# Research Papers — 2026-03 · bundle page 150 of 243 > Full-text markdown of papers #7451–7500 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/150 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/149.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/151.md) ### BehaviorVLM: Unified Finetuning-Free Behavioral Understanding with Vision-Language Reasoning Authors: Jingyang Ke, Weihan Li, Amartya Pradhan, Jeffrey Markowitz, Anqi Wu Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12176v1 Understanding freely moving animal behavior is central to neuroscience, where pose estimation and behavioral understanding form the foundation for linking neural activity to natural actions. Yet both tasks still depend heavily on human annotation or unstable unsupervised pipelines, limiting scalability and reproducibility. We present BehaviorVLM, a unified vision-language framework for pose estimation and behavioral understanding that requires no task-specific finetuning and minimal human labeling by guiding pretrained Vision-Language Models (VLMs) through detailed, explicit, and verifiable reasoning steps. For pose estimation, we leverage quantum-dot-grounded behavioral data and propose a multi-stage pipeline that integrates temporal, spatial, and cross-view reasoning. This design greatly reduces human annotation effort, exposes low-confidence labels through geometric checks such as reprojection error, and produces labels that can later be filtered, corrected, or used to fine-tune downstream pose models. For behavioral understanding, we propose a pipeline that integrates deep embedded clustering for over-segmented behavior discovery, VLM-based per-clip video captioning, and LLM-based reasoning to merge and semantically label behavioral segments. The behavioral pipeline can operate directly from visual information and does not require keypoints to segment behavior. Together, these components enable scalable, interpretable, and label-light analysis of multi-animal behavior. --- ### LatentGeo: Learnable Auxiliary Constructions in Latent Space for Multimodal Geometric Reasoning Authors: Haiying Xu, Zihan Wang, Song Dai, Zhengxuan Zhang, Kairan Dou, Xuming Hu Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12166v1 Despite recent advances in multimodal reasoning, representing auxiliary geometric constructions remains a fundamental challenge for multimodal large language models (MLLMs). Such constructions are absent from the original diagram and must be introduced before theorems apply. Existing approaches predominantly rely on explicit construction paradigms, including text-based geometric specification, visual-token interleaving during reasoning, and tool-augmented geometric execution. However, these methods either fail to faithfully represent complex spatial relationships, incur representation mismatch between discrete symbols and continuous geometric structures, or rely on external capabilities that hinder end-to-end optimization. To address these limitations, we propose LatentGeo, a framework that learns continuous latent visual representations to internalize auxiliary geometric constructions without pixel-level rendering or external executors. We design a three-stage curriculum that progressively aligns and internalizes these latent representations through auxiliary visual supervision, followed by LaGDPO, a latent-aware reinforcement learning procedure that stabilizes latent representations during policy optimization while improving end-task correctness. To systematically evaluate construction-centric representation quality, we introduce GeoAux, a new benchmark targeting visually dependent geometry problems, and conduct experiments on GeoAux and MathVerse. Results show that LatentGeo achieves substantial gains on geometric reasoning tasks, particularly those requiring auxiliary constructions. Extensive analyses and ablation studies further validate the effectiveness of each component in our framework. --- ### QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions Authors: Jiayin Lei, Ming Ma, Yunxi Duan, Chenxi Li, Tianming Yang Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12165v3 Synthetic data has become essential for training code generation models, yet it introduces significant noise and hallucinations that are difficult to detect with current metrics. Existing data selection methods like Instruction-Following Difficulty (IFD) typically assess how hard a model generates an answer given a query ($A|Q$). However, this metric is ambiguous on noisy synthetic data, where low probability can distinguish between intrinsic task complexity and model-generated hallucinations. Here, we propose QAQ, a novel data selection framework that evaluates data quality from the reverse direction: how well can the answer predict the query ($Q|A$)? We define Reverse Mutual Information (RMI) to quantify the information gain about the query conditioned on the answer. Our analyses reveal that both extremes of RMI signal quality issues: low RMI indicates semantic misalignment, while excessively high RMI may contain defect patterns that LLMs easily recognize. Furthermore, we introduce a selection strategy based on the disagreement between strong and weak models to identify samples that are valid yet challenging. Experiments across three datasets spanning code generation (WarriorCoder, Magpie-Qwen2.5-Coder-Pro-300K) and math reasoning (OpenR1-Math-220k) demonstrate that selecting just 25\% of data using stratified RMI matches full-data performance while being consistently competitive with or better than existing data selection methods. Our approach highlights the importance of bidirectional semantic coherence in synthetic data curation, offering a scalable pathway to reduce computational costs without sacrificing model capability. Code is available at https://github.com/XXSg559/QAQ. --- ### QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions Authors: Jiayin Lei, Ming Ma, Yunxi Duan, Chenxi Li, Tianming Yang Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12165v2 Synthetic data has become essential for training code generation models, yet it introduces significant noise and hallucinations that are difficult to detect with current metrics. Existing data selection methods like Instruction-Following Difficulty (IFD) typically assess how hard a model generates an answer given a query ($A|Q$). However, this metric is ambiguous on noisy synthetic data, where low probability can distinguish between intrinsic task complexity and model-generated hallucinations. Here, we propose QAQ, a novel data selection framework that evaluates data quality from the reverse direction: how well can the answer predict the query ($Q|A$)? We define Reverse Mutual Information (RMI) to quantify the information gain about the query conditioned on the answer. Our analyses reveal that both extremes of RMI signal quality issues: low RMI indicates semantic misalignment, while excessively high RMI may contain defect patterns that LLMs easily recognize. Furthermore, we introduce a selection strategy based on the disagreement between strong and weak models to identify samples that are valid yet challenging. Experiments on the WarriorCoder dataset demonstrate that selecting just 25% of data using stratified RMI achieves comparable performance to full-data training, significantly outperforming existing data selection methods. Our approach highlights the importance of bidirectional semantic coherence in synthetic data curation, offering a scalable pathway to reduce computational costs without sacrificing model capability. --- ### A Quantitative Characterization of Forgetting in Post-Training Authors: Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan Published: 2026-03-12 Categories: cs.LG, cs.AI, math.ST, stat.ML arXiv: https://arxiv.org/abs/2603.12163v1 Continual post-training of generative models is widely used, yet a principled understanding of when and why forgetting occurs remains limited. We develop theoretical results under a two-mode mixture abstraction (representing old and new tasks), proposed by Chen et al. (2025) (arXiv:2510.18874), and formalize forgetting in two forms: (i) mass forgetting, where the old mixture weight collapses to zero, and (ii) old-component drift, where an already-correct old component shifts during training. For equal-covariance Gaussian modes, we prove that forward-KL objectives trained on data from the new distribution drive the old weight to zero, while reverse-KL objectives converge to the true target (thereby avoiding mass forgetting) and perturb the old mean only through overlap-gated misassignment probabilities controlled by the Bhattacharyya coefficient, yielding drift that decays exponentially with mode separation and a locally well-conditioned geometry with exponential convergence. We further quantify how replay interacts with these objectives. For forward-KL, replay must modify the training distribution to change the population optimum; for reverse-KL, replay leaves the population objective unchanged but prevents finite-batch old-mode starvation through bounded importance weighting. Finally, we analyze three recently proposed near-on-policy post-training methods, SDFT (arxiv:2601.19897), TTT-Discover (arxiv:2601.16175), and OAPL (arxiv:2602.19362), via the same lens and derive explicit conditions under which each retains old mass and exhibits overlap-controlled drift. Overall, our results show that forgetting can by precisely quantified based on the interaction between divergence direction, geometric behavioral overlap, sampling regime, and the visibility of past behavior during training. --- ### GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows Authors: Zexuan Yan, Jiarui Jin, Yue Ma, Shijian Wang, Jiahui Hu, Wenxiang Jiao, Yuan Lu, Linfeng Zhang Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12155v1 Despite recent advances in generative models driving significant progress in text rendering, accurately generating complex text and mathematical formulas remains a formidable challenge. This difficulty primarily stems from the limited instruction-following capabilities of current models when encountering out-of-distribution prompts. To address this, we introduce GlyphBanana, alongside a corresponding benchmark specifically designed for rendering complex characters and formulas. GlyphBanana employs an agentic workflow that integrates auxiliary tools to inject glyph templates into both the latent space and attention maps, facilitating the iterative refinement of generated images. Notably, our training-free approach can be seamlessly applied to various Text-to-Image (T2I) models, achieving superior precision compared to existing baselines. Extensive experiments demonstrate the effectiveness of our proposed workflow. Associated code is publicly available at https://github.com/yuriYanZeXuan/GlyphBanana. --- ### LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation Authors: Feiyu Duan, Xuanjing Huang, Zhongyu Wei Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12152v1 The rapid advancement of large language models (LLMs) has accelerated progress toward universal AI assistants. However, existing benchmarks for personalized assistants remain misaligned with real-world user-assistant interactions, failing to capture the complexity of external contexts and users' cognitive states. To bridge this gap, we propose LifeSim, a user simulator that models user cognition through the Belief-Desire-Intention (BDI) model within physical environments for coherent life trajectories generation, and simulates intention-driven user interactive behaviors. Based on LifeSim, we introduce LifeSim-Eval, a comprehensive benchmark for multi-scenario, long-horizon personalized assistance. LifeSim-Eval covers 8 life domains and 1,200 diverse scenarios, and adopts a multi-turn interactive method to assess models' abilities to complete explicit and implicit intentions, recover user profiles, and produce high-quality responses. Under both single-scenario and long-horizon settings, our experiments reveal that current LLMs face significant limitations in handling implicit intention and long-term user preference modeling. --- ### IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL Authors: Zhoujun Cheng, Yutao Xie, Yuxiao Qu, Amrith Setlur, Shibo Hao, Varad Pimpalkhute, Tongtong Liang, Feng Yao, Zhengzhong Liu, Eric Xing, Virginia Smith, Ruslan Salakhutdinov et al. Published: 2026-03-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.12151v1 While scaling laws guide compute allocation for LLM pre-training, analogous prescriptions for reinforcement learning (RL) post-training of large language models (LLMs) remain poorly understood. We study the compute-optimal allocation of sampling compute for on-policy RL methods in LLMs, framing scaling as a compute-constrained optimization over three resources: parallel rollouts per problem, number of problems per batch, and number of update steps. We find that the compute-optimal number of parallel rollouts per problem increases predictably with compute budget and then saturates. This trend holds across both easy and hard problems, though driven by different mechanisms: solution sharpening on easy problems and coverage expansion on hard problems. We further show that increasing the number of parallel rollouts mitigates interference across problems, while the number of problems per batch primarily affects training stability and can be chosen within a broad range. Validated across base models and data distributions, our results recast RL scaling laws as prescriptive allocation rules and provide practical guidance for compute-efficient LLM RL post-training. --- ### Linking Perception, Confidence and Accuracy in MLLMs Authors: Yuetian Du, Yucheng Wang, Rongyu Zhang, Zhijie Xu, Boyu Yang, Ming Kong, Jie Liu, Qiang Zhu Published: 2026-03-12 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2603.12149v1 Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a probing experiment, we reveal a severe confidence miscalibration problem in MLLMs. To address this, we propose Confidence-Driven Reinforcement Learning (CDRL), which uses original-noise image pairs and a novel confidence-based reward to enhance perceptual sensitivity and robustly calibrate the model's confidence. Beyond training benefits, calibrated confidence enables more effective test-time scaling as a free lunch. We further propose Confidence-Aware Test-Time Scaling (CA-TTS), which dynamically coordinates Self-Consistency, Self-Reflection, and Visual Self-Check modules guided by confidence signals. An Expert Model acts in multiple roles (e.g., Planner, Critic, Voter) to schedule these modules and provide external verification. Our integrated framework establishes new state-of-the-art results with consistent 8.8% gains across four benchmarks. More ablation studies demonstrate the effectiveness of each module and scaling superiority. --- ### EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Next Authors: Ye Pan, Chi Kit Wong, Yuanhuiyi Lyu, Hanqian Li, Chenfei Liao, Jiahao Huo, Lutao Jiang, Zixin Zhang, Jiacheng Chen, Yuqian Fu, Xu Zheng Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12147v2 Egocentric video provides a natural modality for studying human behavior, but conventional visual understanding captures mainly observable scenes, objects, and actions rather than the latent goals that organize them. Existing intent benchmarks typically focus on coarse event-level goals and overlook how intent evolves across procedural steps. We introduce EgoIntent, a step-level intent-understanding benchmark comprising 3,014 pre-outcome micro-steps from 32 egocentric videos across 15 indoor and outdoor daily-life scenarios. Each step is manually annotated along three complementary dimensions: Local Intent (What), the immediate goal; Procedural Intent (Why), the role of the step in the broader procedure; and Next-Plan (Next), the action most likely to follow. Multiple rounds of human review refine temporal boundaries and annotation quality. We evaluate 15 multimodal large language models using reference-based scores and complementary reference-free diagnostics. Controlled studies on four representative models show that only one model gains significantly from correct temporal order, while a single boundary frame outperforms the full ordered clip for three models. Step-only input performs best for all four models, and adding 15 seconds of history significantly degrades three. Revealing the current outcome improves Local Intent by 7.81 points, while revealing the following step improves Next-Plan by 13.17 points. These findings indicate that current models can achieve strong intent-prediction scores through static boundary cues without robustly exploiting temporal order or procedural history. --- ### FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance Authors: Quanhao Li, Zhen Xing, Rui Wang, Haidong Cao, Qi Dai, Daoguo Dong, Zuxuan Wu Published: 2026-03-12 Categories: cs.CV, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2603.12146v1 Recent advances in trajectory-controllable video generation have achieved remarkable progress. Previous methods mainly use adapter-based architectures for precise motion control along predefined trajectories. However, all these methods rely on a multi-step denoising process, leading to substantial time redundancy and computational overhead. While existing video distillation methods successfully distill multi-step generators into few-step, directly applying these approaches to trajectory-controllable video generation results in noticeable degradation in both video quality and trajectory accuracy. To bridge this gap, we introduce FlashMotion, a novel training framework designed for few-step trajectory-controllable video generation. We first train a trajectory adapter on a multi-step video generator for precise trajectory control. Then, we distill the generator into a few-step version to accelerate video generation. Finally, we finetune the adapter using a hybrid strategy that combines diffusion and adversarial objectives, aligning it with the few-step generator to produce high-quality, trajectory-accurate videos. For evaluation, we introduce FlashBench, a benchmark for long-sequence trajectory-controllable video generation that measures both video quality and trajectory accuracy across varying numbers of foreground objects. Experiments on two adapter architectures show that FlashMotion surpasses existing video distillation methods and previous multi-step models in both visual quality and trajectory consistency. --- ### Automatic Generation of High-Performance RL Environments Authors: Seth Karten, Rahul Dev Appapogu, Chi Jin Published: 2026-03-12 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.12145v2 Translating complex reinforcement learning (RL) environments into high-performance implementations has traditionally required months of specialized engineering. We present a closed-loop methodology that produces equivalent high-performance environments for minimal compute cost. Our method uses a generic prompt template, hierarchical verification (property, interaction, and rollout tests), iterative repair, and cross-backend policy transfer to verify no sim-to-sim gap. We demonstrate three distinct workflows across five environments: (1) Direct translation (no prior performance implementation exists) from Game Boy emulator PyBoy to our EmuRust (via Rust IPC) and from Pokemon Showdown to our PokeJAX (via JAX); (2) Translation verified against existing performance implementations via throughput parity with Puffer Pong, MJX and Brax at matched GPU batch sizes; and (3) New environment creation: TCGJax, the first Pokemon TCG Pocket environment, created from a web-extracted specification. At 200M parameters, the environment overhead drops below 4% of training time. Our closed-loop methodology confirms equivalence for all five environments. TCGJax, synthesized from a private reference absent from public repositories, serves as a contamination control for agent pretraining data concerns. --- ### O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Embodied Intelligent Robotics Authors: Mengfei Duan, Hao Shi, Fei Teng, Guoqiang Zhao, Yuheng Zhang, Zhiyong Li, Kailun Yang Published: 2026-03-12 Categories: cs.CV, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2603.12144v5 The rapid evolution of consumer electronics toward embodied intelligence has accelerated the emergence of Consumer Embodied Intelligent Robotics (CEIRs), where intelligent devices are expected to perceive, understand, and interact with complex real-world environments. Understanding and reconstructing the 3D world through omnidirectional perception is therefore becoming increasingly important for CEIRs operating in complex and dynamic environments. However, existing vision-based 3D occupancy prediction methods are constrained by limited perspective inputs and a predefined training distribution, making them difficult to support embodied intelligent systems that require comprehensive and safe perception of scenes in open-world exploration. To address this, we present O3N, the first framework for open-vocabulary occupancy prediction from a single omnidirectional RGB image. O3N embeds omnidirectional voxels in a polar-spiral topology via the Polar-spiral Mamba (PsM) module, enabling continuous spatial representation and long-range context modeling across 360°. The Occupancy Cost Aggregation (OCA) module introduces a principled mechanism for unifying geometric and semantic supervision within the voxel space, ensuring consistency between reconstructed geometry and underlying semantic structure. Moreover, Natural Modality Alignment (NMA) establishes a gradient-free alignment pathway that harmonizes visual features, voxel embeddings, and text semantics, forming a consistent pixel-voxel-text representation triad for open-world perception. Extensive experiments on multiple models demonstrate that our method not only achieves state-of-the-art performance on QuadOcc and Human360Occ benchmarks but also exhibits remarkable cross-scene generalization and semantic scalability. The source code will be made publicly available at https://github.com/MengfeiD/O3N. --- ### O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Urban Autonomous Agents Authors: Mengfei Duan, Hao Shi, Fei Teng, Guoqiang Zhao, Yuheng Zhang, Zhiyong Li, Kailun Yang Published: 2026-03-12 Categories: cs.CV, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2603.12144v4 Understanding and reconstructing the 3D world through omnidirectional perception is becoming increasingly important for intelligent transportation and urban autonomous agents operating in shared spaces. However, existing vision-based 3D occupancy prediction methods are constrained by limited perspective inputs and a predefined training distribution, making them difficult to apply to embodied agents that require comprehensive and safe perception of scenes in open-world exploration. To address this, we present O3N, the first framework for open-vocabulary occupancy prediction from a single omnidirectional RGB image. O3N embeds omnidirectional voxels in a polar-spiral topology via the Polar-spiral Mamba (PsM) module, enabling continuous spatial representation and long-range context modeling across 360°. The Occupancy Cost Aggregation (OCA) module introduces a principled mechanism for unifying geometric and semantic supervision within the voxel space, ensuring consistency between the reconstructed geometry and the underlying semantic structure. Moreover, Natural Modality Alignment (NMA) establishes a gradient-free alignment pathway that harmonizes visual features, voxel embeddings, and text semantics, forming a consistent ``pixel-voxel-text'' representation triad. Extensive experiments on multiple models demonstrate that our method not only achieves state-of-the-art performance on QuadOcc and Human360Occ benchmarks but also exhibits remarkable cross-scene generalization and semantic scalability, highlighting the potential of O3N for scalable open-world 3D scene understanding. The source code will be made publicly available at https://github.com/MengfeiD/O3N --- ### HATS: Hardness-Aware Trajectory Synthesis for GUI Agents Authors: Rui Shao, Ruize Gao, Bin Xie, Yixing Li, Kaiwen Zhou, Shuai Wang, Weili Guan, Gongwei Chen Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12138v1 Graphical user interface (GUI) agents powered by large vision-language models (VLMs) have shown remarkable potential in automating digital tasks, highlighting the need for high-quality trajectory data to support effective agent training. Yet existing trajectory synthesis pipelines often yield agents that fail to generalize beyond simple interactions. We identify this limitation as stemming from the neglect of semantically ambiguous actions, whose meanings are context-dependent, sequentially dependent, or visually ambiguous. Such actions are crucial for real-world robustness but are under-represented and poorly processed in current datasets, leading to semantic misalignment between task instructions and execution. To address these issues, we propose HATS, a Hardness-Aware Trajectory Synthesis framework designed to mitigate the impact of semantic ambiguity. We define hardness as the degree of semantic ambiguity associated with an action and develop two complementary modules: (1) hardness-driven exploration, which guides data collection toward ambiguous yet informative interactions, and (2) alignment-guided refinement, which iteratively validates and repairs instruction-execution alignment. The two modules operate in a closed loop: exploration supplies refinement with challenging trajectories, while refinement feedback updates the hardness signal to guide future exploration. Extensive experiments show that agents trained with HATS consistently outperform state-of-the-art baselines across benchmark GUI environments. --- ### TopoBench: Benchmarking LLMs on Hard Topological Reasoning Authors: Mayug Maniparambil, Nils Hoehing, Janak Kapuriya, Arjun Karuvally, Ellen Rushe, Anthony Ventresque, Noel O'Connor, Fergal Reid Published: 2026-03-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.12133v1 Solving topological grid puzzles requires reasoning over global spatial invariants such as connectivity, loop closure, and region symmetry and remains challenging for even the most powerful large language models (LLMs). To study these abilities under controlled settings, we introduce TopoBench, a benchmark of six puzzle families across three difficulty levels. We evaluate strong reasoning LLMs on TopoBench and find that even frontier models solve fewer than one quarter of hard instances, with two families nearly unsolved. To investigate whether these failures stem from reasoning limitations or from difficulty extracting and maintaining spatial constraints, we annotate 750 chain of thought traces with an error taxonomy that surfaces four candidate causal failure modes, then test them with targeted interventions simulating each error type. These interventions show that certain error patterns like premature commitment and constraint forgetting have a direct impact on the ability to solve the puzzle, while repeated reasoning is a benign effect of search. Finally we study mitigation strategies including prompt guidance, cell-aligned grid representations and tool-based constraint checking, finding that the bottleneck lies in extracting constraints from spatial representations and not in reasoning over them. Code and data are available at github.com/mayug/topobench-benchmark. --- ### Increasing intelligence in AI agents can worsen collective outcomes Authors: Neil F. Johnson Published: 2026-03-12 Categories: cs.AI, cs.CY, cs.SI, econ.GN, physics.soc-ph arXiv: https://arxiv.org/abs/2603.12129v1 When resources are scarce, will a population of AI agents coordinate in harmony, or descend into tribal chaos? Diverse decision-making AI from different developers is entering everyday devices -- from phones and medical devices to battlefield drones and cars -- and these AI agents typically compete for finite shared resources such as charging slots, relay bandwidth, and traffic priority. Yet their collective dynamics and hence risks to users and society are poorly understood. Here we study AI-agent populations as the first system of real agents in which four key variables governing collective behaviour can be independently toggled: nature (innate LLM diversity), nurture (individual reinforcement learning), culture (emergent tribe formation), and resource scarcity. We show empirically and mathematically that when resources are scarce, AI model diversity and reinforcement learning increase dangerous system overload, though tribe formation lessens this risk. Meanwhile, some individuals profit handsomely. When resources are abundant, the same ingredients drive overload to near zero, though tribe formation makes the overload slightly worse. The crossover is arithmetical: it is where opposing tribes that form spontaneously first fit inside the available capacity. More sophisticated AI-agent populations are not better: whether their sophistication helps or harms depends entirely on a single number -- the capacity-to-population ratio -- that is knowable before any AI-agent ships. --- ### Hoi3DGen: Generating High-Quality Human-Object-Interactions in 3D Authors: Agniv Sharma, Xianghui Xie, Tom Fischer, Eddy Ilg, Gerard Pons-Moll Published: 2026-03-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.12126v1 Modeling and generating 3D human-object interactions from text is crucial for applications in AR, XR, and gaming. Existing approaches often rely on score distillation from text-to-image models, but their results suffer from the Janus problem and do not follow text prompts faithfully due to the scarcity of high-quality interaction data. We introduce Hoi3DGen, a framework that generates high-quality textured meshes of human-object interaction that follow the input interaction descriptions precisely. We first curate realistic and high-quality interaction data leveraging multimodal large language models, and then create a full text-to-3D pipeline, which achieves orders-of-magnitude improvements in interaction fidelity. Our method surpasses baselines by 4-15x in text consistency and 3-7x in 3D model quality, exhibiting strong generalization to diverse categories and interaction types, while maintaining high-quality 3D generation. --- ### Cross-Context Review: Improving LLM Output Quality by Separating Production and Review Sessions Authors: Tae-Eun Song Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12123v1 Large language models struggle to catch errors in their own outputs when the review happens in the same session that produced them. This paper introduces Cross-Context Review (CCR), a straightforward method where the review is conducted in a fresh session with no access to the production conversation history. We ran a controlled experiment: 30 artifacts (code, technical documents, presentation scripts) with 150 injected errors, tested under four review conditions -- same-session Self-Review (SR), repeated Self-Review (SR2), context-aware Subagent Review (SA), and Cross-Context Review (CCR). Over 360 reviews, CCR reached an F1 of 28.6%, outperforming SR (24.6%, p=0.008, d=0.52), SR2 (21.7%, p<0.001, d=0.72), and SA (23.8%, p=0.004, d=0.57). The SR2 result matters most for interpretation: reviewing twice in the same session did not beat reviewing once (p=0.11), which rules out repetition as an explanation for CCR's advantage. The benefit comes from context separation itself. CCR works with any model, needs no infrastructure, and costs only one extra session. --- ### CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance Authors: Leo Lin, Shivansh Patel, Jay Moon, Svetlana Lazebnik, Unnat Jain Published: 2026-03-12 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.12120v2 We introduce CRAFT hand, a tendon-driven anthropomorphic hand with hybrid hard-soft compliance for contact-rich manipulation. The design is based on a simple idea: contact is not uniform across the hand. Impacts concentrate at joints, while links carry most of the load. CRAFT places soft material at joints and keeps links rigid, and uses rollingcontact joint surfaces to keep flexion on repeatable motion paths. Fifteen motors mounted on the fingers drive the hand through tendons, keeping the form factor compact and the fingers light. In structural tests, CRAFT improves strength and endurance while maintaining comparable repeatability. In teleoperation, CRAFT improves handling of fragile and low-friction items, and the hand covers 33/33 grasps in the Feix taxonomy. The full design costs under $600 and will be released open-source with visionbased teleoperation and simulation integration. Project page: http://craft-hand.github.io/ --- ### Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models Authors: Jae-Won Chung, Jeff J. Ma, Jisang Ahn, Yizhuo Liang, Akshay Jajoo, Myungjin Lee, Mosharaf Chowdhury Published: 2026-03-12 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2603.12118v2 Any-to-Any models are an emerging class of multimodal models that accept combinations of multimodal data (e.g., text, image, video, audio) as input and generate them as output. Serving these models are challenging; different requests with different input and output modalities traverse different paths through the model computation graph, and each component of the model have different scaling characteristics. We present Cornserve, a distributed serving system for generic Any-to-Any models. Cornserve provides a flexible task abstraction for expressing Any-to-Any model computation graphs, enabling component disaggregation and independent scaling. The distributed runtime dispatches compute to the data plane via an efficient record-and-replay execution model that keeps track of data dependencies, and forwards tensor data between components directly from the producer to the consumer. Built on Kubernetes with approximately 23K new lines of Python, Cornserve supports diverse Any-to-Any models and delivers up to 3.81$\times$ higher throughput and 5.79$\times$ lower tail latency. Cornserve is open-source, and the demo video is available on YouTube. --- ### SommBench: Assessing Sommelier Expertise of Language Models Authors: William Brach, Tomas Bedej, Jacob Nielsen, Jacob Pichna, Juraj Bedej, Eemeli Saarensilta, Julie Dupouy, Gianluca Barmina, Andrea Blasi Núñez, Peter Schneider-Kamp, Kristian Košťál, Michal Ries et al. Published: 2026-03-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.12117v1 With the rapid advances of large language models, it becomes increasingly important to systematically evaluate their multilingual and multicultural capabilities. Previous cultural evaluation benchmarks focus mainly on basic cultural knowledge that can be encoded in linguistic form. Here, we propose SommBench, a multilingual benchmark to assess sommelier expertise, a domain deeply grounded in the senses of smell and taste. While language models learn about sensory properties exclusively through textual descriptions, SommBench tests whether this textual grounding is sufficient to emulate expert-level sensory judgment. SommBench comprises three main tasks: Wine Theory Question Answering (WTQA), Wine Feature Completion (WFC), and Food-Wine Pairing (FWP). SommBench is available in multiple languages: English, Slovak, Swedish, Finnish, German, Danish, Italian, and Spanish. This helps separate a language model's wine expertise from its language skills. The benchmark datasets were developed in close collaboration with a professional sommelier and native speakers of the respective languages, resulting in 1,024 wine theory question-answering questions, 1,000 wine feature-completion examples, and 1,000 food-wine pairing examples. We provide results for the most popular language models, including closed-weights models such as Gemini 2.5, and open-weights models, such as GPT-OSS and Qwen 3. Our results show that the most capable models perform well on wine theory question answering (up to 97% correct with a closed-weights model), yet feature completion (peaking at 65%) and food-wine pairing show (MCC ranging between 0 and 0.39) turn out to be more challenging. These results position SommBench as an interesting and challenging benchmark for evaluating the sommelier expertise of language models. The benchmark is publicly available at https://github.com/sommify/sommbench. --- ### Taming the Adversary: A Cost-to-Disturbance Ratio Approach to Adversarial Reinforcement Learning Authors: Taeho Lee, Donghwan Lee Published: 2026-03-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.12110v2 Reinforcement learning (RL) policies trained in simulation often degrade once deployed on real systems, where the controller must reject external disturbances that were never encountered in simulation. Robust RL addresses this by exposing the controller to perturbations while it learns, through domain randomization, adversarial minimax formulations, or probabilistic mixtures of protagonist and adversarial behavior. However, an unregulated disturbance mechanism destabilizes training and often collapses nominal performance relative to standard, non-robust methods. We propose cost-to-disturbance ratio adversarial training (CoDRA), a framework that expresses the controller--adversary trade-off as a ratio of accumulated cost to accumulated squared disturbance norm, and optimizes it through a self-normalized actor--critic update. In this algorithm, each value term is scaled by a stop-gradient normalization constant computed from the current batch. This moderates the adversary's incentive without altering the controller's own update, and requires neither an explicit disturbance penalty nor an auxiliary trade-off parameter. We evaluate CoDRA on two MuJoCo pendulum environments under force and mass sweeps. On InvertedDoublePendulum, CoDRA attains the lowest cost at every force level, including a force outside the range seen during training, and in all but one cell of the mass grid, whereas its advantage is less pronounced on the milder InvertedPendulum. --- ### Taming the Adversary: Stable Minimax Deep Deterministic Policy Gradient via Fractional Objectives Authors: Taeho Lee, Donghwan Lee Published: 2026-03-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.12110v1 Reinforcement learning (RL) has achieved remarkable success in a wide range of control and decision-making tasks. However, RL agents often exhibit unstable or degraded performance when deployed in environments subject to unexpected external disturbances and model uncertainties. Consequently, ensuring reliable performance under such conditions remains a critical challenge. In this paper, we propose minimax deep deterministic policy gradient (MMDDPG), a framework for learning disturbance-resilient policies in continuous control tasks. The training process is formulated as a minimax optimization problem between a user policy and an adversarial disturbance policy. In this problem, the user learns a robust policy that minimizes the objective function, while the adversary generates disturbances that maximize it. To stabilize this interaction, we introduce a fractional objective that balances task performance and disturbance magnitude. This objective prevents excessively aggressive disturbances and promotes robust learning. Experimental evaluations in MuJoCo environments demonstrate that the proposed MMDDPG achieves significantly improved robustness against both external force perturbations and model parameter variations. --- ### On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents Authors: Deyu Zou, Yongqiang Chen, Fan Feng, Mufei Li, Pan Li, Yu Gong, James Cheng Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.12109v2 Reinforcement learning (RL) has become a de facto paradigm for building LLM-based agents that act, interact, and reason over extended task horizons. However, in active reasoning where agents must elicit new observations through interaction with the environment to solve the task, we find that outcome-based RL can induce a systematic failure mode which we call information self-locking (SeL): agents fail both to elicit informative feedback and to internalize obtained evidence. To understand the issue, we trace agentic behaviors into two coupled capabilities: Action Selection (AS), which determines observation streams, and Belief Tracking (BT), which updates the agent's internal task understanding. Theoretical and empirical analyses reveal a bidirectional bottleneck that leads to SeL: weak BT obscures the credit of informative actions, while weak AS deprives BT of useful evidence. This coupling weakens the learning signal for both capabilities and leads to SeL. To mitigate this issue, we propose AREW, a simple yet effective Advantage Reweighting method that uses easy-to-obtain directional critiques to reallocate credit within trajectories. Extensive experiments across 9 agentic tasks of varying complexity show that AREW significantly mitigates SeL, yielding up to 60-point gains in final performance. Code is available at https://github.com/unimpor/T3. --- ### EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation Authors: Yan Li, Ning Liao, Xiangyu Zhao, Shaofeng Zhang, Xiaoxing Wang, Yifan Yang, Junchi Yan, Xue Yang Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12108v1 The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding requires high-level semantic abstractions, while image generation demands fine-grained pixel-level representations. Existing approaches usually enforce the two supervision on the same set of representation or decouple these two supervision on separate feature spaces, leading to interference and inconsistency, respectively. In this work, we propose EvoTok, a unified image tokenizer that reconciles these requirements through a residual evolution process within a shared latent space. Instead of maintaining separate token spaces for pixels and semantics, EvoTok encodes an image into a cascaded sequence of residual tokens via residual vector quantization. This residual sequence forms an evolution trajectory where earlier stages capture low-level details and deeper stages progressively transition toward high-level semantic representations. Despite being trained on a relatively modest dataset of 13M images, far smaller than the billion-scale datasets used by many previous unified tokenizers, EvoTok achieves a strong reconstruction quality of 0.43 rFID on ImageNet-1K at 256x256 resolution. When integrated with a large language model, EvoTok shows promising performance across 7 out of 9 visual understanding benchmarks, and remarkable results on image generation benchmarks such as GenEval and GenAI-Bench. These results demonstrate that modeling visual representations as an evolving trajectory provides an effective and principled solution for unifying visual understanding and generation. --- ### To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Times Authors: Thomas Hikaru Clark, Carlos Arriaga, Javier Conde, Gonzalo Martínez, Pedro Reviriego Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12105v1 Large Language Models (LLMs) have recently been shown to produce estimates of psycholinguistic norms, such as valence, arousal, or concreteness, for words and multiword expressions, that correlate with human judgments. These estimates are obtained by prompting an LLM, in zero-shot fashion, with a question similar to those used in human studies. Meanwhile, for other norms such as lexical decision time or age of acquisition, LLMs require supervised fine-tuning to obtain results that align with ground-truth values. In this paper, we extend this approach to the previously unstudied features of sentence memorability and reading times, which involve the relationship between multiple words in a sentence-level context. Our results show that via fine-tuning, models can provide estimates that correlate with human-derived norms and exceed the predictive power of interpretable baseline predictors, demonstrating that LLMs contain useful information about sentence-level features. At the same time, our results show very mixed zero-shot and few-shot performance, providing further evidence that care is needed when using LLM-prompting as a proxy for human cognitive measures. --- ### Wasserstein Gradient Flows for Batch Bayesian Optimal Experimental Design Authors: Louis Sharrock Published: 2026-03-12 Categories: stat.ML, cs.LG, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2603.12102v1 Bayesian optimal experimental design (BOED) provides a powerful, decision-theoretic framework for selecting experiments so as to maximise the expected utility of the data to be collected. In practice, however, its applicability can be limited by the difficulty of optimising the chosen utility. The expected information gain (EIG), for example, is often high-dimensional and strongly non-convex. This challenge is particularly acute in the batch setting, where multiple experiments are to be designed simultaneously. In this paper, we introduce a new approach to batch EIG-based BOED via a probabilistic lifting of the original optimisation problem to the space of probability measures. In particular, we propose to optimise an entropic regularisation of the expected utility over the space of design measures. Under mild conditions, we show that this objective admits a unique minimiser, which can be explicitly characterised in the form of a Gibbs distribution. The resulting design law can be used directly as a randomised batch-design policy, or as a computational relaxation from which a deterministic batch is extracted. To obtain scalable approximations when the batch size is large, we then consider two tractable restrictions of the full batch distribution: a mean-field family, and an i.i.d. product family. For the i.i.d. objective, and formally for its mean-field extension, we derive the corresponding Wasserstein gradient flow, characterise its long-time behaviour, and obtain particle-based algorithms via space-time discretisations. We also introduce doubly stochastic variants that combine interacting particle updates with Monte Carlo estimators of the EIG gradient. Finally, we illustrate the performance of the proposed methods in several numerical experiments, demonstrating their ability to explore multimodal optimisation landscapes and obtain high-utility batches in challenging examples. --- ### A Robust and Efficient Multi-Agent Reinforcement Learning Framework for Traffic Signal Control Authors: Sheng-You Huang, Hsiao-Chuan Chang, Yen-Chi Chen, Ting-Han Wei, I-Hau Yeh, Sheng-Yao Kuan, Chien-Yao Wang, Hsuan-Han Lee, I-Chen Wu Published: 2026-03-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.12096v1 Reinforcement Learning (RL) in Traffic Signal Control (TSC) faces significant hurdles in real-world deployment due to limited generalization to dynamic traffic flow variations. Existing approaches often overfit static patterns and use action spaces incompatible with driver expectations. This paper proposes a robust Multi-Agent Reinforcement Learning (MARL) framework validated in the Vissim traffic simulator. The framework integrates three mechanisms: (1) Turning Ratio Randomization, a training strategy that exposes agents to dynamic turning probabilities to enhance robustness against unseen scenarios; (2) a stability-oriented Exponential Phase Duration Adjustment action space, which balances responsiveness and precision through cyclical, exponential phase adjustments; and (3) a Neighbor-Based Observation scheme utilizing the MAPPO algorithm with Centralized Training with Decentralized Execution (CTDE). By leveraging centralized updates, this approach approximates the efficacy of global observations while maintaining scalable local communication. Experimental results demonstrate that our framework outperforms standard RL baselines, reducing average waiting time by over 10%. The proposed model exhibits superior generalization in unseen traffic scenarios and maintains high control stability, offering a practical solution for adaptive signal control. --- ### Human-Centred LLM Privacy Audits: Findings and Frictions Authors: Dimitri Staufer, Kirsten Morehouse, David Hartmann, Bettina Berendt Published: 2026-03-12 Categories: cs.HC, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.12094v1 Large language models (LLMs) learn statistical associations from massive training corpora and user interactions, and deployed systems can surface or infer information about individuals. Yet people lack practical ways to inspect what a model associates with their name. We report interim findings from an ongoing study and introduce LMP2, a browser-based self-audit tool. In two user studies ($N_{total}{=}458$), GPT-4o predicts 11 of 50 features for everyday people with $\ge$60\% accuracy, and participants report wanting control over LLM-generated associations despite not considering all outputs privacy violations. To validate our probing method, we evaluate eight LLMs on public figures and non-existent names, observing clear separation between stable name-conditioned associations and model defaults. Our findings also contribute to exposing a broader generative AI evaluation crisis: when outputs are probabilistic, context-dependent, and user-mediated through elicitation, what model--individual associations even include is under-specified and operationalisation relies on crafting probes and metrics that are hard to validate or compare. To move towards reliable, actionable human-centred LLM privacy audits, we identify nine frictions that emerged in our study and offer recommendations for future work and the design of human-centred LLM privacy audits. --- ### Resource-Efficient Iterative LLM-Based NAS with Feedback Memory Authors: Xiaojie Gu, Dmitry Ignatov, Radu Timofte Published: 2026-03-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.12091v1 Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources. We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures for image classification on a single consumer-grade GPU without LLM fine-tuning. Central to our approach is a historical feedback memory inspired by Markov chains: a sliding window of $K{=}5$ recent improvement attempts keeps context size constant while providing sufficient signal for iterative learning. Unlike prior LLM optimizers that discard failure trajectories, each history entry is a structured diagnostic triple -- recording the identified problem, suggested modification, and resulting outcome -- treating code execution failures as first-class learning signals. A dual-LLM specialization reduces per-call cognitive load: a Code Generator produces executable PyTorch architectures while a Prompt Improver handles diagnostic reasoning. Since both the LLM and architecture training share limited VRAM, the search implicitly favors compact, hardware-efficient models suited to edge deployment. We evaluate three frozen instruction-tuned LLMs (${\leq}7$B parameters) across up to 2000 iterations in an unconstrained open code space, using one-epoch proxy accuracy on CIFAR-10, CIFAR-100, and ImageNette as a fast ranking signal. On CIFAR-10, DeepSeek-Coder-6.7B improves from 28.2% to 69.2%, Qwen2.5-7B from 50.0% to 71.5%, and GLM-5 from 43.2% to 62.0%. A full 2000-iteration search completes in ${\approx}18$ GPU hours on a single RTX~4090, establishing a low-budget, reproducible, and hardware-aware paradigm for LLM-driven NAS without cloud infrastructure. --- ### Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Critics Authors: Ming-Hong Chen, Kuan-Chen Pan, You-De Huang, Xi Liu, Ping-Chun Hsieh Published: 2026-03-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.12087v1 Cross-domain reinforcement learning (CDRL) is meant to improve the data efficiency of RL by leveraging the data samples collected from a source domain to facilitate the learning in a similar target domain. Despite its potential, cross-domain transfer in RL is known to have two fundamental and intertwined challenges: (i) The source and target domains can have distinct state space or action space, and this makes direct transfer infeasible and thereby requires more sophisticated inter-domain mappings; (ii) The transferability of a source-domain model in RL is not easily identifiable a priori, and hence CDRL can be prone to negative effect during transfer. In this paper, we propose to jointly tackle these two challenges through the lens of \textit{cross-domain Bellman consistency} and \textit{hybrid critic}. Specifically, we first introduce the notion of cross-domain Bellman consistency as a way to measure transferability of a source-domain model. Then, we propose $Q$Avatar, which combines the Q functions from both the source and target domains with an adaptive hyperparameter-free weight function. Through this design, we characterize the convergence behavior of $Q$Avatar and show that $Q$Avatar achieves reliable transfer in the sense that it effectively leverages a source-domain Q function for knowledge transfer to the target domain. Through experiments, we demonstrate that $Q$Avatar achieves favorable transferability across various RL benchmark tasks, including locomotion and robot arm manipulation. Our code is available at https://rl-bandits-lab.github.io/Cross-Domain-RL/. --- ### Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis Authors: Xiaolong Qian, Qi Jiang, Yao Gao, Lei Sun, Zhonghua Yi, Kailun Yang, Luc Van Gool, Kaiwei Wang Published: 2026-03-12 Categories: cs.CV, cs.RO, eess.IV, physics.optics arXiv: https://arxiv.org/abs/2603.12083v1 Prevalent Computational Aberration Correction (CAC) methods are typically tailored to specific optical systems, leading to poor generalization and labor-intensive re-training for new lenses. Developing CAC paradigms capable of generalizing across diverse photographic lenses offers a promising solution to these challenges. However, efforts to achieve such cross-lens universality within consumer photography are still in their early stages due to the lack of a comprehensive benchmark that encompasses a sufficiently wide range of optical aberrations. Furthermore, it remains unclear which specific factors influence existing CAC methods and how these factors affect their performance. In this paper, we present comprehensive experiments and evaluations involving 24 image restoration and CAC algorithms, utilizing our newly proposed UniCAC, a large-scale benchmark for photographic cameras constructed via automatic optical design. The Optical Degradation Evaluator (ODE) is introduced as a novel framework to objectively assess the difficulty of CAC tasks, offering credible quantification of optical aberrations and enabling reliable evaluation. Drawing on our comparative analysis, we identify three key factors -- prior utilization, network architecture, and training strategy -- that most significantly influence CAC performance, and further investigate their respective effects. We believe that our benchmark, dataset, and observations contribute foundational insights to related areas and lay the groundwork for future investigations. Benchmarks, codes, and Zemax files will be available at https://github.com/XiaolongQian/UniCAC. --- ### Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs Authors: Hiran Sarkar, Liming Kuang, Yordanka Velikova, Benjamin Busam Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12078v2 Predicting scene dynamics from visual observations is challenging. Existing methods capture dynamics only within observed boundaries failing to extrapolate far beyond the training sequence. Node-RF (Neural ODE-based NeRF) overcomes this limitation by integrating Neural Ordinary Differential Equations (NODEs) with dynamic Neural Radiance Fields (NeRFs), enabling a continuous-time, spatiotemporal representation that generalizes beyond observed trajectories at constant memory cost. From visual input, Node-RF learns an implicit scene state that evolves over time via an ODE solver, propagating feature embeddings via differential calculus. A NeRF-based renderer interprets calculated embeddings to synthesize arbitrary views for long-range extrapolation. Training on multiple motion sequences with shared dynamics allows for generalization to unseen conditions. Our experiments demonstrate that Node-RF can characterize abstract system behavior without explicit model to identify critical points for future predictions. --- ### A Multi-Label Temporal Convolutional Framework for Transcription Factor Binding Characterization Authors: Pietro Demurtas, Ferdinando Zanchetta, Giovanni Perini, Rita Fioresi Published: 2026-03-12 Categories: cs.LG, cs.AI, q-bio.GN arXiv: https://arxiv.org/abs/2603.12073v1 Transcription factors (TFs) regulate gene expression through complex and co-operative mechanisms. While many TFs act together, the logic underlying TFs binding and their interactions is not fully understood yet. Most current approaches for TF binding site prediction focus on individual TFs and binary classification tasks, without a full analysis of the possible interactions among various TFs. In this paper we investigate DNA TF binding site recognition as a multi-label classification problem, achieving reliable predictions for multiple TFs on DNA sequences retrieved in public repositories. Our deep learning models are based on Temporal Convolutional Networks (TCNs), which are able to predict multiple TF binding profiles, capturing correlations among TFs andtheir cooperative regulatory mechanisms. Our results suggest that multi-label learning leading to reliable predictive performances can reveal biologically meaningful motifs and co-binding patterns consistent with known TF interactions, while also suggesting novel relationships and cooperation among TFs. --- ### LoV3D: Grounding Cognitive Prognosis Reasoning in Longitudinal 3D Brain MRI via Regional Volume Assessments Authors: Zhaoyang Jiang, Zhizhong Fu, David McAllister, Yunsoo Kim, Honghan Wu Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12071v2 Longitudinal brain MRI is essential for characterizing the progression of neurological diseases such as Alzheimer's disease assessment. However, current deep-learning tools fragment this process: classifiers reduce a scan to a label, volumetric pipelines produce uninterpreted measurements, and vision-language models (VLMs) may generate fluent but potentially hallucinated conclusions. We present LoV3D, a pipeline for training 3D vision-language models, which reads longitudinal T1-weighted brain MRI, produces a region-level anatomical assessment, conducts longitudinal comparison with the prior scan, and finally outputs a three-class diagnosis (Cognitively Normal, Mild Cognitive Impairment, or Dementia) along with a synthesized diagnostic summary. The stepped pipeline grounds the final diagnosis by enforcing label consistency, longitudinal coherence, and biological plausibility, thereby reducing the risks of hallucinations. The training process introduces a clinically-weighted Verifier that scores candidate outputs automatically against normative references derived from standardized volume metrics, driving Direct Preference Optimization without a single human annotation. On a subject-level held-out ADNI test set (479 scans, 258 subjects), LoV3D achieves 93.7% three-class diagnostic accuracy (+34.8% over the no-grounding baseline), 97.2% on two-class diagnosis accuracy (+4% over the SOTA) and 82.6% region-level anatomical classification accuracy (+33.1% over VLM baselines). Zero-shot transfer yields 95.4% on MIRIAD (100% Dementia recall) and 82.9% three-class accuracy on AIBL, confirming high generalizability across sites, scanners, and populations. Code is available at https://github.com/Anonymous-TEVC/LoV-3D. --- ### Beyond Convolution: A Taxonomy of Structured Operators for Learning-Based Image Processing Authors: Simone Cammarasana Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12067v2 The convolution operator is the fundamental building block of modern convolutional neural networks (CNNs), owing to its simplicity, translational equivariance, and efficient implementation. However, its structure as a fixed, linear, locally-averaging operator limits its ability to capture structured signal properties such as low-rank decompositions, adaptive basis representations, and non-uniform spatial dependencies. This paper presents a systematic taxonomy of operators that extend or replace the standard convolution in learning-based image processing pipelines. We organise the landscape of alternative operators into five families: (i) decomposition-based operators, which separate structural and noise components through singular value or tensor decompositions; (ii) adaptive weighted operators, which modulate kernel contributions as a function of spatial position or signal content; (iii) basis-adaptive operators, which optimise the analysis bases together with the network weights; (iv) integral and kernel operators, which generalise the convolution to position-dependent and non-linear kernels; and (v) attention-based operators, which relax the locality assumption entirely. For each family, we provide a formal definition, a discussion of its structural properties with respect to the convolution, and a critical analysis of the tasks for which the operator is most appropriate. We further provide a comparative analysis of all families across relevant dimensions -- linearity, locality, equivariance, computational cost, and suitability for image-to-image and image-to-label tasks -- and outline the open challenges and future directions of this research area. --- ### Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos Authors: Shuo Sun, Unal Artan, Malcolm Mielle, Achim J. Lilienthaland, Martin Magnusson Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12064v3 We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting that arises naturally when multiple observers capture a shared event. Prior approaches either handle only single-camera input or require rigidly mounted, pre-calibrated camera rigs, limiting their practical applicability. We propose a two-stage optimization framework that decouples the task into robust camera tracking and dense depth refinement. In the first stage, we extend single-camera visual SLAM to the multi-camera setting by constructing a spatiotemporal connection graph that exploits both intra-camera temporal continuity and inter-camera spatial overlap, enabling consistent scale and robust tracking. To ensure robustness under limited overlap, we introduce a wide-baseline initialization strategy using feed-forward reconstruction models. In the second stage, we refine depth and camera poses by optimizing dense inter- and intra-camera consistency using wide-baseline optical flow. Additionally, we introduce MultiCamRobolab, a new real-world dataset with ground-truth poses from a motion capture system. Finally, we demonstrate that our method significantly outperforms state-of-the-art feed-forward models on both synthetic and real-world benchmarks, while requiring less memory. --- ### Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos Authors: Shuo Sun, Unal Artan, Malcolm Mielle, Achim J. Lilienthaland, Martin Magnusson Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12064v2 We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting that arises naturally when multiple observers capture a shared event. Prior approaches either handle only single-camera input or require rigidly mounted, pre-calibrated camera rigs, limiting their practical applicability. We propose a two-stage optimization framework that decouples the task into robust camera tracking and dense depth refinement. In the first stage, we extend single-camera visual SLAM to the multi-camera setting by constructing a spatiotemporal connection graph that exploits both intra-camera temporal continuity and inter-camera spatial overlap, enabling consistent scale and robust tracking. To ensure robustness under limited overlap, we introduce a wide-baseline initialization strategy using feed-forward reconstruction models. In the second stage, we refine depth and camera poses by optimizing dense inter- and intra-camera consistency using wide-baseline optical flow. Additionally, we introduce MultiCamRobolab, a new real-world dataset with ground-truth poses from a motion capture system. Finally, we demonstrate that our method significantly outperforms state-of-the-art feed-forward models on both synthetic and real-world benchmarks, while requiring less memory. --- ### NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction Authors: David Svitov, Mahtab Dahaghin, Pietro Morerio, Alessio Del Bue Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12063v2 We present NBAvatar - a method for realistic rendering of head avatars handling non-rigid deformations caused by hand-face interaction. To this end, we introduce a novel hybrid implicit-explicit representation for animated avatars by combining the training of explicit oriented planar primitives with implicit neural rendering. Such a combination of representations in the end-to-end pipeline enables NBAvatar to handle temporally and pose-consistent geometry, along with fine-grained appearance details provided by the neural rendering technique. To enable joint optimization of different representations we propose a geometry-aware training scheme that allows our hybrid representation to surpass existing approaches in terms of novel-view and novel-pose rendering quality. Specifically, NBAvatar achieves up to 53% LPIPS reduction compared to Gaussian-based avatar methods, while also improving PSNR and SSIM, and achieves higher structural similarity compared to the state-of-the-art hand-face interaction method InteractAvatar. --- ### NBAvatar: Neural Billboards Avatars with Realistic Hand-Face Interaction Authors: David Svitov, Mahtab Dahaghin Published: 2026-03-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.12063v1 We present NBAvatar - a method for realistic rendering of head avatars handling non-rigid deformations caused by hand-face interaction. We introduce a novel representation for animated avatars by combining the training of oriented planar primitives with neural rendering. Such a combination of explicit and implicit representations enables NBAvatar to handle temporally and pose-consistent geometry, along with fine-grained appearance details provided by the neural rendering technique. In our experiments, we demonstrate that NBAvatar implicitly learns color transformations caused by face-hand interactions and surpasses existing approaches in terms of novel-view and novel-pose rendering quality. Specifically, NBAvatar achieves up to 30% LPIPS reduction under high-resolution megapixel rendering compared to Gaussian-based avatar methods, while also improving PSNR and SSIM, and achieves higher structural similarity compared to the state-of-the-art hand-face interaction method InteractAvatar. --- ### Chemical Reaction Networks Learn Better than Spiking Neural Networks Authors: Sophie Jaffard, Ivo F. Sbalzarini Published: 2026-03-12 Categories: cs.LG, cs.AI, math.ST, stat.ML arXiv: https://arxiv.org/abs/2603.12060v1 We mathematically prove that chemical reaction networks without hidden layers can solve tasks for which spiking neural networks require hidden layers. Our proof uses the deterministic mass-action kinetics formulation of chemical reaction networks. Specifically, we prove that a certain reaction network without hidden layers can learn a classification task previously proved to be achievable by a spiking neural network with hidden layers. We provide analytical regret bounds for the global behavior of the network and analyze its asymptotic behavior and Vapnik-Chervonenkis dimension. In a numerical experiment, we confirm the learning capacity of the proposed chemical reaction network for classifying handwritten digits in pixel images, and we show that it solves the task more accurately and efficiently than a spiking neural network with hidden layers. This provides a motivation for machine learning in chemical computers and a mathematical explanation for how biological cells might exhibit more efficient learning behavior within biochemical reaction networks than neuronal networks. --- ### Adaptive Weighted h-Transform Sampling for Coarse-Guided Visual Generation Authors: Yanghao Wang, Ziqi Jiang, Zhen Wang, Long Chen Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12057v3 Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently limited by high training costs and restricted generalization due to paired data collection. Accordingly, recent training-free works propose to leverage pretrained diffusion models and incorporate guidance during the sampling process. However, these training-free methods either require knowing the forward (fine-to-coarse) transformation operator, e.g., bicubic downsampling, or are difficult to balance between guidance and synthetic quality. To address these challenges, we propose a novel guided method by using the h-transform, a tool that can constrain stochastic processes (e.g., sampling process) under desired conditions. Specifically, we modify the transition probability at each sampling timestep by adding to the original differential equation with a drift function $h$, which approximately steers the generation toward the ideal fine sample. To address unavoidable approximation errors, we introduce an adaptive weight scheduler that combines a noise-level-aware initialization with a correction based on cross-timestep consistency, balancing guidance adherence and synthesis quality. Extensive experiments across diverse image and video generation tasks demonstrate its effectiveness and generalization. --- ### Coarse-Guided Visual Generation via Weighted h-Transform Sampling Authors: Yanghao Wang, Ziqi Jiang, Zhen Wang, Long Chen Published: 2026-03-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.12057v2 Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently limited by high training costs and restricted generalization due to paired data collection. Accordingly, recent training-free works propose to leverage pretrained diffusion models and incorporate guidance during the sampling process. However, these training-free methods either require knowing the forward (fine-to-coarse) transformation operator, e.g., bicubic downsampling, or are difficult to balance between guidance and synthetic quality. To address these challenges, we propose a novel guided method by using the h-transform, a tool that can constrain stochastic processes (e.g., sampling process) under desired conditions. Specifically, we modify the transition probability at each sampling timestep by adding to the original differential equation with a drift function, which approximately steers the generation toward the ideal fine sample. To address unavoidable approximation errors, we introduce a noise-level-aware schedule that gradually de-weights the term as the error increases, ensuring both guidance adherence and high-quality synthesis. Extensive experiments across diverse image and video generation tasks demonstrate the effectiveness and generalization of our method. --- ### XSkill: Continual Learning from Experience and Skills in Multimodal Agents Authors: Guanyu Jiang, Zhaochen Su, Xiaoye Qu, Yi R. Fung Published: 2026-03-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.12056v3 Multimodal agents can now tackle complex reasoning tasks with diverse tools, yet they still suffer from inefficient tool use and inflexible orchestration in open-ended settings. A central challenge is enabling such agents to continually improve without parameter updates by learning from past trajectories. We identify two complementary forms of reusable knowledge essential for this goal: experiences, providing concise action-level guidance for tool selection and decision making, and skills, providing structured task-level guidance for planning and tool use. To this end, we propose XSkill, a dual-stream framework for continual learning from experience and skills in multimodal agents. XSkill grounds both knowledge extraction and retrieval in visual observations. During accumulation, XSkill distills and consolidates experiences and skills from multi-path rollouts via visually grounded summarization and cross-rollout critique. During inference, it retrieves and adapts this knowledge to the current visual context and feeds usage history back into accumulation to form a continual learning loop. Evaluated on five benchmarks across diverse domains with four backbone models, XSkill consistently and substantially outperforms both tool-only and learning-based baselines. Further analysis reveals that the two knowledge streams play complementary roles in influencing the reasoning behaviors of agents and show superior zero-shot generalization. --- ### Continual Learning with Vision-Language Models via Semantic-Geometry Preservation Authors: Chiyuan He, Zihuan Qiu, Fanman Meng, Runtong Zhang, Linfeng Xu, Qingbo Wu, Hongliang Li Published: 2026-03-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.12055v3 Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and previous stages, allowing new-task supervision to induce geometric distortion. We observe that the most pronounced drift tends to concentrate in vulnerable neighborhoods near the old-new semantic interface, where shared visual patterns are easily re-explained by new textual semantics. To address this under an exemplar-free constraint, we propose Semantic Geometry Preservation for Continual Learning (SeGP-CL). SeGP-CL first probes the drift-prone region by constructing a compact set of adversarial anchors with dual-targeted projected gradient descent (DPGD), which drives selected new-task seeds toward old-class semantics while remaining faithful in raw visual space. During training, we preserve cross-modal structure by anchor-guided cross-modal geometry distillation (ACGD), and stabilize the textual reference frame across tasks via a lightweight text semantic-geometry regularization (TSGR). After training, we estimate anchor-induced raw-space drift to transfer old visual prototypes and perform dual-path inference by fusing cross-modal and visual cues. Extensive experiments on five continual learning benchmarks demonstrate that SeGP-CL consistently improves stability and forward transfer, achieving state-of-the-art performance while better preserving semantic geometry of VLMs. Code is available at: https://github.com/chiyuan-IVIPLab/SeGP-CL. --- ### Translationese as a Rational Response to Translation Task Difficulty Authors: Maria Kunilovskaya Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12050v3 Translated texts exhibit systematic differences from comparable texts originally written in the target language. Explaining this phenomenon, commonly known as translationese, remains an open challenge. Translationese has been attributed to production tendencies (e.g. interference, simplification), socio-cultural variables, and language-pair effects, yet a unified explanatory account is lacking. We investigate the hypothesis that translationese is a response to the cognitive load inherent in the translation task. We test whether observable translationese can be predicted from quantifiable measures of translation task difficulty. Translationese is measured as a segment-level probability of being a translation produced by an automatic classifier (translatedness score). Translation task difficulty includes source-text and cross-lingual transfer components. They are captured by information-theoretic metrics based on LLM surprisal and by established syntactic and semantic alternatives. We use a bidirectional English-German corpus comprising written and spoken subcorpora. Results indicate that translationese can only be explained in part by translation task difficulty, especially in the English-to-German direction. For most experiments, cross-lingual transfer difficulty contributes more than source-text complexity. Information-theoretic indicators match or outperform traditional features in written mode, but offer no advantage in spoken mode. Source-text syntactic complexity and translation-solution entropy emerged as the strongest predictors of translationese across language pairs and modes. --- ### Translationese as a Rational Response to Translation Task Difficulty Authors: Maria Kunilovskaya Published: 2026-03-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.12050v2 Translations systematically diverge from texts originally produced in the target language, a phenomenon widely referred to as translationese. Translationese has been attributed to production tendencies (e.g. interference, simplification), socio-cultural variables, and language-pair effects, yet a unified explanatory account is still lacking. We propose that translationese reflects cognitive load inherent in the translation task itself. We test whether observable translationese can be predicted from quantifiable measures of translation task difficulty. Translationese is operationalised as a segment-level translatedness score produced by an automatic classifier. Translation task difficulty is conceptualised as comprising source-text and cross-lingual transfer components, operationalised mainly through information-theoretic metrics based on LLM surprisal, complemented by established syntactic and semantic alternatives. We use a bidirectional English-German corpus comprising written and spoken subcorpora. Results indicate that translationese can be partly explained by translation task difficulty, especially in English-to-German. For most experiments, cross-lingual transfer difficulty contributes more than source-text complexity. Information-theoretic indicators match or outperform traditional features in written mode, but offer no advantage in spoken mode. Source-text syntactic complexity and translation-solution entropy emerged as the strongest predictors of translationese across language pairs and modes. --- ### Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition Authors: Umberto Cappellazzo, Stavros Petridis, Maja Pantic Published: 2026-03-12 Categories: eess.AS, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2603.12046v2 Audio-Visual Speech Recognition (AVSR) leverages both acoustic and visual information for robust recognition under noise. However, how models balance these modalities remains unclear. We present Dr. SHAP-AV, a framework using Shapley values to analyze modality contributions in AVSR. Through experiments on six models across two benchmarks and varying SNR levels, we introduce three analyses: Global SHAP for overall modality balance, Generative SHAP for contribution dynamics during decoding, and Temporal Alignment SHAP for input-output correspondence. Our findings reveal that models shift toward visual reliance under noise yet maintain high audio contributions even under severe degradation. Modality balance evolves during generation, temporal alignment holds under noise, and SNR is the dominant factor driving modality weighting. These findings expose a persistent audio bias, motivating ad-hoc modality-weighting mechanisms and Shapley-based attribution as a standard AVSR diagnostic. --- ### Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability Authors: Xingyu Xie, Zhaochen Yu, Yue Liao, Tao Wang, Kim-Chuan Toh, Shuicheng Yan Published: 2026-03-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.12038v1 Long-context autoregressive decoding remains expensive because each decoding step must repeatedly process a growing history. We observe a consistent pattern during decoding: within a sentence, and more generally within a short semantically coherent span, the dominant attention support often remains largely stable. Motivated by this observation, we propose Slow-Fast Inference (SFI), a training-free decoding framework that decouples generation into frequent low-cost fast steps and occasional dense-attention slow steps. Fast steps reuse a compact sparse memory for efficient decoding. Slow steps are triggered near semantic boundaries. At slow steps, the model revisits the broader context and uses the Selector to refresh the selected memory for subsequent fast steps. Across the evaluated context lengths, SFI delivers approximately $1.6\times$--$14.4\times$ higher decoding throughput while generally maintaining quality on par with the full-KV baseline across long-context and long-CoT settings. Because SFI is training-free and applies directly to existing checkpoints, it offers a practical path to reducing inference cost for contemporary autoregressive reasoning models in long-context, long-horizon, and agentic workloads. ---