and development of uncertainty attribution methods. --- ### TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models Authors: Yushi Guan, Jeanine Ohene-Agyei, Daniel Kwan, Jean Sebastien Dandurand, Yifei Zhang, Nandita Vijaykumar Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.24518v1 To embed domain-specific or specialized knowledge into pre-trained foundation models, fine-tuning using techniques such as parameter efficient fine-tuning (e.g. LoRA) is a common practice. However, as new LLM architectures and pre-trained models emerge, transferring this specialized knowledge to newer models becomes an important task. In many scenarios, the original specialized data may be unavailable due to privacy or commercial restrictions, necessitating distillation and transfer of this specialized knowledge from the fine-tuned base model to a different pre-trained model. We present TuneShift-KD, a novel approach that automatically distills specialized knowledge from a fine-tuned model to a target model using only a few examples representative of the specialized information. Our key insight is that specialized knowledge can be identified through perplexity differences between base and fine-tuned models: prompts where the fine-tuned model responds confidently (low perplexity), but the base model struggles (high perplexity), indicate queries corresponding to the specialized knowledge learned by the fine-tuned model. TuneShift-KD leverages this insight to create a synthetic training dataset to transfer the specialized knowledge. Using an iterative process, TuneShift-KD generates more prompts similar to those that generated responses with specialized knowledge. TuneShift-KD does not require training discriminators or access to training datasets. It is an automated approach that only requires the initial fine-tuned and base models and a few representative prompts. Our experiments demonstrate that models fine-tuned using TuneShift-KD achieve higher accuracy than prior approaches, enabling ease of deployment and more effective transfer of the specialized knowledge. --- ### AVO: Agentic Variation Operators for Autonomous Evolutionary Search Authors: Terry Chen, Zhifan Ye, Bing Xu, Zihao Ye, Timmy Liu, Ali Hassani, Tianqi Chen, Andrew Kerr, Haicheng Wu, Yang Xu, Yu-Jung Chen, Hanfeng Chen et al. Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.24517v1 Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evolutionary search with autonomous coding agents. Rather than confining a language model to candidate generation within a prescribed pipeline, AVO instantiates variation as a self-directed agent loop that can consult the current lineage, a domain-specific knowledge base, and execution feedback to propose, repair, critique, and verify implementation edits. We evaluate AVO on attention, among the most aggressively optimized kernel targets in AI, on NVIDIA Blackwell (B200) GPUs. Over 7 days of continuous autonomous evolution on multi-head attention, AVO discovers kernels that outperform cuDNN by up to 3.5% and FlashAttention-4 by up to 10.5% across the evaluated configurations. The discovered optimizations transfer readily to grouped-query attention, requiring only 30 minutes of additional autonomous adaptation and yielding gains of up to 7.0% over cuDNN and 9.3% over FlashAttention-4. Together, these results show that agentic variation operators move beyond prior LLM-in-the-loop evolutionary pipelines by elevating the agent from candidate generator to variation operator, and can discover performance-critical micro-architectural optimizations that produce kernels surpassing state-of-the-art expert-engineered attention implementations on today's most advanced GPU hardware. --- ### Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs Authors: Alexander Panfilov, Peter Romov, Igor Shilov, Yves-Alexandre de Montjoye, Jonas Geiping, Maksym Andriushchenko Published: 2026-03-25 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2603.24511v2 We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations. We deploy frontier agents, such as Claude Code and Codex, in an autoresearch loop with access to a library of 30+ prior methods and an evaluation script with a fixed compute budget. We show this pipeline to be effective in jailbreaking OpenAI's GPT-OSS-Safeguard-20B and in prompt injections against Meta-SecAlign-70B, an adversarially robust model. For GPT-OSS-Safeguard, the best agent-discovered method achieves up to 80\% attack success rate on CBRN queries, compared to <50\% for existing methods. For SecAlign, it achieves 100\% ASR, while the best prior automated methods only achieve 82\%. Notably, in our setting, attack methods are developed on unrelated surrogate models for a pure random-target token-forcing task, yet generalize directly to prompt injection on the adversarially trained model. Finally, we trace the lineage of methods developed during autoresearch, characterizing the agents' strategies and failure modes. Adversarial ML has long held that defenses must be evaluated against attacks tailored to them; autoresearch automates this principle, and we argue it should be the minimum bar for defense evaluation going forward. --- ### Toward Physically Consistent Driving Video World Models under Challenging Trajectories Authors: Jiawei Zhou, Zhenxin Zhu, Lingyi Du, Linye Lyu, Lijun Zhou, Zhanqian Wu, Hongcheng Luo, Zhuotao Tian, Bing Wang, Guang Chen, Hangjun Ye, Haiyang Sun et al. Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24506v2 Video generation models have shown strong potential as world models for autonomous driving simulation. However, existing approaches are primarily trained on real-world driving datasets, which mostly contain natural and safe driving scenarios. As a result, current models often fail when conditioned on challenging or counterfactual trajectories-such as imperfect trajectories generated by simulators or planning systems-producing videos with severe physical inconsistencies and artifacts. To address this limitation, we propose PhyGenesis, a world model designed to generate driving videos with high visual fidelity and strong physical consistency. Our framework consists of two key components: (1) a physical condition generator that transforms potentially invalid trajectory inputs into physically plausible conditions, and (2) a physics-enhanced video generator that produces high-fidelity multi-view driving videos under these conditions. To effectively train these components, we construct a large-scale, physics-rich heterogeneous dataset. Specifically, in addition to real-world driving videos, we generate diverse challenging driving scenarios using the CARLA simulator, from which we derive supervision signals that guide the model to learn physically grounded dynamics under extreme conditions. This challenging-trajectory learning strategy enables trajectory correction and promotes physically consistent video generation. Extensive experiments demonstrate that PhyGenesis consistently outperforms state-of-the-art methods, especially on challenging trajectories. Our project page is available at: https://wm-research.github.io/PhyGenesis/. --- ### Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling Authors: Mihaela-Larisa Clement, Mónika Farsang, Agnes Poks, Johannes Edelmann, Manfred Plöchl, Radu Grosu, Ezio Bartocci Published: 2026-03-25 Categories: cs.LG, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2603.24503v1 The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on embedded hardware, especially when models are complex or horizons are long. Learning-based NMPC approximations shift this computation offline but typically demand large expert datasets and costly training. We propose Sequential-AMPC, a sequential neural policy that generates MPC candidate control sequences by sharing parameters across the prediction horizon. For deployment, we wrap the policy in a safety-augmented online evaluation and fallback mechanism, yielding Safe Sequential-AMPC. Compared to a naive feedforward policy baseline across several benchmarks, Sequential-AMPC requires substantially fewer expert MPC rollouts and yields candidate sequences with higher feasibility rates and improved closed-loop safety. On high-dimensional systems, it also exhibits better learning dynamics and performance in fewer epochs while maintaining stable validation improvement where the feedforward baseline can stagnate. --- ### Project and Generate: Divergence-Free Neural Operators for Incompressible Flows Authors: Xigui Li, Hongwei Zhang, Ruoxi Jiang, Deshu Chen, Chensen Lin, Limei Han, Yuan Qi, Xin Guo, Yuan Cheng Published: 2026-03-25 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2603.24500v1 Learning-based models for fluid dynamics often operate in unconstrained function spaces, leading to physically inadmissible, unstable simulations. While penalty-based methods offer soft regularization, they provide no structural guarantees, resulting in spurious divergence and long-term collapse. In this work, we introduce a unified framework that enforces the incompressible continuity equation as a hard, intrinsic constraint for both deterministic and generative modeling. First, to project deterministic models onto the divergence-free subspace, we integrate a differentiable spectral Leray projection grounded in the Helmholtz-Hodge decomposition, which restricts the regression hypothesis space to physically admissible velocity fields. Second, to generate physically consistent distributions, we show that simply projecting model outputs is insufficient when the prior is incompatible. To address this, we construct a divergence-free Gaussian reference measure via a curl-based pushforward, ensuring the entire probability flow remains subspace-consistent by construction. Experiments on 2D Navier-Stokes equations demonstrate exact incompressibility up to discretization error and substantially improved stability and physical consistency. --- ### Reflected diffusion models adapt to low-dimensional data Authors: Asbjørn Holk, Claudia Strauch, Lukas Trottner Published: 2026-03-25 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2603.24495v1 While the mathematical foundations of score-based generative models are increasingly well understood for unconstrained Euclidean spaces, many practical applications involve data restricted to bounded domains. This paper provides a statistical analysis of reflected diffusion models on the hypercube $(0,1)^D$ for target distributions supported on $d$-dimensional linear subspaces. A primary challenge in this setting is the absence of Gaussian transition kernels, which play a central role in standard theory in $\mathbb{R}^D$. By employing an easily implementable infinite series expansion of the transition densities, we develop analytic tools to bound the score function and its approximation by sparse ReLU networks. For target densities with Sobolev smoothness $α$, we establish a convergence rate in the $1$-Wasserstein distance of order $n^{-\frac{α+1-δ}{2α+d}}$ for arbitrarily small $δ> 0$, demonstrating that the generative algorithm fully adapts to the intrinsic dimension $d$. These results confirm that the presence of reflecting boundaries does not degrade the fundamental statistical efficiency of the diffusion paradigm, matching the almost optimal rates known for unconstrained settings. --- ### Uniform Laws of Large Numbers in Product Spaces Authors: Ron Holzman, Shay Moran, Alexander Shlimovich Published: 2026-03-25 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2603.24493v1 Uniform laws of large numbers form a cornerstone of Vapnik--Chervonenkis theory, where they are characterized by the finiteness of the VC dimension. In this work, we study uniform convergence phenomena in cartesian product spaces, under assumptions on the underlying distribution that are compatible with the product structure. Specifically, we assume that the distribution is absolutely continuous with respect to the product of its marginals, a condition that captures many natural settings, including product distributions, sparse mixtures of product distributions, distributions with low mutual information, and more. We show that, under this assumption, a uniform law of large numbers holds for a family of events if and only if the linear VC dimension of the family is finite. The linear VC dimension is defined as the maximum size of a shattered set that lies on an axis-parallel line, namely, a set of vectors that agree on all but at most one coordinate. This dimension is always at most the classical VC dimension, yet it can be arbitrarily smaller. For instance, the family of convex sets in $\mathbb{R}^d$ has linear VC dimension $2$, while its VC dimension is infinite already for $d\ge 2$. Our proofs rely on estimator that departs substantially from the standard empirical mean estimator and exhibits more intricate structure. We show that such deviations from the standard empirical mean estimator are unavoidable in this setting. Throughout the paper, we propose several open questions, with a particular focus on quantitative sample complexity bounds. --- ### Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Models Authors: Siqi Liu, Xinyang Li, Bochao Zou, Junbao Zhuo, Huimin Ma, Jiansheng Chen Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24484v1 As large language models (LLMs) continue to advance, there is increasing interest in their ability to infer human mental states and demonstrate a human-like Theory of Mind (ToM). Most existing ToM evaluations, however, are centered on text-based inputs, while scenarios relying solely on visual information receive far less attention. This leaves a gap, since real-world human-AI interaction typically requires multimodal understanding. In addition, many current methods regard the model as a black box and rarely probe how its internal attention behaves in multiple-choice question answering (QA). The impact of LLM hallucinations on such tasks is also underexplored from an interpretability perspective. To address these issues, we introduce VisionToM, a vision-oriented intervention framework designed to strengthen task-aware reasoning. The core idea is to compute intervention vectors that align visual representations with the correct semantic targets, thereby steering the model's attention through different layers of visual features. This guidance reduces the model's reliance on spurious linguistic priors, leading to more reliable multimodal language model (MLLM) outputs and better QA performance. Experiments on the EgoToM benchmark-an egocentric, real-world video dataset for ToM with three multiple-choice QA settings-demonstrate that our method substantially improves the ToM abilities of MLLMs. Furthermore, results on an additional open-ended generation task show that VisionToM enables MLLMs to produce free-form explanations that more accurately capture agents' mental states, pushing machine-human collaboration toward greater alignment. --- ### Multi-Agent Reasoning with Consistency Verification Improves Uncertainty Calibration in Medical MCQA Authors: John Ray B. Martinez Published: 2026-03-25 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.24481v2 Miscalibrated confidence scores are a practical obstacle to deploying AI in clinical settings. A model that is always overconfident offers no useful signal for deferral. We present a multi-agent framework that combines domain-specific specialist agents with Two-Phase Verification (Wu et al., 2024) and S-Score Weighted Fusion to improve both calibration and discrimination in medical multiple-choice question answering. Four specialist agents (respiratory, cardiology, neurology, gastroenterology) generate independent diagnoses using Qwen2.5-7B-Instruct. Each diagnosis undergoes a two-phase self-verification process that measures internal consistency and produces a Specialist Confidence Score (S-score). The S-scores drive a weighted fusion strategy that selects the final answer and calibrates the reported confidence. We evaluate on high-disagreement subsets of MedQA-USMLE and MedMCQA (100 and 250 questions). All results are specific to this filtered regime. On MedQA-250, the full system achieves ECE = 0.091 (74.4% reduction over the single-specialist baseline) and AUROC = 0.630 (+0.056) at 59.2% accuracy. Calibration gains of 49-74% hold across all four settings. Ablation analysis reveals that Two-Phase Verification drives ECE reduction while multi-agent reasoning drives AUROC improvement, suggesting that consistency checking and ensemble aggregation address different failure modes of LLM uncertainty. Whether the resulting confidence signal is sufficient to support clinical deferral decisions in practice remains a direction for future investigation. --- ### Positive-First Most Ambiguous: A Simple Active Learning Criterion for Interactive Retrieval of Rare Categories Authors: Kawtar Zaher, Olivier Buisson, Alexis Joly Published: 2026-03-25 Categories: cs.CV, cs.HC, cs.IR arXiv: https://arxiv.org/abs/2603.24480v2 Real-world fine-grained visual retrieval often requires discovering a rare concept from large unlabeled collections with minimal supervision. This is especially critical in biodiversity monitoring, ecological studies, and long-tailed visual domains, where the target may represent only a tiny fraction of the data, creating highly imbalanced binary problems. Interactive retrieval with relevance feedback offers a practical solution: starting from a small query, the system selects candidates for binary user annotation and iteratively refines a lightweight classifier. While Active Learning (AL) is commonly used to guide selection, conventional AL assumes symmetric class priors and large annotation budgets, limiting effectiveness in imbalanced, low-budget, low-latency settings. We introduce Positive-First Most Ambiguous (PF-MA), a simple yet effective AL criterion that explicitly addresses the class imbalance asymmetry: it prioritizes near-boundary samples while favoring likely positives, enabling rapid discovery of subtle visual categories while maintaining informativeness. Unlike standard methods that oversample negatives, PF-MA consistently returns small batches with a high proportion of relevant samples, improving early retrieval and user satisfaction. To capture retrieval diversity, we also propose a class coverage metric that measures how well selected positives span the visual variability of the target class. Experiments on long-tailed datasets, including fine-grained botanical data, demonstrate that PF-MA consistently outperforms strong baselines in both coverage and classifier performance, across varying class sizes and descriptors. Our results highlight that aligning AL with the asymmetric and user-centric objectives of interactive fine-grained retrieval enables simple yet powerful solutions for retrieving rare and visually subtle categories in realistic human-in-the-loop settings. --- ### Composer 2 Technical Report Authors: Cursor Research, :, Aaron Chan, Ahmed Shalaby, Alexander Wettig, Aman Sanger, Andrew Zhai, Anurag Ajay, Ashvin Nair, Charlie Snell, Chen Lu, Chen Shen et al. Published: 2026-03-25 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2603.24477v2 Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learning to improve end-to-end coding performance through stronger reasoning, accurate multi-step execution, and coherence on long-horizon realistic coding problems. We develop infrastructure to support training in the same Cursor harness that is used by the deployed model, with equivalent tools and structure, and use environments that match real problems closely. To measure the ability of the model on increasingly difficult tasks, we introduce a benchmark derived from real software engineering problems in large codebases including our own. Composer 2 is a frontier-level coding model and demonstrates a process for training strong domain-specialized models. On our CursorBench evaluations the model achieves a major improvement in accuracy compared to previous Composer models (61.3). On public benchmarks the model scores 61.7 on Terminal-Bench and 73.7 on SWE-bench Multilingual in our harness, comparable to state-of-the-art systems. --- ### Conformalized Transfer Learning for Li-ion Battery State of Health Forecasting under Manufacturing and Usage Variability Authors: Samuel Filgueira da Silva, Mehmet Fatih Ozkan, Faissal El Idrissi, Marcello Canova Published: 2026-03-25 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.24475v1 Accurate forecasting of state-of-health (SOH) is essential for ensuring safe and reliable operation of lithium-ion cells. However, existing models calibrated on laboratory tests at specific conditions often fail to generalize to new cells that differ due to small manufacturing variations or operate under different conditions. To address this challenge, an uncertainty-aware transfer learning framework is proposed, combining a Long Short-Term Memory (LSTM) model with domain adaptation via Maximum Mean Discrepancy (MMD) and uncertainty quantification through Conformal Prediction (CP). The LSTM model is trained on a virtual battery dataset designed to capture real-world variability in electrode manufacturing and operating conditions. MMD aligns latent feature distributions between simulated and target domains to mitigate domain shift, while CP provides calibrated, distribution-free prediction intervals. This framework improves both the generalization and trustworthiness of SOH forecasts across heterogeneous cells. --- ### Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? Authors: Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dohyung Kim, Jiwon Jeon, Dongsheng Li, Yuqing Yang Published: 2026-03-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.24472v4 Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading performance. We trace this degradation to the suppression of epistemic verbalization - the model's expression of uncertainty during reasoning. Through controlled experiments varying conditioning context richness and task coverage, we show that conditioning the teacher on rich information suppresses uncertainty expression, enabling rapid in-domain optimization with limited task coverage but harming OOD performance, where unseen problems benefit from expressing uncertainty and adjusting accordingly. Across Qwen3-1.7B/8B, DeepSeek-Distill-Qwen-7B, and Olmo3-7B-Instruct, we observe performance drops of up to 40%. Our findings highlight that exposing appropriate levels of uncertainty is crucial for robust reasoning and underscore the importance of optimizing reasoning behavior beyond merely reinforcing correct answer traces. --- ### Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? Authors: Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dohyung Kim, Jiwon Jeon, Dongsheng Li, Yuqing Yang Published: 2026-03-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.24472v3 Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading performance. We trace this degradation to the suppression of epistemic verbalization - the model's expression of uncertainty during reasoning. Through controlled experiments varying conditioning context richness and task coverage, we show that conditioning the teacher on rich information suppresses uncertainty expression, enabling rapid in-domain optimization with limited task coverage but harming OOD performance, where unseen problems benefit from expressing uncertainty and adjusting accordingly. Across Qwen3-1.7B/8B, DeepSeek-Distill-Qwen-7B, and Olmo3-7B-Instruct, we observe performance drops of up to 40%. Our findings highlight that exposing appropriate levels of uncertainty is crucial for robust reasoning and underscore the importance of optimizing reasoning behavior beyond merely reinforcing correct answer traces. --- ### Counting Without Numbers and Finding Without Words Authors: Badri Narayana Patro Published: 2026-03-25 Categories: cs.CV, cs.AI, cs.CL, cs.SI arXiv: https://arxiv.org/abs/2603.24470v2 Every year, 10 million pets enter shelters, separated from their families. Despite desperate searches by both guardians and lost animals, 70% never reunite, not because matches do not exist, but because current systems look only at appearance, while animals recognize each other through sound. We ask, why does computer vision treat vocalizing species as silent visual objects? Drawing on five decades of cognitive science showing that animals perceive quantity approximately and communicate identity acoustically, we present the first multimodal reunification system integrating visual and acoustic biometrics. Our species-adaptive architecture processes vocalizations from 10Hz elephant rumbles to 4kHz puppy whines, paired with probabilistic visual matching that tolerates stress-induced appearance changes. This work demonstrates that AI grounded in biological communication principles can serve vulnerable populations that lack human language. --- ### MechMath: Sorrifier-Driven Formal Decomposition Workflow for Automated Theorem Proving Authors: Ruichen Qiu, Yichuan Cao, Junqi Liu, Dakai Guo, Xiao-Shan Gao, Lihong Zhi, Ruyong Feng Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.24465v2 Recent advances in large language models (LLMs) and LLM-based agents have substantially improved the capabilities of automated theorem proving. However, for problems that require complex mathematical reasoning, current systems seldom succeed in their initial attempt, necessitating iterative adjustments to their proof strategies. Existing approaches for handling failed attempts typically either iteratively fix errors within the proof or discard the entire proof and regenerate it from scratch. The former leads to progressively longer contexts, which degrade the model's ability to attend to the remaining unresolved subproblems, while the latter is inefficient, as it may abandon mostly correct reasoning due to localized errors. To address this dilemma, we present MechMath, an agent system centered on a Sorrifier-driven formal decomposition paradigm. By leveraging the sorry placeholder in Lean to precisely isolate unresolved subgoals while preserving the surrounding verified proof structure, MechMath extracts each failed subproblem into a clean, self-contained context and resolves it independently. This avoids both the waste of full regeneration and the excessive context length induced by repeated repairs. Experimental results on challenging mathematical competition benchmarks, including IMO 2025, Putnam 2025, miniF2F, and a subset of ProverBench, demonstrate that our agent achieves significant advantages in proving efficiency. --- ### Mechanic: Sorrifier-Driven Formal Decomposition Workflow for Automated Theorem Proving Authors: Ruichen Qiu, Yichuan Cao, Junqi Liu, Dakai Guo, Xiao-Shan Gao, Lihong Zhi, Ruyong Feng Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.24465v1 Recent advances in large language models (LLMs) and LLM-based agents have substantially improved the capabilities of automated theorem proving. However, for problems requiring complex mathematical reasoning, current systems rarely succeed on the first try and must repeatedly modify their proof strategies. Existing approaches for handling failed attempts typically either discard the entire proof and regenerate it from scratch or iteratively fix errors within the proof. The former is inefficient, as it may abandon mostly correct reasoning due to localized errors, while the latter, although preserving prior progress, leads to progressively longer contexts which progressively degrades the model's ability to attend to the remaining unresolved subproblems. To address this dilemma, we propose Mechanic, a novel agent system that employs a sorry-driven formal decomposition strategy. By leveraging the sorry placeholder in Lean to precisely isolate unresolved subgoals while preserving the surrounding verified proof structure, Mechanic extracts each failed subproblem into a clean, self-contained context and resolves it independently. This avoids both the waste of full regeneration and the excessive context length induced by repeated repairs. Experimental results on challenging mathematical competition benchmarks, including IMO 2025 and Putnam 2025, demonstrate that our agent achieves significant advantages in proving efficiency. --- ### OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning Authors: Kaihang Pan, Qi Tian, Jianwei Zhang, Weijie Kong, Jiangfeng Xiong, Yanxin Long, Shixue Zhang, Haiyi Qiu, Tan Wang, Zheqi Lv, Shuyuan Tu, Yue Wu et al. Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24458v3 While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, the academic research community lags far behind: most of its models remain heavily fragmented, and the few existing efforts toward unified video generation still struggle to seamlessly integrate diverse tasks within a single framework. To bridge this gap, we propose OmniWeaving, an omni-level video generation model featuring powerful multimodal composition and reasoning-informed capabilities. By leveraging a massive-scale pretraining dataset that encompasses diverse compositional and reasoning-augmented scenarios, OmniWeaving learns to temporally bind interleaved text, multi-image, and video inputs while acting as an intelligent agent to infer complex user intentions for sophisticated video creation. Furthermore, we introduce IntelligentVBench, the first comprehensive benchmark designed to rigorously assess next-level intelligent unified video generation. Extensive experiments demonstrate that OmniWeaving achieves SoTA performance among open-source academic unified models. The code and model are publicly available. Project Page: https://omniweaving.github.io. --- ### OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning Authors: Kaihang Pan, Qi Tian, Jianwei Zhang, Weijie Kong, Jiangfeng Xiong, Yanxin Long, Shixue Zhang, Haiyi Qiu, Tan Wang, Zheqi Lv, Yue Wu, Liefeng Bo et al. Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24458v2 While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fragmented, and the few existing efforts toward unified video generation still struggle to seamlessly integrate diverse tasks within a single framework. To bridge this gap, we propose OmniWeaving, an omni-level video generation model featuring powerful multimodal composition and reasoning-informed capabilities. By leveraging a massive-scale pretraining dataset that encompasses diverse compositional and reasoning-augmented scenarios, OmniWeaving learns to temporally bind interleaved text, multi-image, and video inputs while acting as an intelligent agent to infer complex user intentions for sophisticated video creation. Furthermore, we introduce IntelligentVBench, the first comprehensive benchmark designed to rigorously assess next-level intelligent unified video generation. Extensive experiments demonstrate that OmniWeaving achieves SoTA performance among open-source unified models. The codes and model have already been publicly available. Project Page: https://omniweaving.github.io. --- ### Unleashing Vision-Language Semantics for Deepfake Video Detection Authors: Jiawen Zhu, Yunqi Miao, Xueyi Zhang, Jiankang Deng, Guansong Pang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24454v1 Recent Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) such as CLIP exhibit strong generalization capabilities in detecting artifacts across different identities. However, existing approaches focus on leveraging visual features only, overlooking their most distinctive strength -- the rich vision-language semantics embedded in the latent space. We propose VLAForge, a novel DFD framework that unleashes the potential of such cross-modal semantics to enhance model's discriminability in deepfake detection. This work i) enhances the visual perception of VLM through a ForgePerceiver, which acts as an independent learner to capture diverse, subtle forgery cues both granularly and holistically, while preserving the pretrained Vision-Language Alignment (VLA) knowledge, and ii) provides a complementary discriminative cue -- Identity-Aware VLA score, derived by coupling cross-modal semantics with the forgery cues learned by ForgePerceiver. Notably, the VLA score is augmented by an identity prior-informed text prompting to capture authenticity cues tailored to each identity, thereby enabling more discriminative cross-modal semantics. Comprehensive experiments on video DFD benchmarks, including classical face-swapping forgeries and recent full-face generation forgeries, demonstrate that our VLAForge substantially outperforms state-of-the-art methods at both frame and video levels. Code is available at https://github.com/mala-lab/VLAForge. --- ### Integrating Causal Machine Learning into Clinical Decision Support Systems: Insights from Literature and Practice Authors: Domenique Zipperling, Lukas Schmidt, Benedikt Hahn, Niklas Kühl, Steven Kimbrough Published: 2026-03-25 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.24448v2 Current clinical decision support systems (CDSSs) typically base their predictions on correlation, not causation. In recent years, causal machine learning (ML) has emerged as a promising way to improve decision-making with CDSSs by offering interpretable, treatment-specific reasoning. However, existing research often emphasizes model development rather than designing clinician-facing interfaces. To address this gap, we investigated how CDSSs based on causal ML should be designed to effectively support collaborative clinical decision-making. Using a design science research methodology, we conducted a structured literature review and interviewed experienced physicians. From these, we derived eight empirically grounded design requirements, developed seven design principles, and proposed nine practical design features. Our results establish guidance for designing CDSSs that deliver causal insights, integrate seamlessly into clinical workflows, and support trust, usability, and human-AI collaboration. We also reveal tensions around automation, responsibility, and regulation, highlighting the need for an adaptive certification process for ML-based medical products. --- ### CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents Authors: Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin, Aarash Feizi, Kaixin Li, Patrice Bechard, Spandana Gella, Sai Rajeswar Published: 2026-03-25 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.24440v1 Computer-use agents (CUAs) hold great promise for automating complex desktop workflows, yet progress toward general-purpose agents is bottlenecked by the scarcity of continuous, high-quality human demonstration videos. Recent work emphasizes that continuous video, not sparse screenshots, is the critical missing ingredient for scaling these agents. However, the largest existing open dataset, ScaleCUA, contains only 2 million screenshots, equating to less than 20 hours of video. To address this bottleneck, we introduce CUA-Suite, a large-scale ecosystem of expert video demonstrations and dense annotations for professional desktop computer-use agents. At its core is VideoCUA, which provides approximately 10,000 human-demonstrated tasks across 87 diverse applications with continuous 30 fps screen recordings, kinematic cursor traces, and multi-layerfed reasoning annotations, totaling approximately 55 hours and 6 million frames of expert video. Unlike sparse datasets that capture only final click coordinates, these continuous video streams preserve the full temporal dynamics of human interaction, forming a superset of information that can be losslessly transformed into the formats required by existing agent frameworks. CUA-Suite further provides two complementary resources: UI-Vision, a rigorous benchmark for evaluating grounding and planning capabilities in CUAs, and GroundCUA, a large-scale grounding dataset with 56K annotated screenshots and over 3.6 million UI element annotations. Preliminary evaluation reveals that current foundation action models struggle substantially with professional desktop applications (~60% task failure rate). Beyond evaluation, CUA-Suite's rich multimodal corpus supports emerging research directions including generalist screen parsing, continuous spatial control, video-based reward modeling, and visual world models. All data and models are publicly released. --- ### Enes Causal Discovery Authors: Alexis Kafantaris Published: 2026-03-25 Categories: cs.NE, cs.AI, cs.LG, cs.SC arXiv: https://arxiv.org/abs/2603.24436v3 Enes The proposed architecture is a mixture of experts, which allows for the model entities, such as the causal relationships, to be further parameterized. More specifically, an attempt is made to exploit a neural net as implementing neurons poses a great challenge for this dataset. To explain, a simple and fast Pearson coefficient linear model usually achieves good scores. An aggressive baseline that requires a really good model to overcome that is. Moreover, there are major limitations when it comes to causal discovery of observational data. Unlike the sachs one did not use interventions but only prior knowledge; the most prohibiting limitation is that of the data which is addressed. Thereafter, the method and the model are described and after that the results are presented. --- ### The Gait Signature of Frailty: Transfer Learning based Deep Gait Models for Scalable Frailty Assessment Authors: Laura McDaniel, Basudha Pal, Crystal Szczesny, Yuxiang Guo, Zhaoyang Wang, Ryan Roemmich, Peter Abadir, Rama Chellappa Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24434v2 Frailty is a condition in aging medicine characterized by diminished physiological reserve and increased vulnerability to stressors. However, frailty assessment remains subjective, heterogeneous, and difficult to scale in clinical practice. Gait is a sensitive marker of biological aging, capturing multisystem decline before overt disability. Yet the application of modern computer vision to gait-based frailty assessment has been limited by small, imbalanced datasets and a lack of clinically representative benchmarks. In this work, we introduce a publicly available silhouette-based frailty gait dataset collected in a clinically realistic setting, spanning the full frailty spectrum and including older adults who use walking aids. Using this dataset, we evaluate how pretrained gait recognition models can be adapted for frailty classification under limited data conditions. We study both convolutional and hybrid attention-based architectures and show that predictive performance depends primarily on how pretrained representations are transferred rather than architectural complexity alone. Across models, selectively freezing low-level gait representations while allowing higher-level features to adapt yields more stable and generalizable performance than either full fine-tuning or rigid freezing. Conservative handling of class imbalance further improves training stability, and combining complementary learning objectives enhances discrimination between clinically adjacent frailty states. Interpretability analyses reveal consistent model attention to lower-limb and pelvic regions, aligning with established biomechanical correlates of frailty. Together, these findings establish gait-based representation learning as a scalable, non-invasive, and interpretable framework for frailty assessment and support the integration of modern biometric modeling approaches into aging research and clinical practice. --- ### What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification Authors: Massa Baali, Sarthak Bisht, Rita Singh, Bhiksha Raj Published: 2026-03-25 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2603.24432v1 Speaker verification at large scale remains an open challenge as fixed-margin losses treat all samples equally regardless of quality. We hypothesize that mislabeled or degraded samples introduce noisy gradients that disrupt compact speaker manifolds. We propose Curry (CURriculum Ranking), an adaptive loss that estimates sample difficulty online via Sub-center ArcFace: confidence scores from dominant sub-center cosine similarity rank samples into easy, medium, and hard tiers using running batch statistics, without auxiliary annotations. Learnable weights guide the model from stable identity foundations through manifold refinement to boundary sharpening. To our knowledge, this is the largest-scale speaker verification system trained to date. Evaluated on VoxCeleb1-O, and SITW, Curry reduces EER by 86.8\% and 60.0\% over the Sub-center ArcFace baseline, establishing a new paradigm for robust speaker verification on imperfect large-scale data. --- ### Learning Response-Statistic Shifts and Parametric Roll Episodes from Wave--Vessel Time Series via LSTM Functional Models Authors: Jose del Aguila Ferrandis Published: 2026-03-25 Categories: cs.LG, physics.comp-ph, physics.data-an, physics.flu-dyn arXiv: https://arxiv.org/abs/2603.24431v1 Parametric roll is a rare but high-consequence instability that can trigger abrupt regime changes in ship response, including pronounced shifts in roll statistics and tail risk. This paper develops a data-driven surrogate that learns the nonlinear, causal functional mapping from incident wave--motion time series to vessel motions, and demonstrates that the surrogate reproduces both (i) parametric roll episodes and (ii) the associated statistical shifts in the response. Crucially, the learning framework is data-source agnostic: the paired wave--motion time series can be obtained from controlled experiments (e.g., towing-tank or basin tests with wave probes and motion tracking) when a hull exists, or from high-fidelity simulations during design when experiments are not yet available. To provide a controlled severe-sea demonstration, we generate training data with a URANS numerical wave tank, using long-crested irregular seas synthesized from a modified Pierson--Moskowitz spectrum. The demonstration dataset comprises 49 random-phase realizations for each of three sea states, simulated at a fixed forward speed selected to yield encounter conditions under which parametric-roll episodes can occur. A stacked LSTM surrogate is trained on wave-elevation time series and evaluated on held-out realizations using time-domain accuracy and distributional fidelity metrics. In the most severe case, the model tracks the onset and growth of large-amplitude roll consistent with parametric excitation, and captures the corresponding changes in roll probability density functions (PDFs). We further compare loss-function choices (MSE, relative-entropy-based objectives, and amplitude-weighted variants) and show how they trade average error for improved tail fidelity relevant to operability and risk assessment. --- ### Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching Authors: Arsen Kuzhamuratov, Mikhail Zhirnov, Andrey Kuznetsov, Ivan Oseledets, Konstantin Sobolev Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.24428v1 Accurate subseasonal weather forecasting remains a major challenge due to the inherently chaotic nature of the atmosphere, which limits the predictive skill of conventional models beyond the mid-range horizon (approximately 15 days). In this work, we present \textit{Marchuk}, a generative latent flow-matching model for global weather forecasting spanning mid-range to subseasonal timescales, with prediction horizons of up to 30 days. Marchuk conditions on current-day weather maps and autoregressively predicts subsequent days' weather maps within the learned latent space. We replace rotary positional encodings (RoPE) with trainable positional embeddings and extend the temporal context window, which together enhance the model's ability to represent and propagate long-range temporal dependencies during latent forecasting. Marchuk offers two key advantages: high computational efficiency and strong predictive performance. Despite its compact architecture of only 276 million parameters, the model achieves performance comparable to LaDCast, a substantially larger model with 1.6 billion parameters, while operating at significantly higher inference speeds. We open-source our inference code and model at: https://v-gen-ai.github.io/Marchuk/ --- ### Continuous-Time Learning of Probability Distributions: A Case Study in a Digital Trial of Young Children with Type 1 Diabetes Authors: Antonio Álvarez-López, Marcos Matabuena Published: 2026-03-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.24427v1 Understanding how biomarker distributions evolve over time is a central challenge in digital health and chronic disease monitoring. In diabetes, changes in the distribution of glucose measurements can reveal patterns of disease progression and treatment response that conventional summary measures miss. Motivated by a 26-week clinical trial comparing the closed-loop insulin delivery system t:slim X2 with standard therapy in children with type 1 diabetes, we propose a probabilistic framework to model the continuous-time evolution of time-indexed distributions using continuous glucose monitoring data (CGM) collected every five minutes. We represent the glucose distribution as a Gaussian mixture, with time-varying mixture weights governed by a neural ODE. We estimate the model parameter using a distribution-matching criterion based on the maximum mean discrepancy. The resulting framework is interpretable, computationally efficient, and sensitive to subtle temporal distributional changes. Applied to CGM trial data, the method detects treatment-related improvements in glucose dynamics that are difficult to capture with traditional analytical approaches. --- ### OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework Authors: Ben Chen, Siyuan Wang, Yufei Ma, Zihan Liang, Xuxin Zhang, Yue Lv, Ying Yang, Huangyu Dai, Lingtao Mao, Tong Zhao, Zhipeng Qian, Xinyu Sun et al. Published: 2026-03-25 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.24422v2 Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it offers advantages such as end-to-end joint optimization and high computational efficiency. OneSearch, as a representative industrial-scale deployed generative search framework, has brought significant commercial and operational benefits. However, its inadequate understanding of complex queries, inefficient exploitation of latent user intents, and overfitting to narrow historical preferences have limited its further performance improvement. To address these challenges, we propose OneSearch-V2, a latent reasoning enhanced self-distillation generative search framework. It contains three key innovations: (1) a thought-augmented complex query understanding module, which enables deep query understanding and overcomes the shallow semantic matching limitations of direct inference; (2) a reasoning-internalized self-distillation training pipeline, which uncovers users' potential yet precise e-commerce intentions beyond log-fitting through implicit in-context learning; (3) a behavior preference alignment optimization system, which mitigates reward hacking arising from the single conversion metric, and addresses personal preference via direct user feedback. Extensive offline evaluations demonstrate OneSearch-V2's strong query recognition and user profiling capabilities. Online A/B tests further validate its business effectiveness, yielding +3.98\% item CTR, +2.07\% buyer volume, and +2.11\% order volume. Manual evaluation further confirms gains in search experience quality, with +1.37\% in page good rate and +1.65\% in query-item relevance. More importantly, OneSearch-V2 effectively mitigates common search system issues such as information bubbles and long-tail sparsity, without incurring additional inference costs or serving latency. --- ### ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers Authors: Songyang Liu, Chaozhuo Li, Chenxu Wang, Jinyu Hou, Zejian Chen, Litian Zhang, Zheng Liu, Qiwei Ye, Yiming Hei, Xi Zhang, Zhongyuan Wang Published: 2026-03-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.24414v1 OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file access, and shell command execution. However, these broad operational privileges introduce critical security vulnerabilities, transforming model errors into tangible system-level threats such as sensitive data leakage, privilege escalation, and malicious third-party skill execution. Existing security measures for the OpenClaw ecosystem remain highly fragmented, addressing only isolated stages of the agent lifecycle rather than providing holistic protection. To bridge this gap, we present ClawKeeper, a real-time security framework that integrates multi-dimensional protection mechanisms across three complementary architectural layers. (1) \textbf{Skill-based protection} operates at the instruction level, injecting structured security policies directly into the agent context to enforce environment-specific constraints and cross-platform boundaries. (2) \textbf{Plugin-based protection} serves as an internal runtime enforcer, providing configuration hardening, proactive threat detection, and continuous behavioral monitoring throughout the execution pipeline. (3) \textbf{Watcher-based protection} introduces a novel, decoupled system-level security middleware that continuously verifies agent state evolution. It enables real-time execution intervention without coupling to the agent's internal logic, supporting operations such as halting high-risk actions or enforcing human confirmation. We argue that this Watcher paradigm holds strong potential to serve as a foundational building block for securing next-generation autonomous agent systems. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and robustness of ClawKeeper across diverse threat scenarios. We release our code. --- ### Pingala: Prosody-Aware Decoding for Sanskrit Poetry Generation Authors: Manoj Balaji Jagadeeshan, Atul Singh, Nallani Chakravartula Sahith, Amrith Krishna, Pawan Goyal Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.24413v2 Poetry generation in Sanskrit typically requires the verse to be semantically coherent and adhere to strict prosodic rules. In Sanskrit prosody, every line of a verse is typically a fixed length sequence of syllables adhering to prescribed binary patterns of syllable weights. We observe that instead of treating a verse as a monolithic sequence, segmenting them as grouped-lines leads to significant improvement in semantic coherence by 10\% with comparable metrical adherence. Specifically, Pingala, our proposed decoding approach is designed to encourage every line to have well-formed words and our token selection biases the model towards it by preferring longer tokens. Writing in Sanskrit follows phonemic orthography, hence using a phonetically aware transliteration scheme, SLP1, increased the metrical alignment by 46\% with comparable semantic similarity, for a instruction fine-tuned large language models like Phi-4. We also introduce a new approach for reference-free evaluation using cross-encoders which achieved better alignment with true poetry instances. --- ### Real Talk, Virtual Faces: Symbolic-Semantic Discourse Geometry of Virtual and Human Influencer Audiences Authors: Shahram Chaudhry, Sidahmed Benabderrahmane, Talal Rahwan Published: 2026-03-25 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.24410v2 Virtual influencers~(VIs) -- digitally constructed social-media personas -- are becoming increasingly visible in online culture, marketing, and identity formation. Yet it remains unclear whether audiences respond to them through the same discourse patterns used for human influencers~(HIs), or whether virtuality produces distinctive modes of reaction. Existing studies often rely on surveys, engagement statistics, or marginal sentiment distributions, which reveal what audiences say but not how affective, topical, and psycholinguistic signals are jointly organised. We introduce a symbolic-semantic framework for analysing audience discourse around virtual and human influencers. The symbolic layer uses Formal Concept Analysis and association rule mining to extract closed co-occurrence structures from sentiment labels, topic tags, and Big Five psycholinguistic cues. The semantic layer renders these formal concepts as natural-language descriptions, embeds them with MiniLM, and compares their geometry across VI and HI audiences. Applied to 69,498 YouTube comments from three matched VI-HI influencer pairs, our analysis shows that HI discourse is organised around a compact, stability-centred pattern in which low neuroticism anchors positive sentiment, whereas VI discourse supports multiple discourse regimes. VI concepts are also more semantically dispersed than HI concepts, while both groups show strong symbolic-semantic alignment between closed-set structure and embedding geometry. Finally, VI discourse contains a distinct artificial-identity region and a higher concentration of negative sentiment in sensitive topics such as mental health, body image, and artificial identity. These findings suggest that virtuality reshapes not only the sentiment of audience reactions, but also the symbolic and semantic organisation of online social discourse. --- ### Teacher-Student Diffusion Model for Text-Driven 3D Hand Motion Generation Authors: Ching-Lam Cheng, Bin Zhu, Shengfeng He Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24407v1 Generating realistic 3D hand motion from natural language is vital for VR, robotics, and human-computer interaction. Existing methods either focus on full-body motion, overlooking detailed hand gestures, or require explicit 3D object meshes, limiting generality. We propose TSHaMo, a model-agnostic teacher-student diffusion framework for text-driven hand motion generation. The student model learns to synthesize motions from text alone, while the teacher leverages auxiliary signals (e.g., MANO parameters) to provide structured guidance during training. A co-training strategy enables the student to benefit from the teacher's intermediate predictions while remaining text-only at inference. Evaluated using two diffusion backbones on GRAB and H2O, TSHaMo consistently improves motion quality and diversity. Ablations confirm its robustness and flexibility in using diverse auxiliary inputs without requiring 3D objects at test time. ---