# Research Papers — 2026-03 · bundle page 219 of 243 > Full-text markdown of papers #10901–10950 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/219 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/218.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/220.md) ### Polyp Segmentation Using Wavelet-Based Cross-Band Integration for Enhanced Boundary Representation Authors: Haesung Oh, Jaesung Lee Published: 2026-03-04 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.03682v1 Accurate polyp segmentation is essential for early colorectal cancer detection, yet achieving reliable boundary localization remains challenging due to low mucosal contrast, uneven illumination, and color similarity between polyps and surrounding tissue. Conventional methods relying solely on RGB information often struggle to delineate precise boundaries due to weak contrast and ambiguous structures between polyps and surrounding mucosa. To establish a quantitative foundation for this limitation, we analyzed polyp-background contrast in the wavelet domain, revealing that grayscale representations consistently preserve higher boundary contrast than RGB images across all frequency bands. This finding suggests that boundary cues are more distinctly represented in the grayscale domain than in the color domain. Motivated by this finding, we propose a segmentation model that integrates grayscale and RGB representations through complementary frequency-consistent interaction, enhancing boundary precision while preserving structural coherence. Extensive experiments on four benchmark datasets demonstrate that the proposed approach achieves superior boundary precision and robustness compared to conventional models. --- ### EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs Authors: Yuhao Chen, Bin Shan, Xin Ye, Cheng Chen Published: 2026-03-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03681v1 Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution images and videos. Existing visual token pruning methods mainly operate after visual encoding, overlooking the substantial computational cost incurred during the encoding stage. To address this issue, we propose EvoPrune, an early-stage visual token pruning method for MLLMs that performs pruning directly during visual encoding. Specifically, EvoPrune employs a layer-wise pruning strategy guided by token similarity, diversity, and attention-based importance to retain the most informative visual tokens at selected encoding layers. Extensive experiments on image and video benchmarks validate the effectiveness of EvoPrune. In particular, on the VideoMME dataset, EvoPrune achieves 2$\times$ inference speedup with less than 1% performance degradation, demonstrating its potential for latency-sensitive MLLM deployment. --- ### MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation Authors: Lu Yang, Zelai Xu, Minyang Xie, Jiaxuan Gao, Zhao Shok, Yu Wang, Yi Wu Published: 2026-03-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03680v1 Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some flexibility, they fail to internalize the adaptive ability required for long-term improvement. Meta-Reinforcement Learning (meta-RL) provides an alternative by embedding the learning process directly within the model. However, existing meta-RL approaches for LLMs focus primarily on exploration in single-agent settings, neglecting the strategic exploitation necessary for multi-agent environments. We propose MAGE, a meta-RL framework that empowers LLM agents for strategic exploration and exploitation. MAGE utilizes a multi-episode training regime where interaction histories and reflections are integrated into the context window. By using the final episode reward as the objective, MAGE incentivizes the agent to refine its strategy based on past experiences. We further combine population-based training with an agent-specific advantage normalization technique to enrich agent diversity and ensure stable learning. Experiment results show that MAGE outperforms existing baselines in both exploration and exploitation tasks. Furthermore, MAGE exhibits strong generalization to unseen opponents, suggesting it has internalized the ability for strategic exploration and exploitation. Code is available at https://github.com/Lu-Yang666/MAGE. --- ### MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation Authors: Guoyi Li, Shihao Xu, Jiatong Ma, Zhongjiang Yao, Yunyun Han, Jianhua Chen, Yafeng Deng Published: 2026-03-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03677v2 Psychiatric consultation requires agents to elicit discriminative evidence, map uncertain narratives to diagnostic criteria, and decide when evidence suffices. Existing dialogue and retrieval-augmented systems condition policies on raw histories or appended passages, leaving observed evidence, missing checks, differentials, and support reliability entangled. We introduce MIND, a criteria-grounded evidence-state decision interface. At each turn, MIND constructs a typed state containing observed evidence, unresolved criterion checks, active differentials, criterion-linked supports, and reliability metadata. A training-split Psychiatric Reasoning Bank supplies gated supports, turning retrieval into state construction rather than prompt injection. The same state conditions action selection, process rewards, information-gain scoring, and trajectory rectification. Under EMR-grounded simulator protocols, MIND improves accuracy by 8.8 and 7.3 points over strong inference-only, RAG, and RL baselines, with gains transferring to public MDD-5k dialogues. Matched interventions attribute these gains to the shared state rather than prompt length, retrieval text, or formatting. MIND targets screening-level decision support, not autonomous diagnosis. Code is available at https://github.com/Lingxi-mental-health/MIND.Å --- ### MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation Authors: Guoyi Li, Shihao Xu, Jiatong Ma, Yunyun Han, Jianhua Chen, Yafeng Deng Published: 2026-03-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03677v1 Large language models (LLMs) have advanced medical dialogue systems, yet psychiatric consultation poses substantially higher demands due to subjective ambiguity and comorbidity complexity: an agent must continuously extract psychopathological cues from incomplete and inconsistent patient reports in multi-turn interactions and perform rigorous differential diagnostic reasoning. However, existing methods face two fundamental challenges. First, without criteria-grounded clinical supports, they are prone to unsupported clinical assertions when symptoms are atypical or underspecified. Second, in multi-turn interactions, they struggle to mitigate inquiry drift (off-topic or low-yield questioning) and optimize questioning strategies. To address these challenges, we propose MIND, a unified inquiry--diagnosis reinforcement learning framework for psychiatric consultation. Specifically, we build a Criteria-Grounded Psychiatric Reasoning Bank (PRB) that summarizes dialogue context into clinical retrieval states, retrieves semantically similar reference consultations, and distills reusable criteria-grounded clinical supports to guide criteria-aligned inquiry and reasoning. Building on this foundation, MIND enforces explicit clinical reasoning with rubric-based process rewards to provide fine-grained supervision over intermediate decision steps, and incorporates a value-aware trajectory rectification mechanism to jointly improve information acquisition and diagnostic decision-making across turns. Extensive experiments demonstrate that MIND consistently outperforms strong baselines in diagnostic accuracy, empathetic interaction quality, interpretability, and generalization. --- ### A Stein Identity for q-Gaussians with Bounded Support Authors: Sophia Sklaviadis, Thomas Moellenhoff, Andre F. T. Martins, Mario A. T. Figueiredo, Mohammad Emtiyaz Khan Published: 2026-03-04 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.03673v1 Stein's identity is a fundamental tool in machine learning with applications in generative models, stochastic optimization, and other problems involving gradients of expectations under Gaussian distributions. Less attention has been paid to problems with non-Gaussian expectations. Here, we consider the class of bounded-support $q$-Gaussians and derive a new Stein identity leading to gradient estimators which have nearly identical forms to the Gaussian ones, and which are similarly easy to implement. We do this by extending the previous results of Landsman, Vanduffel, and Yao (2013) to prove new Bonnet- and Price-type theorems for q-Gaussians. We also simplify their forms by using escort distributions. Our experiments show that bounded-support distributions can reduce the variance of gradient estimators, which can potentially be useful for Bayesian deep learning and sharpness-aware minimization. Overall, our work simplifies the application of Stein's identity for an important class of non-Gaussian distributions. --- ### Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation Authors: Xuan Yang, Hsi-Wen Chen, Ming-Syan Chen, Jian Pei Published: 2026-03-04 Categories: cs.LG, cs.AI, cs.DB, cs.GT arXiv: https://arxiv.org/abs/2603.03672v2 The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Existing accelerations remain global and ignore a structural property of modern predictors: for a given test instance, only a small subset of training points influences the prediction. We formalize this model-induced locality through support sets defined by the model's computational pathway (e.g., neighbors in KNN, leaves in trees, receptive fields in GNNs), showing that Shapley computation can be projected onto these supports without loss when locality is exact. This reframes Shapley evaluation as a structured data processing problem over overlapping support-induced subset families rather than exhaustive coalition enumeration. We prove that the intrinsic complexity of Local Shapley is governed by the number of distinct influential subsets, establishing an information-theoretic lower bound on retraining operations. Guided by this result, we propose LSMR (Local Shapley via Model Reuse), an optimal subset-centric algorithm that trains each influential subset exactly once via support mapping and pivot scheduling. For larger supports, we develop LSMR-A, a reuse-aware Monte Carlo estimator that remains unbiased with exponential concentration, with runtime determined by the number of distinct sampled subsets rather than total draws. Experiments across multiple model families demonstrate substantial retraining reductions and speedups while preserving high valuation fidelity. --- ### Can LLM Aid in Solving Constraints with Inductive Definitions? Authors: Weizhi Feng, Shidong Shen, Jiaxiang Liu, Taolue Chen, Fu Song, Zhilin Wu Published: 2026-03-04 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2603.03668v2 Solving constraints involving inductive (aka recursive) definitions is challenging. State-of-the-art SMT/CHC solvers and first-order logic provers provide only limited support for solving such constraints, especially when they involve, e.g., abstract data types. In this work, we leverage structured prompts to elicit Large Language Models (LLMs) to generate auxiliary lemmas that are necessary for reasoning about these inductive definitions. We further propose a neuro-symbolic approach, which synergistically integrates LLMs with constraint solvers: the LLM iteratively generates conjectures, while the solver checks their validity and usefulness for proving the goal. We evaluate our approach on a diverse benchmark suite comprising constraints originating from algebrai data types and recurrence relations. The experimental results show that our approach can improve the state-of-the-art SMT and CHC solvers, solving considerably more (around 25%) proof tasks involving inductive definitions, demonstrating its efficacy. --- ### Machine Pareidolia: Protecting Facial Image with Emotional Editing Authors: Binh M. Le, Simon S. Woo Published: 2026-03-04 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.03665v1 The proliferation of facial recognition (FR) systems has raised privacy concerns in the digital realm, as malicious uses of FR models pose a significant threat. Traditional countermeasures, such as makeup style transfer, have suffered from low transferability in black-box settings and limited applicability across various demographic groups, including males and individuals with darker skin tones. To address these challenges, we introduce a novel facial privacy protection method, dubbed \textbf{MAP}, a pioneering approach that employs human emotion modifications to disguise original identities as target identities in facial images. Our method uniquely fine-tunes a score network to learn dual objectives, target identity and human expression, which are jointly optimized through gradient projection to ensure convergence at a shared local optimum. Additionally, we enhance the perceptual quality of protected images by applying local smoothness regularization and optimizing the score matching loss within our network. Empirical experiments demonstrate that our innovative approach surpasses previous baselines, including noise-based, makeup-based, and freeform attribute methods, in both qualitative fidelity and quantitative metrics. Furthermore, MAP proves its effectiveness against an online FR API and shows advanced adaptability in uncommon photographic scenarios. --- ### Principled Learning-to-Communicate with Quasi-Classical Information Structures Authors: Xiangyu Liu, Haoyi You, Kaiqing Zhang Published: 2026-03-04 Categories: eess.SY, cs.LG, cs.MA, math.OC arXiv: https://arxiv.org/abs/2603.03664v2 Learning-to-communicate (LTC) in partially observable environments has received increasing attention in deep multi-agent reinforcement learning, where the control and communication strategies are jointly learned. Meanwhile, the impact of communication on decision-making has been extensively studied in control theory. In this paper, we seek to formalize and better understand LTC by bridging these two lines of work, through the lens of information structures (ISs). To this end, we formalize LTC in decentralized partially observable Markov decision processes (Dec-POMDPs) under the common-information-based framework from decentralized stochastic control, and classify LTC problems based on the ISs before (additional) information sharing. We first show that non-classical LTCs are computationally intractable in general, and thus focus on quasi-classical (QC) LTCs. We then propose a series of conditions for QC LTCs, under which LTC preserves the QC IS after information sharing, whereas violating them can cause computational hardness in general. Further, we develop provable planning and learning algorithms for QC LTCs, and establish quasi-polynomial time and sample complexities for several QC LTC examples that satisfy the above conditions. Along the way, we also establish new results on a relationship between (strictly) QC IS and the condition of having strategy-independent common-information-based beliefs (SI-CIBs), as well as on solving Dec-POMDPs without computationally intractable oracles but beyond those with SI-CIBs, which may be of independent interest. --- ### Graph Negative Feedback Bias Correction Framework for Adaptive Heterophily Modeling Authors: Jiaqi Lv, Qingfeng Du, Yu Zhang, Yongqi Han, Sheng Li Published: 2026-03-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03662v1 Graph Neural Networks (GNNs) have emerged as a powerful framework for processing graph-structured data. However, conventional GNNs and their variants are inherently limited by the homophily assumption, leading to degradation in performance on heterophilic graphs. Although substantial efforts have been made to mitigate this issue, they remain constrained by the message-passing paradigm, which is inherently rooted in homophily. In this paper, a detailed analysis of how the underlying label autocorrelation of the homophily assumption introduces bias into GNNs is presented. We innovatively leverage a negative feedback mechanism to correct the bias and propose Graph Negative Feedback Bias Correction (GNFBC), a simple yet effective framework that is independent of any specific aggregation strategy. Specifically, we introduce a negative feedback loss that penalizes the sensitivity of predictions to label autocorrelation. Furthermore, we incorporate the output of graph-agnostic models as a feedback term, leveraging independent node feature information to counteract correlation-induced bias guided by Dirichlet energy. GNFBC can be seamlessly integrated into existing GNN architectures, improving overall performance with comparable computational and memory overhead. --- ### InEdit-Bench: Benchmarking Intermediate Logical Pathways for Intelligent Image Editing Models Authors: Zhiqiang Sheng, Xumeng Han, Zhiwei Zhang, Zenghui Xiong, Yifan Ding, Aoxiang Ping, Xiang Li, Tong Guo, Yao Mao Published: 2026-03-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03657v1 Multimodal generative models have made significant strides in image editing, demonstrating impressive performance on a variety of static tasks. However, their proficiency typically does not extend to complex scenarios requiring dynamic reasoning, leaving them ill-equipped to model the coherent, intermediate logical pathways that constitute a multi-step evolution from an initial state to a final one. This capacity is crucial for unlocking a deeper level of procedural and causal understanding in visual manipulation. To systematically measure this critical limitation, we introduce InEdit-Bench, the first evaluation benchmark dedicated to reasoning over intermediate pathways in image editing. InEdit-Bench comprises meticulously annotated test cases covering four fundamental task categories: state transition, dynamic process, temporal sequence, and scientific simulation. Additionally, to enable fine-grained evaluation, we propose a set of assessment criteria to evaluate the logical coherence and visual naturalness of the generated pathways, as well as the model's fidelity to specified path constraints. Our comprehensive evaluation of 14 representative image editing models on InEdit-Bench reveals significant and widespread shortcomings in this domain. By providing a standardized and challenging benchmark, we aim for InEdit-Bench to catalyze research and steer development towards more dynamic, reason-aware, and intelligent multimodal generative models. --- ### Mozi: Governed Autonomy for Drug Discovery LLM Agents Authors: He Cao, Siyu Liu, Fan Zhang, Zijing Liu, Hao Li, Bin Feng, Shengyuan Bai, Leqing Chen, Kai Xie, Yu Li Published: 2026-03-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03655v1 Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlenecked by two critical barriers: unconstrained tool-use governance and poor long-horizon reliability. In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories, where early-stage hallucinations multiplicatively compound into downstream failures. To overcome this, we present Mozi, a dual-layer architecture that bridges the flexibility of generative AI with the deterministic rigor of computational biology. Layer A (Control Plane) establishes a governed supervisor--worker hierarchy that enforces role-based tool isolation, limits execution to constrained action spaces, and drives reflection-based replanning. Layer B (Workflow Plane) operationalizes canonical drug discovery stages -- from Target Identification to Lead Optimization -- as stateful, composable skill graphs. This layer integrates strict data contracts and strategic human-in-the-loop (HITL) checkpoints to safeguard scientific validity at high-uncertainty decision boundaries. Operating on the design principle of ``free-form reasoning for safe tasks, structured execution for long-horizon pipelines,'' Mozi provides built-in robustness mechanisms and trace-level audibility to completely mitigate error accumulation. We evaluate Mozi on PharmaBench, a curated benchmark for biomedical agents, demonstrating superior orchestration accuracy over existing baselines. Furthermore, through end-to-end therapeutic case studies, we demonstrate Mozi's ability to navigate massive chemical spaces, enforce stringent toxicity filters, and generate highly competitive in silico candidates, effectively transforming the LLM from a fragile conversationalist into a reliable, governed co-scientist. --- ### Field imaging framework for morphological characterization of aggregates with computer vision: Algorithms and applications Authors: Haohang Huang Published: 2026-03-04 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2603.03654v1 Construction aggregates, including sand and gravel, crushed stone and riprap, are the core building blocks of the construction industry. State-of-the-practice characterization methods mainly relies on visual inspection and manual measurement. State-of-the-art aggregate imaging methods have limitations that are only applicable to regular-sized aggregates under well-controlled conditions. This dissertation addresses these major challenges by developing a field imaging framework for the morphological characterization of aggregates as a multi-scenario solution. For individual and non-overlapping aggregates, a field imaging system was designed and the associated segmentation and volume estimation algorithms were developed. For 2D image analyses of aggregates in stockpiles, an automated 2D instance segmentation and morphological analysis approach was established. For 3D point cloud analyses of aggregate stockpiles, an integrated 3D Reconstruction-Segmentation-Completion (RSC-3D) approach was established: 3D reconstruction procedures from multi-view images, 3D stockpile instance segmentation, and 3D shape completion to predict the unseen sides. First, a 3D reconstruction procedure was developed to obtain high-fidelity 3D models of collected aggregate samples, based on which a 3D aggregate particle library was constructed. Next, two datasets were derived from the 3D particle library for 3D learning: a synthetic dataset of aggregate stockpiles with ground-truth instance labels, and a dataset of partial-complete shape pairs, developed with varying-view raycasting schemes. A state-of-the-art 3D instance segmentation network and a 3D shape completion network were trained on the datasets, respectively. The application of the integrated approach was demonstrated on real stockpiles and validated with ground-truth, showing good performance in capturing and predicting the unseen sides of aggregates. --- ### Linguistically Informed Graph Model and Semantic Contrastive Learning for Korean Short Text Classification Authors: JaeGeon Yoo, Byoungwook Kim, Yeongwook Yang, Hong-Jun Jang Published: 2026-03-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03652v1 Short text classification (STC) remains a challenging task due to the scarcity of contextual information and labeled data. However, existing approaches have pre-dominantly focused on English because most benchmark datasets for the STC are primarily available in English. Consequently, existing methods seldom incorporate the linguistic and structural characteristics of Korean, such as its agglutinative morphology and flexible word order. To address these limitations, we propose LIGRAM, a hierarchical heterogeneous graph model for Korean short-text classification. The proposed model constructs sub-graphs at the morpheme, part-of-speech, and named-entity levels and hierarchically integrates them to compensate for the limited contextual information in short texts while precisely capturing the grammatical and semantic dependencies inherent in Korean. In addition, we apply Semantics-aware Contrastive Learning (SemCon) to reflect semantic similarity across documents, enabling the model to establish clearer decision boundaries even in short texts where class distinctions are often ambiguous. We evaluate LIGRAM on four Korean short-text datasets, where it consistently outperforms existing baseline models. These outcomes validate that integrating language-specific graph representations with SemCon provides an effective solution for short text classification in agglutinative languages such as Korean. --- ### Freezing of Gait Prediction using Proactive Agent that Learns from Selected Experience and DDQN Algorithm Authors: Septian Enggar Sukmana, Sang Won Bae, Tomohiro Shibata Published: 2026-03-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03651v1 Freezing of Gait (FOG) is a debilitating motor symptom commonly experienced by individuals with Parkinson's Disease (PD) which often leads to falls and reduced mobility. Timely and accurate prediction of FOG episodes is essential for enabling proactive interventions through assistive technologies. This study presents a reinforcement learning-based framework designed to identify optimal pre-FOG onset points, thereby extending the prediction horizon for anticipatory cueing systems. The model implements a Double Deep Q-Network (DDQN) architecture enhanced with Prioritized Experience Replay (PER) allowing the agent to focus learning on high-impact experiences and refine its policy. Trained over 9000 episodes with a reward shaping strategy that promotes cautious decision-making, the agent demonstrated robust performance in both subject-dependent and subject-independent evaluations. The model achieved a prediction horizon of up to 8.72 seconds prior to FOG onset in subject-independent scenarios and 7.89 seconds in subject-dependent settings. These results highlight the model's potential for integration into wearable assistive devices, offering timely and personalized interventions to mitigate FOG in PD patients. --- ### Adaptive Sensing of Continuous Physical Systems for Machine Learning Authors: Felix Köster, Atsushi Uchida Published: 2026-03-04 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2603.03650v1 Physical dynamical systems can be viewed as natural information processors: their systems preserve, transform, and disperse input information. This perspective motivates learning not only from data generated by such systems, but also how to measure them in a way that extracts the most useful information for a given task. We propose a general computing framework for adaptive information extraction from dynamical systems, in which a trainable attention module learns both where to probe the system state and how to combine these measurements to optimize prediction performance. As a concrete instantiation, we implement this idea using a spatiotemporal field governed by a partial differential equation as the underlying dynamics, though the framework applies equally to any system whose state can be sampled. Our results show that adaptive spatial sensing significantly improves prediction accuracy on canonical chaotic benchmarks. This work provides a perspective on attention-enhanced reservoir computing as a special case of a broader paradigm: neural networks as trainable measurement devices for extracting information from physical dynamical systems. --- ### Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration Authors: Xiaohui Sun, Hanlin Wu Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03648v2 Face restoration can be formulated as a continuous-time transformation between image distributions via Flow Matching (FM). However, standard FM typically employs independent coupling, ignoring the statistical correlation between low-quality (LQ) and high-quality (HQ) data. This leads to intersecting trajectories and high velocity-field curvature, requiring multi-step integration. We propose Shortcut-constrained Coupling Flow for Face Restoration (SCFlowFR) to address these challenges. By establishing a data-dependent coupling, we explicitly model the LQ-HQ dependency to minimize path crossovers and promote near-linear probability flow. Furthermore, we employ a conditional mean estimator to refine the source distribution's anchor, effectively tightening the transport cost and stabilizing the velocity field. To ensure stable one-step inference, a shortcut constraint is introduced to supervise average velocities over arbitrary intervals, mitigating discretization bias in large-step updates. SCFlowFR achieves state-of-the-art one-step restoration, providing a superior trade-off between perceptual fidelity and computational efficiency. --- ### InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions Authors: Mohamed Elmoghany, Liangbing Zhao, Xiaoqian Shen, Subhojyoti Mukherjee, Yang Zhou, Gang Wu, Viet Dac Lai, Seunghyun Yoon, Ryan Rossi, Abdullah Rashwan, Puneet Mathur, Varun Manjunatha et al. Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03646v1 Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background consistency across shots, seamless multi-subject shot-to-shot transitions, and scalability to hour-long narratives. Our approach introduces a background-consistent generation pipeline that maintains visual coherence across scenes while preserving character identity and spatial relationships. We further propose a transition-aware video synthesis module that generates smooth shot transitions for complex scenarios involving multiple subjects entering or exiting frames, going beyond the single-subject limitations of prior work. To support this, we contribute with a synthetic dataset of 10,000 multi-subject transition sequences covering underrepresented dynamic scene compositions. On VBench, InfinityStory achieves the highest Background Consistency (88.94), highest Subject Consistency (82.11), and the best overall average rank (2.80), showing improved stability, smoother transitions, and better temporal coherence. --- ### Bridging Pedagogy and Play: Introducing a Language Mapping Interface for Human-AI Co-Creation in Educational Game Design Authors: Daijin Yang, Erica Kleinman, Casper Harteveld Published: 2026-03-04 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.03644v1 Educational games can foster critical thinking, problem-solving, and motivation, yet instructors often find it difficult to design games that reliably achieve specific learning outcomes. Existing authoring environments reduce the need for programming expertise, but they do not eliminate the underlying challenges of educational game design, and they can leave non-expert designers reliant on opaque suggestions from AI systems. We designed a controlled natural language framework-based web tool that positions language as the primary interface for LLM-assisted educational game design. In the tool, users and an LLM assistant collaboratively develop a structured language that maps pedagogy to gameplay through four linked components. We argue that, by making pedagogical intent explicit and editable in the interface, the tool has the potential to lower design barriers for non-expert designers, preserves human agency in critical decisions, and enables alignment and reflections between pedagogy and gameplay during and after co-creation. --- ### Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions Authors: Neha Nagaraja, Lan Zhang, Zhilong Wang, Bo Zhang, Pawan Patil Published: 2026-03-04 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2603.03637v1 Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions are embedded into natural images to override model behavior. Our end-to-end IPI pipeline incorporates segmentation-based region selection, adaptive font scaling, and background-aware rendering to conceal prompts from human perception while preserving model interpretability. Using the COCO dataset and GPT-4-turbo, we evaluate 12 adversarial prompt strategies and multiple embedding configurations. The results show that IPI can reliably manipulate the output of the model, with the most effective configuration achieving up to 64\% attack success under stealth constraints. These findings highlight IPI as a practical threat in black-box settings and underscore the need for defenses against multimodal prompt injection. --- ### Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study Authors: Neha Nagaraja, Hayretdin Bahsi Published: 2026-03-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.03633v1 While incorporating LLMs into systems offers significant benefits in critical application areas such as healthcare, new security challenges emerge due to the potential cyber kill chain cycles that combine adversarial model, prompt injection and conventional cyber attacks. Threat modeling methods enable the system designers to identify potential cyber threats and the relevant mitigations during the early stages of development. Although the cyber security community has extensive experience in applying these methods to software-based systems, the elicited threats are usually abstract and vague, limiting their effectiveness for conducting proper likelihood and impact assessments for risk prioritization, especially in complex systems with novel attacks surfaces, such as those involving LLMs. In this study, we propose a structured, goal driven risk assessment approach that contextualizes the threats with detailed attack vectors, preconditions, and attack paths through the use of attack trees. We demonstrate the proposed approach on a case study with an LLM agent-based healthcare system. This study harmonizes the state-of-the-art attacks to LLMs with conventional ones and presents possible attack paths applicable to similar systems. By providing a structured risk assessment, this study makes a significant contribution to the literature and advances the secure-by-design practices in LLM-based systems. --- ### Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme Authors: Zhiyuan Zhan, Masashi Sugiyama Published: 2026-03-04 Categories: stat.ML, cs.LG, math.NA, math.PR arXiv: https://arxiv.org/abs/2603.03626v1 Low-dimensional structure in real-world data plays an important role in the success of generative models, which motivates diffusion models defined on intrinsic data manifolds. Such models are driven by stochastic differential equations (SDEs) on manifolds, which raises the need for convergence theory of numerical schemes for manifold-valued SDEs. In Euclidean space, the Euler--Maruyama (EM) scheme achieves strong convergence with order $1/2$, but an analogous result for manifold discretizations is less understood in general settings. In this work, we study a geometric version of the EM scheme for SDEs on Riemannian manifolds and prove strong convergence with order $1/2$ under geometric and regularity conditions. As an application, we obtain a Wasserstein bound for sampling on manifolds via the geometric EM discretization of Riemannian Langevin dynamics. --- ### A Neural Topic Method Using a Large-Language-Model-in-the-Loop for Business Research Authors: Stephan Ludwig, Peter J. Danaher, Xiaohao Yang Published: 2026-03-04 Categories: cs.CL, econ.EM arXiv: https://arxiv.org/abs/2603.03623v1 The growing use of unstructured text in business research makes topic modeling a central tool for constructing explanatory variables from reviews, social media, and open-ended survey responses, yet existing approaches function poorly as measurement instruments. Prior work shows that textual content predicts outcomes such as sales, satisfaction, and firm performance, but probabilistic models often generate conceptually diffuse topics, neural topic models are difficult to interpret in theory-driven settings, and large language model approaches lack standardization, stability, and alignment with document-level representations. We introduce LX Topic, a neural topic method that conceptualizes topics as latent linguistic constructs and produces calibrated document-level topic proportions for empirical analysis. LX Topic builds on FASTopic to ensure strong document representativeness and integrates large language model refinement at the topic-word level using alignment and confidence-weighting mechanisms that enhance semantic coherence without distorting document-topic distributions. Evaluations on large-scale Amazon and Yelp review datasets demonstrate that LX Topic achieves the highest overall topic quality relative to leading models while preserving clustering and classification performance. By unifying topic discovery, refinement, and standardized output in a web-based system, LX Topic establishes topic modeling as a reproducible, interpretable, and measurement-oriented instrument for marketing research and practice. --- ### Extending Neural Operators: Robust Handling of Functions Beyond the Training Set Authors: Blaine Quackenbush, Paul J. Atzberger Published: 2026-03-04 Categories: cs.LG, cs.CV, math.NA, math.OC, stat.ML arXiv: https://arxiv.org/abs/2603.03621v1 We develop a rigorous framework for extending neural operators to handle out-of-distribution input functions. We leverage kernel approximation techniques and provide theory for characterizing the input-output function spaces in terms of Reproducing Kernel Hilbert Spaces (RKHSs). We provide theorems on the requirements for reliable extensions and their predicted approximation accuracy. We also establish formal relationships between specific kernel choices and their corresponding Sobolev Native Spaces. This connection further allows the extended neural operators to reliably capture not only function values but also their derivatives. Our methods are empirically validated through the solution of elliptic partial differential equations (PDEs) involving operators on manifolds having point-cloud representations and handling geometric contributions. We report results on key factors impacting the accuracy and computational performance of the extension approaches. --- ### CoRe-BT: A Multimodal Radiology-Pathology-Text Benchmark for Robust Brain Tumor Typing Authors: Juampablo E. Heras Rivera, Daniel K. Low, Xavier Xiong, Jacob J. Ruzevick, Daniel D. Child, Wen-wai Yim, Mehmet Kurt, Asma Ben Abacha Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03618v1 Accurate brain tumor typing requires integrating heterogeneous clinical evidence, including magnetic resonance imaging (MRI), histopathology, and pathology reports, which are often incomplete at the time of diagnosis. We introduce CoRe-BT, a cross-modal radiology-pathology-text benchmark for brain tumor typing, designed to study robust multimodal learning under missing modality conditions. The dataset comprises 310 patients with multi-sequence brain MRI (T1, T1c, T2, FLAIR), including 95 cases with paired H&E-stained whole-slide pathology images and pathology reports. All cases are annotated with tumor type and grade, and MRI volumes include expert-annotated tumor masks, enabling both region-aware modeling and auxiliary learning tasks. Tumors are categorized into six clinically relevant classes capturing the heterogeneity of common and rare glioma subtypes. We evaluate tumor typing under variable modality availability by comparing MRI-only models with multimodal approaches that incorporate pathology information when present. Baseline experiments demonstrate the feasibility of multimodal fusion and highlight complementary modality contributions across clinically relevant typing tasks. CoRe-BT provides a grounded testbed for advancing multimodal glioma typing and representation learning in realistic scenarios with incomplete clinical data. --- ### RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation Authors: Hao Li, Yuhao Wang, Wenning Hao, Pingping Zhang, Dong Wang, Huchuan Lu Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03617v1 RGB-Thermal (RGBT) tracking aims to achieve robust object localization across diverse environmental conditions by fusing visible and thermal infrared modalities. However, existing RGBT trackers rely solely on initial-frame visual information for target modeling, failing to adapt to appearance variations due to the absence of language guidance. Furthermore, current methods suffer from redundant search regions and heterogeneous modality gaps, causing background distraction. To address these issues, we first introduce textual descriptions into RGBT tracking benchmarks. This is accomplished through a pipeline that leverages Multi-modal Large Language Models (MLLMs) to automatically produce texual annotations. Afterwards, we propose RAGTrack, a novel Retrieval-Augmented Generation framework for robust RGBT tracking. To this end, we introduce a Multi-modal Transformer Encoder (MTE) for unified visual-language modeling. Then, we design an Adaptive Token Fusion (ATF) to select target-relevant tokens and perform channel exchanges based on cross-modal correlations, mitigating search redundancies and modality gaps. Finally, we propose a Context-aware Reasoning Module (CRM) to maintain a dynamic knowledge base and employ a Retrieval-Augmented Generation (RAG) to enable temporal linguistic reasoning for robust target modeling. Extensive experiments on four RGBT benchmarks demonstrate that our framework achieves state-of-the-art performance across various challenging scenarios. The source code is available https://github.com/IdolLab/RAGTrack. --- ### LeafInst - Unified Instance Segmentation Network for Fine-Grained Forestry Leaf Phenotype Analysis: A New UAV based Benchmark Authors: Taige Luo, Junru Xie, Chenyang Fan, Bingrong Liu, Ruisheng Wang, Yang Shao, Sheng Xu, Lin Cao Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03616v1 Intelligent forest tree breeding has advanced plant phenotyping, yet existing research largely focuses on large-leaf agricultural crops, with limited attention to fine-grained leaf analysis of sapling trees in open-field environments. Natural scenes introduce challenges including scale variation, illumination changes, and irregular leaf morphology. To address these issues, we collected UAV RGB imagery of field-grown saplings and constructed the Poplar-leaf dataset, containing 1,202 branches and 19,876 pixel-level annotated leaf instances. To our knowledge, this is the first instance segmentation dataset specifically designed for forestry leaves in open-field conditions. We propose LeafInst, a novel segmentation framework tailored for irregular and multi-scale leaf structures. The model integrates an Asymptotic Feature Pyramid Network (AFPN) for multi-scale perception, a Dynamic Asymmetric Spatial Perception (DASP) module for irregular shape modeling, and a dual-residual Dynamic Anomalous Regression Head (DARH) with Top-down Concatenation decoder Feature Fusion (TCFU) to improve detection and segmentation performance. On Poplar-leaf, LeafInst achieves 68.4 mAP, outperforming YOLOv11 by 7.1 percent and MaskDINO by 6.5 percent. On the public PhenoBench benchmark, it reaches 52.7 box mAP, exceeding MaskDINO by 3.4 percent. Additional experiments demonstrate strong generalization and practical utility for large-scale leaf phenotyping. --- ### Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression Authors: Haotian Zhang, Feiyue Long, Yixin Yu, Jian Xue, Haocheng Tang, Tongda Xu, Zhenning Shi, Yan Wang, Siwei Ma, Jiaqi Zhang Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03615v1 Multi-view image compression (MIC) aims to achieve high compression efficiency by exploiting inter-image correlations, playing a crucial role in 3D applications. As a subfield of MIC, distributed multi-view image compression (DMIC) offers performance comparable to MIC while eliminating the need for inter-view information at the encoder side. However, existing methods in DMIC typically treat all images equally, overlooking the varying degrees of correlation between different views during decoding, which leads to suboptimal coding performance. To address this limitation, we propose a novel $\textbf{OmniParallax Attention Mechanism}$ (OPAM), which is a general mechanism for explicitly modeling correlations and aligned features between arbitrary pairs of information sources. Building upon OPAM, we propose a Parallax Multi Information Fusion Module (PMIFM) to adaptively integrate information from different sources. PMIFM is incorporated into both the joint decoder and the entropy model to construct our end-to-end DMIC framework, $\textbf{ParaHydra}$. Extensive experiments demonstrate that $\textbf{ParaHydra}$ is $\textbf{the first DMIC method}$ to significantly surpass state-of-the-art MIC codecs, while maintaining low computational overhead. Performance gains become more pronounced as the number of input views increases. Compared with LDMIC, $\textbf{ParaHydra}$ achieves bitrate savings of $\textbf{19.72%}$ on WildTrack(3) and up to $\textbf{24.18%}$ on WildTrack(6), while significantly improving coding efficiency (as much as $\textbf{65}\times$ in decoding and $\textbf{34}\times$ in encoding). --- ### Empirical Evaluation of No Free Lunch Violations in Permutation-Based Optimization Authors: Grzegorz Sroka Published: 2026-03-04 Categories: stat.ML, cs.NE, math.OC arXiv: https://arxiv.org/abs/2603.03613v1 The No Free Lunch (NFL) theorem guarantees equal average performance only under uniform sampling of a function space closed under permutation (c.u.p.). We ask when this averaging ceases to reflect what benchmarking actually reports. We study an iterative-search setting with sampling without replacement, where algorithms differ only in evaluation order. Binary objectives allow exhaustive evaluation in the fully enumerable case, and efficiency is defined by the first time the global minimum is reached. We then construct two additional benchmarks by algebraically recombining the same baseline functions through sums and differences. Function-algorithm relations are examined via correlation structure, hierarchical clustering, delta heatmaps, and PCA. A one-way ANOVA with Tukey contrasts confirms that algebraic reformulations induce statistically meaningful shifts in performance patterns. The uniformly sampled baseline remains consistent with the global NFL symmetry. In contrast, the algebraically modified benchmarks yield stable re-rankings and coherent clusters of functions and sampling policies. Composite objectives can also exhibit non-additive search effort despite being built from simpler components. Monte Carlo experiments indicate that order effects persist in larger spaces and depend on function class. Taken together, the results show how objective reformulation and benchmark design can generate structured local departures from NFL intuition. They motivate algorithm choice that is aware of both the problem class and the objective representation. This message applies to evolutionary computation as well as to statistical procedures based on relabeling, resampling, and permutation tests. --- ### Why Are Linear RNNs More Parallelizable? Authors: William Merrill, Hongjian Jiang, Yanhong Li, Anthony Lin, Ashish Sabharwal Published: 2026-03-04 Categories: cs.LG, cs.CC, cs.CL, cs.FL arXiv: https://arxiv.org/abs/2603.03612v3 The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability. While prior work establishes the expressivity benefits of LRNNs over transformers, it is unclear what makes LRNNs -- but not traditional, nonlinear RNNs -- as easy to parallelize in practice as transformers. We answer this question by providing a tight connection between types of RNNs and standard complexity classes. We show that LRNNs can be viewed as log-depth (bounded fan-in) arithmetic circuits, which represents only a slight depth overhead relative to log-depth boolean circuits that transformers admit. Furthermore, we show that nonlinear RNNs can solve $\mathsf{L}$-complete problems (and even $\mathsf{P}$-complete ones, under polynomial precision), revealing a fundamental barrier to parallelizing them as efficiently as transformers. Our theory also identifies fine-grained expressivity differences between recent popular LRNN variants: permutation-diagonal LRNNs are $\mathsf{NC}^1$-complete whereas diagonal-plus-low-rank LRNNs are more expressive ($\mathsf{PNC}^1$-complete). We provide further insight by associating each type of RNN with a corresponding automata-theoretic model that it can simulate. Together, our results reveal fundamental tradeoffs between nonlinear RNNs and different variants of LRNNs, providing a foundation for designing LLM architectures that achieve an optimal balance between expressivity and parallelism. --- ### Riemannian Optimization in Modular Systems Authors: Christian Pehle, Jean-Jacques Slotine Published: 2026-03-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03610v1 Understanding how systems built out of modular components can be jointly optimized is an important problem in biology, engineering, and machine learning. The backpropagation algorithm is one such solution and has been instrumental in the success of neural networks. Despite its empirical success, a strong theoretical understanding of it is lacking. Here, we combine tools from Riemannian geometry, optimal control theory, and theoretical physics to advance this understanding. We make three key contributions: First, we revisit the derivation of backpropagation as a constrained optimization problem and combine it with the insight that Riemannian gradient descent trajectories can be understood as the minimum of an action. Second, we introduce a recursively defined layerwise Riemannian metric that exploits the modular structure of neural networks and can be efficiently computed using the Woodbury matrix identity, avoiding the $O(n^3)$ cost of full metric inversion. Third, we develop a framework of composable ``Riemannian modules'' whose convergence properties can be quantified using nonlinear contraction theory, providing algorithmic stability guarantees of order $O(κ^2 L/(ξμ\sqrt{n}))$ where $κ$ and $L$ are Lipschitz constants, $μ$ is the mass matrix scale, and $ξ$ bounds the condition number. Our layerwise metric approach provides a practical alternative to natural gradient descent. While we focus here on studying neural networks, our approach more generally applies to the study of systems made of modules that are optimized over time, as it occurs in biology during both evolution and development. --- ### Tracking Feral Horses in Aerial Video Using Oriented Bounding Boxes Authors: Saeko Takizawa, Tamao Maeda, Shinya Yamamoto, Hiroaki Kawashima Published: 2026-03-04 Categories: cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2603.03604v1 The social structures of group-living animals such as feral horses are diverse and remain insufficiently understood, even within a single species. To investigate group dynamics, aerial videos are often utilized to track individuals and analyze their movement trajectories, which are essential for evaluating inter-individual interactions and comparing social behaviors. Accurate individual tracking is therefore crucial. In multi-animal tracking, axis-aligned bounding boxes (bboxes) are widely used; however, for aerial top-view footage of entire groups, their performance degrades due to complex backgrounds, small target sizes, high animal density, and varying body orientations. To address this issue, we employ oriented bounding boxes (OBBs), which include rotation angles and reduce unnecessary background. Nevertheless, current OBB detectors such as YOLO-OBB restrict angles within a 180$^{\circ}$ range, making it impossible to distinguish head from tail and often causing sudden 180$^{\circ}$ flips across frames, which severely disrupts continuous tracking. To overcome this limitation, we propose a head-orientation estimation method that crops OBB-centered patches, applies three detectors (head, tail, and head-tail), and determines the final label through IoU-based majority voting. Experiments using 299 test images show that our method achieves 99.3% accuracy, outperforming individual models, demonstrating its effectiveness for robust OBB-based tracking. --- ### Detection and Identification of Penguins Using Appearance and Motion Features Authors: Kasumi Seko, Hiroki Kinoshita, Raj Rajeshwar Malinda, Hiroaki Kawashima Published: 2026-03-04 Categories: cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2603.03603v1 In animal facilities, continuous surveillance of penguins is essential yet technically challenging due to their homogeneous visual characteristics, rapid and frequent posture changes, and substantial environmental noise such as water reflections. In this study, we propose a framework that enhances both detection and identification performance by integrating appearance and motion features. For detection, we adapted YOLO11 to process consecutive frames to overcome the lack of temporal consistency in single-frame detectors. This approach leverages motion cues to detect targets even when distinct visual features are obscured. Our evaluation shows that fine-tuning the model with two-frame inputs improves mAP@0.5 from 0.922 to 0.933, outperforming the baseline, and successfully recovers individuals that are indistinguishable in static images. For identification, we introduce a tracklet-based contrastive learning approach applied after tracking. Through qualitative visualization, we demonstrate that the method produces coherent feature embeddings, bringing samples from the same individual closer in the feature space, suggesting the potential for mitigating ID switching. --- ### DM-CFO: A Diffusion Model for Compositional 3D Tooth Generation with Collision-Free Optimization Authors: Yan Tian, Pengcheng Xue, Weiping Ding, Mahmoud Hassaballah, Karen Egiazarian, Aura Conci, Abdulkadir Sengur, Leszek Rutkowski Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03602v1 The automatic design of a 3D tooth model plays a crucial role in dental digitization. However, current approaches face challenges in compositional 3D tooth generation because both the layouts and shapes of missing teeth need to be optimized.In addition, collision conflicts are often omitted in 3D Gaussian-based compositional 3D generation, where objects may intersect with each other due to the absence of explicit geometric information on the object surfaces. Motivated by graph generation through diffusion models and collision detection using 3D Gaussians, we propose an approach named DM-CFO for compositional tooth generation, where the layout of missing teeth is progressively restored during the denoising phase under both text and graph constraints. Then, the Gaussian parameters of each layout-guided tooth and the entire jaw are alternately updated using score distillation sampling (SDS). Furthermore, a regularization term based on the distances between the 3D Gaussians of neighboring teeth and the anchor tooth is introduced to penalize tooth intersections. Experimental results on three tooth-design datasets demonstrate that our approach significantly improves the multiview consistency and realism of the generated teeth compared with existing methods. Project page: https://amateurc.github.io/CF-3DTeeth/. --- ### NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training Authors: Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin P Hewa Koneputugodage, Shamane Siriwardhana, Violetta Shevchenko, Karol Pajak, James Snewin, Gil Avraham, Alexander Long Published: 2026-03-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03597v1 The rapid progress of large language models (LLMs) is increasingly constrained by memory and deployment costs, motivating compression methods for practical deployment. Many state-of-the-art compression pipelines leverage the low-rank structure of trained weight matrices, a phenomenon often associated with the properties of popular optimizers such as Adam. In this context, Muon is a recently proposed optimizer that improves LLM pretraining via full-rank update steps, but its induced weight-space structure has not been characterized yet. In this work, we report a surprising empirical finding: despite imposing full-rank updates, Muon-trained models exhibit pronounced low-rank structure in their weight matrices and are readily compressible under standard pipelines. Motivated by this insight, we propose NuMuon, which augments Muon with a nuclear-norm constraint on the update direction, further constraining the learned weights toward low-rank structure. Across billion-parameter-scale models, we show that NuMuon increases weight compressibility and improves post-compression model quality under state-of-the-art LLM compression pipelines while retaining Muon's favorable convergence behavior. --- ### MEM: Multi-Scale Embodied Memory for Vision Language Action Models Authors: Marcel Torne, Karl Pertsch, Homer Walke, Kyle Vedder, Suraj Nair, Brian Ichter, Allen Z. Ren, Haohuan Wang, Jiaming Tang, Kyle Stachowicz, Karan Dhabalia, Michael Equi et al. Published: 2026-03-04 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.03596v2 Conventionally, memory in end-to-end robotic learning involves inputting a sequence of past observations into the learned policy. However, in complex multi-stage real-world tasks, the robot's memory must represent past events at multiple levels of granularity: from long-term memory that captures abstracted semantic concepts (e.g., a robot cooking dinner should remember which stages of the recipe are already done) to short-term memory that captures recent events and compensates for occlusions (e.g., a robot remembering the object it wants to pick up once its arm occludes it). In this work, our main insight is that an effective memory architecture for long-horizon robotic control should combine multiple modalities to capture these different levels of abstraction. We introduce Multi-Scale Embodied Memory (MEM), an approach for mixed-modal long-horizon memory in robot policies. MEM combines video-based short-horizon memory, compressed via a video encoder, with text-based long-horizon memory. Together, they enable robot policies to perform tasks that span up to fifteen minutes, like cleaning up a kitchen, or preparing a grilled cheese sandwich. Additionally, we find that memory enables MEM policies to intelligently adapt manipulation strategies in-context. --- ### Hybrid Belief Reinforcement Learning for Efficient Coordinated Spatial Exploration Authors: Danish Rizvi, David Boyle Published: 2026-03-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03595v1 Coordinating multiple autonomous agents to explore and serve spatially heterogeneous demand requires jointly learning unknown spatial patterns and planning trajectories that maximize task performance. Pure model-based approaches provide structured uncertainty estimates but lack adaptive policy learning, while deep reinforcement learning often suffers from poor sample efficiency when spatial priors are absent. This paper presents a hybrid belief-reinforcement learning (HBRL) framework to address this gap. In the first phase, agents construct spatial beliefs using a Log-Gaussian Cox Process (LGCP) and execute information-driven trajectories guided by a Pathwise Mutual Information (PathMI) planner with multi-step lookahead. In the second phase, trajectory control is transferred to a Soft Actor-Critic (SAC) agent, warm-started through dual-channel knowledge transfer: belief state initialization supplies spatial uncertainty, and replay buffer seeding provides demonstration trajectories generated during LGCP exploration. A variance-normalized overlap penalty enables coordinated coverage through shared belief state, permitting cooperative sensing in high-uncertainty regions while discouraging redundant coverage in well-explored areas. The framework is evaluated on a multi-UAV wireless service provisioning task. Results show 10.8% higher cumulative reward and 38% faster convergence over baselines, with ablation studies confirming that dual-channel transfer outperforms either channel alone. --- ### Deep Interest Mining for Intent-Enriched Semantic IDs in Multimodal Generative Recommendation Authors: Yangchen Zeng, Jinze Wang Published: 2026-03-03 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.20861v3 Semantic IDs (SIDs) provide the discrete item vocabulary used by generative recommendation, but their quality depends on what item evidence is preserved before quantization. In product recommendation, surface metadata often misses latent usage intent, visual evidence may be only weakly reflected in text, and downstream policy learning provides sparse feedback about whether a generated SID corresponds to a semantically useful item. We introduce \textbf{DeepInterestGR}, an intent-enriched SID framework for generative recommendation. Before SID quantization, \textbf{CMSA} enriches item representations through two complementary evidence paths: recommendation-oriented VLM captions and projected image embeddings. \textbf{DCIM} then uses an LLM to mine item-side intent descriptors -- latent usage motivations implied by product content rather than personalized user states. During policy training over the constructed SIDs, \textbf{QARM} adds a relevance-gated semantic-quality bonus on top of standard SID rewards, applying the bonus only when the generated SID decodes to the target item. Thus, semantic quality cannot reward a fluent but irrelevant item prediction. Experiments on three Amazon Product Review categories (Beauty, Sports, and Instruments) show that DeepInterestGR improves over competitive generative and RL-based baselines, with relative gains of up to \textbf{15.1\%} in NDCG@5 and \textbf{13.9\%} in NDCG@10 over the strongest per-metric baseline. Component ablations, CMSA branch analyses, reward variants, and SID-level case studies support a bounded claim: enriching pre-quantization item evidence with visual cues and item-side intent descriptors, together with relevance-gated semantic rewards, improves SID-based generative recommendation under the evaluated settings. --- ### The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge? Authors: Yirong Zeng, Shen You, Yufei Liu, Qunyao Du, Xiao Ding, Yutai Hou, Yuxian Wang, Wu Ning, Haonan Song, Dandan Tu, Bibo Cai, Ting Liu Published: 2026-03-03 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.19749v1 Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical yet under-explored phenomenon: tool overuse, the unnecessary tool-use during reasoning. In this paper, we first reveal this phenomenon is pervasive across diverse LLMs. We then experimentally elucidate its underlying mechanisms through two key lenses: (1) First, by analyzing tool-use behavior across different internal knowledge availability regions, we identify a \textit{knowledge epistemic illusion}: models misjudge internal knowledge boundaries and fail to accurately perceive their actual knowledge availability. To mitigate this, we propose a knowledge-aware epistemic boundary alignment strategy based on direct preference optimization, which reduces tool usage in by 82.8\% while yielding an accuracy improvement. (2) Second, we establish a causal link between reward structures and tool-use behavior by visualizing the tool-augmented training process. It reveals that \textit{outcome-only rewards} inadvertently encourage tool overuse by rewarding only final correctness, regardless of tool efficiency. To verify this, we balance reward signals during training rather than relying on outcome-only rewards, cutting unnecessary tool calls by 66.7\% (7B) and 60.7\% (32B) without sacrificing accuracy. Finally, we provide theoretical justification in this two lenses to understand tool overuse. --- ### Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development Authors: Matteo Casserini, Alessandro Facchini, Andrea Ferrario Published: 2026-03-03 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.16323v2 As autonomous coding agents become deeply embedded in software development workflows, their high operational velocity introduces a critical oversight challenge: the accumulating divergence between agentic actions and architectural intent. We term this process agentic entropy: a systemic drift that traditional code diff-based and HCXAI methods fail to capture, as they address local outputs rather than global agentic behaviour. To close this gap, we propose a process-oriented explainability framework that exposes how agentic decisions unfold across time, tool calls, and architectural boundaries. Built around three pillars (conformity seeding, reasoning monitoring, and a causal graph interface) our approach provides intent-level telemetry that complements, rather than replaces, existing review practices. We demonstrate its relevance across two user profiles: lay users engaged in vibe coding, who gain structural visibility otherwise masked by functional success; and professional developers, who gain richer contextual grounding for code review without increased overhead. By treating cognitive drift as a first-class concern alongside code quality, our framework supports the minimum level of human comprehension required for agentic oversight to remain substantive. --- ### Acoustic and Facial Markers of Perceived Conversational Success in Spontaneous Speech Authors: Thanushi Withanage, Elizabeth Redcay, Carol Espy-Wilson Published: 2026-03-03 Categories: cs.HC, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.15322v1 Individuals often align their speaking patterns with their interlocutors, a phenomenon linked to engagement and rapport. While well documented in task-oriented dialogues, less is known about entrainment in naturalistic, non-task and virtual settings. In this study, we analyze a large corpus of spontaneous dyadic Zoom conversations to examine how conversational dynamics relate to perceived interaction quality. We extract multimodal features encompassing turn-taking, pauses, facial movements, and acoustic measures such as pitch and intensity. Perceived conversational success was quantified via factor analysis of post-conversation ratings. Results demonstrate that entrainment reliably detected in spontaneous speech and correlates with higher perceived success. These findings identify key interactional markers of conversational quality and highlight opportunities for targeted interventions to foster more effective and engaging communication. --- ### DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review Authors: Yixuan Weng, Minjun Zhu, Qiujie Xie, Zhiyuan Ning, Shichen Li, Panzhong Lu, Zhen Lin, Enhao Gu, Qiyao Sun, Yue Zhang Published: 2026-03-03 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2604.09590v1 Automated peer review is often framed as generating fluent critique, yet reviewers and area chairs need judgments they can \emph{audit}: where a concern applies, what evidence supports it, and what concrete follow-up is required. DeepReviewer~2.0 is a process-controlled agentic review system built around an output contract: it produces a \textbf{traceable review package} with anchored annotations, localized evidence, and executable follow-up actions, and it exports only after meeting minimum traceability and coverage budgets. Concretely, it first builds a manuscript-only claim--evidence--risk ledger and verification agenda, then performs agenda-driven retrieval and writes anchored critiques under an export gate. On 134 ICLR~2025 submissions under three fixed protocols, an \emph{un-finetuned 196B} model running DeepReviewer~2.0 outperforms Gemini-3.1-Pro-preview, improving strict major-issue coverage (37.26\% vs.\ 23.57\%) and winning 71.63\% of micro-averaged blind comparisons against a human review committee, while ranking first among automatic systems in our pool. We position DeepReviewer~2.0 as an assistive tool rather than a decision proxy, and note remaining gaps such as ethics-sensitive checks. --- ### An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code Authors: Sophie Weidmann, Fernando Castor Published: 2026-03-03 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.02352v1 Although LLMs are capable of generating functionally correct code, they also tend to produce less energy-efficient code in comparison to human-written solutions. As these inefficiencies lead to higher computational overhead, they are in direct conflict with Green Software Development (GSD) efforts, which aim to reduce the energy consumption of code. To support these efforts, this study aims to investigate whether and how LLMs can be optimized to promote the generation of energy-efficient code. To this end, we employ Contrastive Prompt Tuning (CPT). CPT combines Contrastive Learning techniques, which help the model to distinguish between efficient and inefficient code, and Prompt Tuning, a Parameter-Efficient Fine Tuning (PEFT) approach that requires only a fraction of the cost of traditional fine tuning. This study evaluates CPT on Python, Java and C++ coding problems across three different models to provide a comprehensive evaluation. The method achieves consistent improvements in code accuracy for two models but efficiency gains vary by model, language and task complexity, indicating that improvements are not uniformly reliable. --- ### MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing Authors: Runze Li, Kedi Chen, Guwei Feng, Mo Yu, Jun Wang, Wei Zhang Published: 2026-03-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.22289v1 Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack interpretability. Large Language Models (LLMs) offer strong reasoning capabilities but struggle with limited context windows and hallucinations. Furthermore, existing LLM-based methods typically require expensive fine-tuning, limiting scalability and adaptability to new data. We propose MERIT (Memory-Enhanced Retrieval for Interpretable Knowledge Tracing), a training-free framework combining frozen LLM reasoning with structured pedagogical memory. Rather than updating parameters, MERIT transforms raw interaction logs into an interpretable memory bank. The framework uses semantic denoising to categorize students into latent cognitive schemas and constructs a paradigm bank where representative error patterns are analyzed offline to generate explicit Chain-of-Thought (CoT) rationales. During inference, a hierarchical routing mechanism retrieves relevant contexts, while a logic-augmented module applies semantic constraints to calibrate predictions. By grounding the LLM in interpretable memory, MERIT achieves state-of-the-art performance on real-world datasets without gradient updates. This approach reduces computational costs and supports dynamic knowledge updates, improving the accessibility and transparency of educational diagnosis. --- ### Evaluating Prompting Strategies for Chart Question Answering with Large Language Models Authors: Ruthuparna Naikar, Ying Zhu Published: 2026-03-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.22288v1 Prompting strategies affect LLM reasoning performance, but their role in chart-based QA remains underexplored. We present a systematic evaluation of four widely used prompting paradigms (Zero-Shot, Few-Shot, Zero-Shot Chain-of-Thought, and Few-Shot Chain-of-Thought) across GPT-3.5, GPT-4, and GPT-4o on the ChartQA dataset. Our framework operates exclusively on structured chart data, isolating prompt structure as the only experimental variable, and evaluates performance using two metrics: Accuracy and Exact Match. Results from 1,200 diverse ChartQA samples show that Few-Shot Chain-of-Thought prompting consistently yields the highest accuracy (up to 78.2\%), particularly on reasoning-intensive questions, while Few-Shot prompting improves format adherence. Zero-Shot performs well only with high-capacity models on simpler tasks. These findings provide actionable guidance for selecting prompting strategies in structured data reasoning tasks, with implications for both efficiency and accuracy in real-world applications. --- ### Thinking into the Future: Latent Lookahead Training for Transformers Authors: Lorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Moin Nabi Published: 2026-03-03 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.20219v1 Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or reflecting upon multiple plausible continuations. Furthermore, the compute allocation across tokens is uniform; every token is formed based on a single forward-pass, potentially limiting the model's expressiveness in cases where difficult tokens require inherently more compute. Towards addressing these limitations, we introduce latent lookahead, a training strategy that enables models to "think" before generating: at selected positions in the sequence, before committing to the next token, the model performs a multi-step lookahead in latent space. More precisely, instead of sampling future tokens, we leverage the network's latent space by recursively feeding its hidden states back into the context for $τ$ steps, investing more compute on predicting that token. This produces $τ$ latent predictions that are supervised against the next $τ$ ground-truth tokens, encouraging the model to "lookahead" and refine its prediction. We show that latent lookahead substantially outperforms both autoregressive and non-autoregressive baselines on planning tasks such as maze solving, Sudoku, and ProsQA, where foresight is essential. --- ### An experimental study of KV cache reuse strategies in chunk-level caching systems Authors: Samuel Cestola, Tianxiang Xia, Zheng Weiyan, Zheng Pengfei, Diego Didona Published: 2026-03-03 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.20218v1 Retrieval-augmented generation improves large language models' accuracy by adding relevant retrieved text to the prompt. Chunk level caching (CLC) accelerates inference by precomputing KV caches for these retrieved chunks and reusing them. However, these caches miss cross-attention dependencies between chunks, which can reduce output quality. Several methods try to improve CLC accuracy using different techniques. We make two main contributions. First, we show that existing CLC approaches have fundamental limitations that limit their accuracy or their applicability. We back this conclusion with an extensive CLC system experimental evaluation. Second, we observe that existing CLC techniques are complementary. We leverage this insight to propose a new CLC design that carefully combines them and achieves better accuracy. --- ### Expected Reward Prediction, with Applications to Model Routing Authors: Kenan Hasanaliyev, Silas Alberti, Jenny Hamer, Dheeraj Rajagopal, Kevin Robinson, Jasper Snoek, Victor Veitch, Alexander Nicholas D'Amour Published: 2026-03-03 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.20217v1 Reward models are a standard tool to score responses from LLMs. Reward models are built to rank responses to a fixed prompt sampled from a single model, for example to choose the best of n sampled responses. In this paper, we study whether scores from response-level reward models lifted to score a model's suitability for a prompt, prior to seeing responses from that model. Specifically, we show that it is straightforward to predict the expected reward that an LLM would earn from the reward model under repeated sampling. Further, we show that these expected reward predictions are precise and discriminative enough to support an application to a model routing protocol that routes prompts to models at inference time to maximize reward while controlling computational cost. We demonstrate the performance of this routing procedure on the open-perfectblend dataset, using a model pool composed of Llama3.1-Instruct 8B/70B, Gemma2-IT 9B/27B, and Gemma1-IT 7B models. Our simple expected reward prediction--based routing (ERP) outperforms baselines that route prompts to models with the best average performance within each prompt's category, and explains the success of more complex routing protocols that implicitly estimate an expected reward. Our approach has the added advantage of being trivially extensible as new models are added to the pool. --- ### Locally Coherent Parallel Decoding in Diffusion Language Models Authors: Michael Hersche, Nicolas Menet, Ronan Tanios, Abbas Rahimi Published: 2026-03-03 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.20216v2 Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency and bidirectional capabilities that are particularly appealing for code generation and editing. Achieving sub-linear latency in discrete DLMs requires predicting multiple tokens in parallel. However, standard DLMs sample tokens independently from conditional marginal distributions, failing to capture the joint dependencies among concurrently generated tokens. As a result, they often lead to syntactic inconsistencies and break multi-token structures. In this work, we introduce CoDiLA (Coherent Diffusion with Local Autoregression), a method that reconciles parallel sampling with local dependency modeling. Rather than forcing the DLM to resolve fine-grained syntax, CoDiLA delegates local decoding to a small, auxiliary AR model operating on the diffusion latents. This design allows for parallel generation while ensuring sequential validity within a block and maintaining core DLM capabilities, including bidirectional modeling across blocks. We demonstrate that using a highly compact auxiliary AR model (e.g., 0.6B parameters) effectively eliminates coherence artifacts, establishing a new Pareto frontier for accuracy and speed in code generation benchmarks. ---