# Research Papers — 2026-05 · bundle page 100 of 326 > Full-text markdown of papers #4951–5000 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/100 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/99.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/101.md) ### Preisach Attention: A Hysteretic Model of Sequential Memory Authors: Piotr Frydrych Published: 2026-05-22 Categories: cs.LG, cond-mat.dis-nn, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2605.23603v1 We introduce the Preisach Attention Layer (PAL), a novel sequence modelling architecture grounded in the classical Preisach hysteresis operator from mathematical physics. PAL replaces the softmax attention mechanism with a binary relay operator parameterised by learned activation and deactivation thresholds, maintaining a stack of local extrema as its internal state. A single-layer PAL-Transformer with O(1) depth is Turing-complete under arbitrary precision arithmetic, achievable through simulation of a two-stack pushdown automaton -- in contrast to the O(log n) depth required by standard hard-attention transformers. Second, we prove that the function classes computable by PAL and by the transformer are incomparable: PAL computes historical range statistics in O(1) layers that require O(log n) layers for transformers, while transformers support random-access retrieval that PAL cannot perform without auxiliary state. The separating property is rate-independence -- PAL responds only to the sequence of local extrema, not to absolute token positions or temporal spacing. Third, we show that the extremum stack constitutes a minimal sufficient statistic of the input history for all rate-independent functionals, providing a formal analogue of the wiping property in classical hysteresis theory. PAL is thus an efficient architecture for tasks with long episodic memory and weak positional dependence, with O(n log n) total inference cost versus O(n^2) for standard attention. --- ### GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes Authors: Beibei Lin, Xiao Cao, Jingyuan Guo, Robby T. Tan Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23602v1 Existing 3DGS methods effectively render high-quality novel views in clear-day scenes. However, they struggle with night scenes, particularly in glow regions, due to the lack of structural features such as textures and edges, which are key cues for splatting-based reconstruction. To address this problem, we leverage a diffusion model and a Vision Foundation Model (VFM) to compensate for missing structural cues. Our method consists of two key novel ideas: semantic feature generation and novel-view semantic learning. First, semantic feature generation produces high-quality semantic features as implicit structural cues for novel views. Specifically, a diffusion model synthesizes novel views with unknown camera poses from training views, while a VFM evaluates their quality. Once high-quality novel views are identified, the VFM extracts robust features to construct the semantic feature bank. Second, novel-view semantic learning enables 3DGS to optimize rendered novel views without requiring ground truth. It achieves this by extracting semantic features from a rendered novel view, searching the feature bank for the most similar features, and minimizing their distance. This process enforces implicit structural constraints, ensuring semantically coherent, artifact-free rendered views. Extensive experiments demonstrate the effectiveness of our GlowGS in generating semantically accurate 3D views, showing significant improvements over existing methods. --- ### Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts Authors: Shivam Chourasia, Hitesh Kapoor, Nilesh Patil Published: 2026-05-22 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.23597v1 Matching person names across heterogeneous records is a core challenge in entity resolution, especially within linguistically and culturally complex environments. Variations in naming conventions, inconsistent transliteration across scripts, and frequent data entry errors make it difficult to unify user identities, an essential requirement for Know Your Customer (KYC) compliance. While Large Language Models have shown promise in understanding natural language, they often struggle with the structured ambiguity present in such domain-specific settings. This paper introduces Structure-Guided Entity Resolution (SGER), a novel framework that fine-tunes an LLM through a two-phase curriculum. The model is first trained to parse the grammatical and semantic structure of personal names, then optimized for the downstream task of binary entity matching. We evaluate SGER in the challenging context of Indian identity data, one of the most linguistically diverse and noisy environments globally. SGER achieves 99.02% accuracy and an F1 of 0.994 on a held-out set of 50,000 real-world pairs, outperforming GPT-4o few-shot prompting and single-stage fine-tuning baselines. The system is fully deployed in production at Dream11, the world's largest fantasy sports platform, serving 250M+ users. Our results demonstrate that curriculum-guided training enables robust, high-precision entity resolution in real-world multilingual systems at scale. --- ### Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning Authors: Trinh Pham, Viet Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.CV, cs.ET, cs.PF arXiv: https://arxiv.org/abs/2605.23595v3 The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data. Existing evaluation pipelines typically rely on costly annotation, repeated fine-tuning, or assumptions that do not generalize well to new models. We introduce MetaEvaluator, a cost-effective, model-agnostic framework for fast, label-free evaluation of unseen models across diverse architectures and modalities. MetaEvaluator meta-learns over a pool of reference models to acquire an effective initialization for accurate assessment of unseen models, thereby amortizing evaluation cost and eliminating the need for per-model retraining. To the best of our knowledge, this is the first model-agnostic framework that evaluates new models on unlabeled datasets. Extensive experiments demonstrate that MetaEvaluator delivers stable and accurate performance estimates at substantially lower cost than conventional approaches, enabling scalable benchmarking on unlabeled datasets for emerging models. The code is available at: https://github.com/phkhanhtrinh23/MetaEvaluator. --- ### Solving the Aircraft Disassembly Scheduling Problem Authors: Charles Thomas, Pierre Schaus Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.23592v1 Dismantling aircrafts reaching their end of life is a complex endeavour that is necessary in terms of sustainability but yields small income margins for air transport companies. An efficient scheduling of the disassembly procedure is thus crucial to ensure the profitability of the process and incentivize practice. This is a large scheduling problem that involves thousands of tasks and many different constraints: Extracting parts that are destined to be reused requires technicians with specific certifications and equipment. Extraction operations might be subject to precedence relations. Furthermore, the aircraft must be kept balanced during the whole process. Finally, some of the locations of the aircraft have a limited space that caps the number of technicians able to work there concurrently. This article presents the problem in details and proposes two approaches to solve the problem: a Constraint Programming model and a MIP model. The models are tested on instances of varying sizes involving up to 1450 tasks, which are based on real operational data provided by an industrial partner. --- ### Asymmetric Scaling Laws from Sparse Features Authors: John Sous, Michael Winer Published: 2026-05-22 Categories: stat.ML, cond-mat.dis-nn, cs.LG, math.ST arXiv: https://arxiv.org/abs/2605.23591v1 We introduce a model for neural scaling laws under sparse activations. In the model, test loss is often dominated by rare coordinates that are never observed in the training input. This mechanism induces a novel bottleneck absent from dense models. We derive the asymptotic population loss in both the underparameterized and overparameterized regimes, and show that the loss exhibits a double-descent peak near the interpolation threshold -- where the number of parameters is just sufficient to fit the training data -- resulting in a loss curve governed by two distinct scaling exponents -- one for the overparameterized regime and one for the underparameterized regime -- with a gap determined by the degree of sparsity. Additionally, we derive a compute-optimal frontier that favors increasing dataset size over model capacity under fixed compute budgets. We also analyze gradient-descent dynamics and identify a scaling law for the probability that fixed-step gradient descent becomes unstable. We further show that the sparsity-induced effect persists under nonlinear activations. --- ### Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents Authors: Jiazheng Kang, Bowen Zhang, Zixin Song, Jiangwang Chen, Xiao Yang, Da Zhu, Guanjun Jiang Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.23590v2 ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to take next, and when to stop, often producing shallow, redundant, or poorly targeted trajectories. Prior work has explored rubrics as external quality signals, but existing uses are mostly evaluative rather than action-guiding: rubrics typically serve as training-time rewards or post-hoc evaluators of completed outputs, and in deep-research settings they are often coarse-grained and report-level rather than step-level. We introduce Co-ReAct, a rubric-guided action-selection framework that uses rubrics as step-level guidance during inference. At each decision step, Co-ReAct injects a rubric into the agent's context to guide the next Reason-or-Act decision, specifying what the agent should target in evidence seeking, search, reasoning, or self-evaluation. To make this guidance reliable, we train a dedicated rubric generator with GRPO. Unlike prior pairwise or binary preference formulations, our objective optimizes a list-wise Spearman rank-correlation reward against multi-judge expert consensus rankings, encouraging rubrics that are discriminative rather than merely plausible. On DeepResearchBench and SQA-CS-V2, Co-ReAct consistently improves over ReAct and representative test-time compute baselines across search agents built on both 8B/14B open-source and frontier closed-source base models. The trained rubric generator can also serve as a drop-in component that improves these baselines without changing their underlying decision mechanisms. Our code is publicly available at https://github.com/ZBWpro/Co-ReAct. --- ### How Many Training Samples Are Needed for the Inverse Kinematics Solutions by Artificial Neural Networks Authors: Dong-Won Lim Published: 2026-05-22 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2605.23583v1 Inverse Kinematics (IK) plays a critical role in robotic motion planning and control. The IK solutions of a robot manipulator could be done by conventional ways such as geometric, algebraic, or Jacobian methods, which have drawbacks. The Artificial Neural Networks (ANNs) have become a promising alternative for approximating IK solutions due to their generalization ability and computational efficiency. This approach basically trains only a few samples of the end effector that are recorded for the solution of the IK problem. However, a fundamental question remains: how many training samples are sufficient to achieve reliable and accurate IK predictions? This study investigates the mathematical framework of relating the size of training datasets and the accuracy of ANN-based IK solvers. Using an articulated robotic manipulator, we generate varying amounts of joint-position pairs to train feedforward neural networks and assess their accuracy, convergence, and generalization capability. The results reveal more training samples than 125 did not contribute to the improvement of the model efficiency that the comparable measure dealing with the approximation accuracy over the sampling size, offering valuable insight into data efficiency. This work provides practical guidance for optimizing the data sizing of ANN solutions, balancing computational cost and model accuracy for real-world robotic applications. --- ### Calibration-Informative Region Selection for Online LiDAR--Camera Calibration in Agricultural Environments Authors: Rajitha de Silva, Grzegorz Cielniak Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23580v1 Reliable multi-modal calibration requires identifying which observations truly constrain the extrinsic parameters and which ones mainly add noise or ambiguity. In this paper, we propose a support-map-driven approach to multi-modal calibration that decouples four functional blocks: initial calibration, cross-modal residual extraction, support-map estimation, and support-aware refinement. We instantiate this formulation for online LiDAR--camera calibration using MDPCalib, a target-less LiDAR--camera calibration method based on motion and deep point correspondences, and CMRNext, a dense LiDAR--camera matching model that predicts optical-flow-like image-plane residuals. The key contribution is a dense calibration support map that aggregates cross-modal agreement over aligned observations and highlights where calibration evidence is consistently reliable. Across the Bacchus Long-Term (BLT) dataset and KITTI, we show that calibration evidence is spatially and semantically non-uniform, indicating that some semantic regions provide stronger cues for calibration than others. On KITTI, support-guided refinement improves the calibration performance with better translation accuracy while rotational gains remain limited. --- ### Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents Authors: Yuandao Cai, Yuzhang Zhu, Liyou Gao, Wensheng Tang, Shengchao Qin Published: 2026-05-22 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2605.23574v1 Long-horizon language agents can make many plausible local tool calls yet fail to persist until a requested count is actually complete. We study this gap as Quantitative Goal Persistence (QGP): whether an agent keeps working until an external verifier confirms enough distinct valid items. PushBench turns this into a benchmark for repository-artifact collection and verifier-backed work units, so repeated work, duplicate submissions, false completion, and progress drift are measured directly rather than hidden behind a final success flag. In matched controller comparisons, a state-tracking retrieval controller reaches 69-78% success while eliminating duplicate submissions, and a backlog-tracking work-unit controller reaches 25-50% success in settings where standard and completion-gated controllers complete no task instances. Black-box frontier-agent evaluations with Claude Code (Sonnet 4.6) and Codex CLI (gpt-5.4) solve many 50-artifact tasks but drop to 3 out of 9 successes per condition at 100 artifacts. The results show that quantitative goals stress a different reliability requirement from local task competence: agents must maintain verified progress and stop only when the requested work is complete. --- ### HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval Authors: Vipul Gupta, Shikhar Mohan, Lakshya Kumar, Pranjal Chitale, Nikit Begwani, Amit Singh, Manik Varma Published: 2026-05-22 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23572v1 In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval models based on Small Language Models (SLMs) such as Qwen3-Embedding-4B/8B set strong upper bounds on public benchmarks, their deployment in high-throughput, latency-sensitive environments remains impractical. In this paper, we present HARNESS-LM (HLM), a three-phase training framework for transferring the capabilities of large-scale retrievers into compact, cost-efficient models. The approach comprises: (1) training a high-performance reference ("teacher") retriever by fine-tuning a billion-parameter-scale SLM; (2) aligning query representations via an L2 objective to distill knowledge into a sub-600M parameter student encoder; and (3) applying a final contrastive refinement stage to optimize the student for retrieval performance. We also present a comprehensive empirical study of key design choices, including alignment objectives, embedding dimensionality, model scale, architecture, and optimization strategies, to identify configurations that are most effective in production settings. On a real-world Bing Ads evaluation benchmark, HLM recovers over 98% of the reference retriever's precision across multiple settings, while delivering up to 27x lower online query-encoder latency and 20x higher throughput on NVIDIA A100 GPUs. Online A/B testing on Bing Ads further shows a +1% Revenue, +0.6% Impression, and +0.4% Click uplift over the current ensemble of retrievers running in production with the deployed 190M parameter model, clearly highlighting the practical efficacy of the HLM recipe in a real-world sponsored search setting. --- ### CP or DP? Why Not Both: A Case Study in the Partial Shop Scheduling Problem Authors: Emma Legrand, Roger Kameugne, Pierre Schaus Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.23569v1 Dynamic Programming (DP) and Constraint Programming (CP) are well-established paradigms for solving combinatorial optimization problems. Usually, these two approaches are used separately. This paper aims to show that the two can be combined effectively and elegantly, with DP serving as the primary search framework and CP used as a subroutine to leverage global constraint propagation. This paper presents such an approach for the Partial Shop Scheduling Problem (PSSP), for which a pure DP method has previously been proposed, and efficient CP filtering algorithms are available. The PSSP is a general scheduling problem where each job consists of a set of operations with arbitrary precedence constraints. The approach is flexible enough to accommodate anytime DP strategies, such as anytime column search, whereas the original DP algorithm operated in a strictly layer-wise manner. Moreover, the flexibility of the CP modeling makes it straightforward to incorporate arbitrary precedence constraints. As a result, the model naturally handles any precedence graph and even enables the design of a Large Neighborhood Search (LNS) scheme, in which the DP model is reused, and partial-order schedules are imposed across restarts to improve the incumbent solution. While not competitive with state-of-the-art pure CP solvers for this specific problem, our primary contribution is demonstrating the viability of this hybrid integration. --- ### Understanding Goal Generalisation in Sequential Reinforcement Learning Authors: Jason Ross Brown, Edward James Young Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.23565v1 Reinforcement learning agents often exhibit unintended goal-directed behaviour outside their training distribution, but we currently lack a principled understanding of how such agents will generalise to novel environments based on their training history. We address this gap for agents trained sequentially on one or more tasks. We study over 100 sequential training pipelines, evaluating behaviour across over 250 out-of-distribution environments. We find that salient features drive generalisation, and that goals learnt early in training can persist and influence those acquired later. To explain these phenomena, we introduce latent policy gradients, a method that predicts what out-of-distribution behaviour a training pipeline will likely induce. Our method simulates the evolution of low-dimensional latent variables during training according to what would achieve high reward on the training objective with respect to a simple model of how the latent variables map to behaviour. It achieves strong predictive accuracy, generalises to unseen types of training pipeline, and is interpretable. Our findings demonstrate that while out-of-distribution RL agent behaviour is dependent on the whole training pipeline, this dependence has an underlying structure we can capture, laying groundwork for understanding goal generalisation from a developmental perspective. --- ### MARS: Magnitude-Aware Rank Statistics Authors: Muhammad Rajabinasab, Afsaneh M. Nejad, Arthur Zimek Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23563v1 Comprehensive evaluation of machine learning models is the key to make sure that they perform as robustly and consistently as desired. In order to summarize the experimental results and pick a winner, Critical Difference (CD) diagrams are used. Standard CD diagrams rely on discrete ranks, discarding the magnitude of performance gaps between models, raising an issue which we call magnitude-blindness. In order to address this issue, we propose Magnitude-Aware Rank Statistics (MARS) that incorporates a relative margin coefficient as a weight for the discrete ranks. This coefficient scales ranks based on the distance between the best and worst performers, with a dynamic projection to handle boundary cases. Followed by the calculation of a CD value, MARS results in a more realistic statistical representation of differences of model performances and more insights on how methods actually perform in vast and extensive experimental settings. --- ### ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning Authors: Elie Abboud, Oren Gal Published: 2026-05-22 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2605.23562v1 Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes reward design especially delicate. Reward shaping can accelerate learning, but in the multi-agent setting it must preserve the strategic structure of the problem rather than merely improve short-term optimization. We propose Automatic Reward-shaping in Multi-agent Systems (ARMS), a self-supervised reward shaping framework for MARL that learns dense shaping signals from sparse environmental rewards through trajectory ranking. Since single-agent trajectory-ranking guarantees do not directly transfer to MARL, we reformulate policy invariance through conditional best-response reasoning, and show that if certain conditions hold, then using shaping rewards preserves each agent's best-response set under fixed opponent policies, and consequently preserve the set of Nash equilibria. Guided by this perspective, ARMS alternates between policy learning and reward learning while sharing shaping parameters across agents for efficiency. Experiments in a partially observable multi-agent pathfinding domain show that ARMS improves sampling efficiency under increasing reward sparsity and agent count, generalizes to unseen environments, and reveals a MARL-specific failure mode in which limited exploration and coupled policy--reward dynamics induce oscillatory behavior. Increasing exploration mitigates this effect and stabilizes learning. To the best of our knowledge, ARMS is the first automatic reward shaping framework for MARL whose design is motivated by a game-theoretic equilibrium-preservation result. --- ### PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA Authors: Chunze Yang, Qidong Liu, Wenjie Zhao, Yue Tang, Jiusong Ge, Di Zhang, Jiashuai Liu, Lei Wu, Junbo Lu, Ni Zhang, Xian Wu, Zeyu Gao et al. Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23559v1 Whole-slide image visual question answering (WSI-VQA) frames pathology as an extreme-context search problem: to answer a free-form clinical query, a system must first navigate a gigapixel slide under a strict inspection budget to locate sparse, high-resolution evidence. Existing approaches largely fall into two paradigms: i) supervised pathology multimodal large language models (MLLMs) and agents can absorb localization and reasoning into learned modules, but they often couple navigation to task-specific supervision and retraining, limiting their practicality; ii) training-free pathology agents avoid this cost by keeping core models frozen, but often follow a question-first design, constructing the initial candidate set mainly from query-conditioned relevance. This can miss decisive morphology that is not named in the question, and force heavier inference-time scaffolding. To address this challenge, we introduce PathNavigate, a training-free pathology agent built around a scan-search-readout routine. Before question matching, PathNavigate scans the current slide at low magnification with a shared online memory module over frozen pathology features, producing a slide-specific surprise field that marks an abnormal-region pool. It then applies question-conditioned PLIP relevance only within this pool to select high-magnification search targets. Finally, it extracts local high-magnification evidence and answers with a frozen perceptor-adjudicator stack, using the same online memory as slide-level context. Experiments on WSI-VQA and SlideBench-BCNB show that the proposed scan-search-readout design improves answer accuracy and yields more interpretable evidence-selection trajectories with higher efficiency.The code is available online. --- ### Is Dimensionality a Barrier for Retrieval Models? Authors: Kiril Bangachev, Guy Bresler, Jonathan Kogan, Yury Polyanskiy Published: 2026-05-22 Categories: cs.LG, cs.IR, math.CO arXiv: https://arxiv.org/abs/2605.23556v1 Why does the low dimensionality of representations, typically $d\approx 1000$, not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of data points? To answer this question, we study maximal-margin embeddings in the following retrieval model, classically studied in communication complexity (PS86) and more recently in embedding-based retrieval (WBNL26). Let $A\in \{0,1\}^{N\times n}$ be a matrix indicating whether each of $N$ queries is relevant to each of $n$ documents. We are interested in the largest margin $m>0,$ denoted by $\mathsf{m}^{\mathsf{rd}}(d, A),$ for which there exist unit norm embeddings of the queries and documents $\{U_j\}_{j = 1}^N, \{V_i\}_{i = 1}^n$ with the following property. $\langle U_j, V_i\rangle \ge m$ whenever $A_{ji} = 1$ and $\langle U_j, V_i\rangle \le -m$ otherwise. A large margin is a key proxy for representation quality: it controls both robustness to perturbations and compositional generalization across queries. Our main theorem establishes that the best possible margin without a restriction on the dimension, $\mathsf{m}^{\mathsf{rd}}(+\infty, A),$ can be nearly achieved in dimension $d = O(\mathsf{m}^{\mathsf{rd}}(+\infty, A)^{-2}\log n)$ which improves a theorem of (BDES02). Together with a matching lower bound in Theorem 1.5, we conclude that when $A\in \{0,1\}^{\binom{n}{k}\times n}$ is the matrix containing all possible $k$-sparse rows once, dimension $d = O(k\log (n/k))$ is necessary and sufficient for the maximal possible margin $\mathsf{m}^{\mathsf{rd}}(+\infty, A) = Θ(k^{-1/2})$ in this setting. This fully resolves the setup of (WBNL26). We also give several constructions for large margins when $d = o(k\log (n/k)).$ Finally, we empirically test the InfoNCE and sigmoid losses for producing large margin embeddings and demonstrate a clear advantage of the sigmoid loss. --- ### Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos Authors: Gangjian Zhang, Jian Shu, Sicheng Yu, Wenhao Shen, Yu Feng, Hao Wang Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23555v1 This paper addresses the challenge of reconstructing photorealistic and animatable 3D human avatars from monocular videos. While existing methods rely on combining per-subject optimization with generic human priors, they often fail to capture fine-grained details when training frames are limited. To mitigate this data scarcity, we propose TrioMan, a systematic tri-module framework for augmented 3D avatar learning. Our approach comprises three synergistic components. The Generator creates diverse unseen samples by imposing Gaussian perturbations on pose and camera. The Refiner improves the quality of generated data through one-step diffusion guided by texture and geometry cues. The Examiner selects subject-consistent samples using a dual-branch attention-based similarity evaluation. Experiments on the X-Humans and NeuMan benchmarks show that TrioMan outperforms state-of-the-art methods. --- ### Goal-Conditioned Agents that Learn Everything All at Once Authors: Michael Matthews, Matthew Jackson, Michael Beukman, Thomas Foster, Alistair Letcher, Scott Fujimoto, Cédric Colas, Jakob Foerster Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.23551v1 A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing on-policy updates with respect to the commanded goal. All-goals learning, where each transition is used for learning off-policy with respect to every goal, allows agents to extract maximal information, however it is usually computationally infeasible when done via naive relabelling. This can be overcome by jointly outputting values and actions for every goal at once, allowing for efficient, parallel all-goals updates with a single pass through the network, in a process we call Learning Everything all at Once (LEO). We show that this approach significantly outperforms other methods on goal-conditioned Craftax and is competitive with existing baselines on continuous control environments, while achieving a >250x speed-up compared to all-goals relabelling. We then go on to show that this approach can be made even more powerful by using LEO as a teacher network, rather than a direct actor. We hope that, by unlocking all-goals learning at scale, LEO can serve as a useful tool for RL practitioners in complex environments. We open source our code. --- ### RA-DCA: A Randomized Active-Set DCA for Directional Stationarity in Max-Structured DC Programs Authors: Yi-Shuai Niu Published: 2026-05-22 Categories: math.OC, cs.AI, math.NA arXiv: https://arxiv.org/abs/2605.23550v1 We study nonsmooth difference-of-convex programs whose subtracted convex term is a finite maximum of smooth convex functions. In this setting, standard DCA iterations may converge to critical points that are not directionally stationary, whereas exact active-vertex screening can be expensive when active sets are large or combinatorial. We propose RA-DCA, a vertex-first randomized active-set DCA that projects active gradients onto sampled directions, checks a sampled vertex residual, and uses a small linear program only as a low-residual convex-combination fallback. The method preserves the descent structure of DCA and reduces the randomized screening layer to matrix multiplications. Under the stated regularity, numerical active-set consistency, and random-embedding assumptions, every accumulation point generated by the safeguarded method is directionally stationary with probability one. MATLAB experiments first test the theorem on degenerate max-affine, max-quadratic, and sparse support-function models, where the safeguard avoids nonstationary critical points and closely tracks a full active-vertex scan. Block top-k tests then show that the same screening idea remains useful when exact aggregate enumeration is combinatorial. Trimmed-regression, complementarity, and QUBO diagnostics separate cases where active-set selection helps from cases dominated by multistart search, the DC split, or other problem-specific features. --- ### When One Point Is Not Enough: Addressing Ambiguous Instances in Dimensionality Reduction by Splitting Authors: Diede P. M. van der Hoorn, Alessio Arleo, Fernando V. Paulovich Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23540v2 Dimensionality Reduction (DR) methods are widely used to visualize high-dimensional data. One key task in DR-based analysis is discovering neighborhoods, which relies on analyzing the fine-grained local structure of a projection. However, DR is an inherently lossy process; no technique can perfectly preserve the high-dimensional relationships, and projections therefore contain visual artifacts. In this paper, we highlight a typically overlooked source of visual artifacts: ambiguous instances. These are instances that are highly similar to multiple mutually dissimilar neighborhoods in the high-dimensional space. Standard DR methods cannot faithfully project such instances, since each data instance is mapped to a single point in the visual space. As a result, such an instance is placed in only one of its neighborhoods (or in none at all), so only part of its neighborhood structure is represented. We call this distortion partial neighborhood embedding. In this paper, we introduce a graph-based approach that identifies ambiguous instances and replicates them as multiple points in the projection, placing each copy within its respective neighborhood. We use UMAP for our results, but our approach also generalizes to other local graph-based DR techniques. We show that our approach reveals previously hidden neighborhood memberships in projections and reduces partial neighborhood embedding across multiple examples, and is further supported by quantitative analyses. --- ### Concomitant DAG Learning: On the Roles of Noise Adaptivity, Sparsity, and Non-negativity Authors: Gonzalo Mateos, Samuel Rey, Hamed Ajorlou, Mariano Tepper Published: 2026-05-22 Categories: stat.ML, eess.SP arXiv: https://arxiv.org/abs/2605.23537v1 Directed acyclic graphs (DAGs) constitute a central modeling tool to enable principled reasoning about cause-effect interactions in complex systems. However, since the causal structure underlying a group of variables is often unknown and interventions may be infeasible or ethically challenging to implement, there is a need to address the task of inferring DAGs from observational data. However, most classical structure identification approaches face two key obstacles: the combinatorial challenge of enforcing acyclicity, which severely limits scalability, and identifiability challenges arising from latent confounding or heterogeneous noise. This tutorial offers an overview of recent signal processing and optimization advances that address these issues by recasting DAG structure learning as a continuous, score-based estimation problem over adjacency matrices. We begin with a didactic introduction to structural equation models and the formulation of causal graph recovery, followed by a historical survey of score-based methods ranging from early combinatorial search schemes and greedy heuristics to modern continuous frameworks that leverage smooth characterizations of acyclicity. Building on this foundation, we describe concomitant DAG estimation methods that jointly infer sparse causal structure and exogenous noise levels, improving robustness under heteroscedasticity and distribution shifts by rendering the estimator noise adaptive. All in all, the tutorial introduces readers to challenges and opportunities for signal processing research at the crossroads of causal inference, high-dimensional statistics, and scalable graph learning, while outlining emerging directions including online, nonlinear, and neural causal discovery. --- ### PixIE: Prompted Pixel-Space Low-Light Image Enhancement Authors: Ruirui Lin, Guoxi Huang, David Bull, Nantheera Anantrasirichai Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23531v3 Low-light images suffer from severe noise, contrast loss, and semantic ambiguity, making enhancement a joint problem of denoising and detail recovery. We propose PixIE, a feed-forward pixel-space LLIE framework semantically prompted by a foundation model (FM). PixIE first performs cross-scale denoising to suppress noise while preserving structure, then refines details using Prompted Pixel Blocks (PPBs), which inject intermediate FM features through a novel spatially continuous modulation (SCMo). To make pixel-space attention efficient across scales, we introduce Spatial-Channel Compaction (SCC), which jointly reduces the spatial token grid and channel dimension. We further propose Multi-Receptive-Field Pixel Embedding (MRPE) to provide neighborhood-aware pixel representations before semantic prompting, improving robustness to signal-dependent noise beyond point-wise embeddings. Experiments on standard LLIE benchmarks demonstrate state-of-the-art performance, achieving the best PSNR, SSIM, and LPIPS on the challenging LOLv2-Real benchmark. Qualitative comparisons further show sharper details with more natural and consistent textures, improving both reconstruction fidelity and perceptual quality. --- ### ComPose: When to Trust Hands for Object Pose Tracking Authors: Jisu Shin, Junoh Lee, JunGyu Lee, Inhwan Bae, Dohyeon Lee, Hokyun Im, Youngwoon Lee, Hae-Gon Jeon Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23523v1 Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they rely heavily on strong external priors, such as depth data or 3D templates, and remain highly vulnerable to severe occlusions by hand grasps despite the use of explicit masks. In this work, we present ComPose, a 6DoF object tracking framework designed for hand-aware object pose estimation from RGB video. Rather than treating the hand purely as an occluder, our method harmonizes hand motions as a \textit{complementary cue} for object tracking. In detail, we recover a variety of object motions over time by combining object and hand cues from foundation models within a unified tracking pipeline. Here, ComPose adaptively selects informative hand joints, combines object- and hand-derived cues for motion estimation, and refines the resulting object motion using visible geometric evidence and a learned correction. We further enforce the temporal consistency over both rotation and translation, yielding stable 3D object trajectories over time without any external smoothing. Extensive experiments show that our method is accurate, efficient, and robust under severe hand occlusion and geometric ambiguity. In addition, the resulting trajectories can also effectively transfer to downstream robot manipulation by enabling robots to reconstruct human actions from online videos. --- ### Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models Authors: Jade Zou, Tao Huang, Weijie Kong, Junzhe Li, Yue Wu, Qi Tian, Jiangfeng Xiong, Jianwei Zhang, Liefeng Bo, Zhao Zhong Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.23522v1 Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy, and its design can significantly affect the reward optimization performance. We break down the sampler design into two interdependent components: choosing the right amount of stochastic exploration, and discretizing the resulting SDE faithfully at the small step counts used in RL. To address the first component, we analyze the inherent tension between exploration and stability in denoising and derive an SDE schedule that balances the two. Turning to the discretization challenge, we use a toy example to show that existing samplers can deviate from the flow-matching process, either by introducing excessive discretization noise or by relying on heuristic rules that do not guarantee convergence to the data distribution. To address these issues, we propose Precise, a new stochastic sampler that balances effective exploration with stability. Crucially, Precise keeps the denoising trajectory SDE-consistent through a novel approximation that freezes the clean-latent posterior mean, resolving the excess noise issue in standard samplers. Extensive experiments demonstrate that this formulation leads to significantly faster and more stable reward optimization via reinforcement learning, achieving state-of-the-art alignment scores (e.g., PickScore, HPSv2.1) while requiring 13.1-53.2% less wall-clock training time to match the best in-domain performance of prior samplers. --- ### VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset Authors: Zhizhou Chen, Shanyan Guan, Zhanxin Gao, En Ci, Yanhao Ge, Wei Li, Zhenyu Zhang, Jian Yang, Ying Tai Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23518v1 Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in modeling high-frequency texture details. We introduce VINS-120K, the first large-scale dataset for instruction-based UHR image editing, comprising 120K carefully curated triplets of instruction, input image, and edited image. Each image exceeds 4K resolution ($\geq$4096 $\times$ 4096) and is filtered through a rigorous multi-stage pipeline to ensure visual quality, instruction alignment, and aesthetic fidelity. Built on VINS-120K, we further develop a high-frequency-aware post-adaptation strategy to extend pretrained non-high-resolution models to the UHR regime. We also present VINS-4KEval, a benchmark covering diverse editing types, to facilitate consistent evaluation in UHR settings. Experiments confirm that our work improves fine-grained detail synthesis and texture realism in UHR image editing. --- ### Learning partially observed systems with neural Hamiltonian ordinary differential equations Authors: Sunniva Meltzer, Sølve Eidnes, Alexander Johannes Stasik Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23510v1 When learning dynamical systems from data, embedding physical structure can constrain the solution space and improve generalization, but many physics-informed models assume access to the full system state. This limits their use in partially observed settings, where some state variables are completely unobserved and must be inferred without direct supervision. Here, we present neural Hamiltonian ordinary differential equations (NHODE), a framework that combines Hamiltonian neural networks (HNNs) with neural ordinary differential equations (neural ODEs) to learn partially observed dynamical systems from data. The Hamiltonian structure enforces energy conservation by construction, while the neural ODE framework enables a flexible training procedure that allows the loss to be defined only on observed variables. We also incorporate additional physical constraints through symmetry-aware coordinate transformations and separable energy formulations. The framework is evaluated on systems of increasing complexity, from linear and nonlinear mass-spring systems to the chaotic three-body problem. Across all examples, increasing the amount of embedded physical structure improves the accuracy and long-horizon stability of the predictions. Even in the most challenging regimes, the NHODE framework captures both observed and latent dynamics, whereas purely data-driven baselines become unstable. --- ### DrawVideo: Generating Long Video from Storyboard Keyframe Sketches Authors: Chuanzhi Xu, Huiqi Liang, Bang Shi, Huiming Zhang, Yifan Xiao, Guangcheng Lin, Haodong Chen, Qiang Qu, Zhicheng Lu, Weidong Cai Published: 2026-05-22 Categories: cs.GR, cs.AI, cs.CV, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2605.23508v1 Long video generation requires high-fidelity synthesis, coherent narrative structure, and user control over extended time spans. Existing text-to-video methods often rely on a single long prompt, limiting control over pose, composition, layout, and motion. We propose DrawVideo, a sketch-guided, storyboard-driven framework for controllable long-video generation. DrawVideo decomposes long videos into independently controllable shots, each defined by a black-and-white sketch, an appearance prompt, and a motion prompt. The sketch controls pose and layout, the appearance prompt defines identity, scene, and style, and the motion prompt guides temporal dynamics. DrawVideo follows a hierarchical 'global multi-shot, local single-sketch' strategy: it first generates a structure-aligned reference keyframe, then expands the motion prompt into derivative keyframes representing action states, and finally synthesizes clips between adjacent keyframes to build each shot. We also introduce SketchLongVideo, the first dataset for sketch-guided text-to-long-video generation, constructed from animation videos via shot detection, keyframe extraction, vision-language recognition, prompt decomposition, and sketch conversion. Experiments show that DrawVideo achieves strong structural controllability, appearance consistency, visual stability, and coherent long-video generation. --- ### MDS-DETR: DETR with Masked Duplicate Suppressor Authors: Chanho Lee, Seunghee Koh, Yunho Jeon, Junmo Kim Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23507v1 The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low recall. A common approach to address this issue is to use one-to-many label assignment to provide more positive samples. However, existing methods that use one-to-many matching as an auxiliary objective lead to increased training costs, with their auxiliary decoders discarded during inference. To address this limitation, we propose MDS-DETR, which leverages both one-to-one and one-to-many supervision within a single decoder. Specifically, we introduce a Masked Duplicate Suppressor (MDS) that injects asymmetry into self-attention via confidence-based causal masking. MDS filters out the duplicates generated by the one-to-many supervised layer, enables explainable, duplicate-free predictions in a fully end-to-end framework. MDS-DETR outperforms existing one-to-many DETR variants such as MS-DETR, MR.DETR and Relation-DETR, without relying on any additional queries or auxiliary decoders. Under a 12-epoch training schedule on MS COCO with a ResNet-50 backbone, MDS-DETR achieves a +2.8 mAP improvement over Deformable-DETR with only a 5\% increase in training time, and outperforms the state-of-the-art MR.DETR by +0.3 mAP while being even 20\% faster in training. Our code and models are available at \href{https://github.com/dcholee/mds-detr}{https://github.com/DChoLee/MDS-DETR}. --- ### VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection Authors: Alberto D. Cencillo, Leonardo Concepción, Isaac Triguero, Julián Luengo Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.23504v1 Anomaly detection in multivariate time series is a critical task across a wide range of real-world applications, where abnormal behaviour is rare, labels are unavailable, and the cost of a miss is high. The central challenge is learning a characterisation of normality precise enough to flag deviations. Representation self-supervised learning, typically through contrastive approaches, addresses this by embedding temporal patches into a latent space where normality occupies a well-defined region, with anomalies detected by geometric deviation. However, contrastive approaches shape this space indirectly through pair-sampling heuristics, providing no explicit control over the geometric structure that distance-based scoring requires. This means how tightly normal representations are grouped, and whether distances are directionally meaningful. We present VACE (Velocity-Aligned Channel Embeddings), a self-supervised anomaly detection method that represents normality as a compact, directionally coherent region in the embedding space. To this end, VACE trains a channel-aware encoder through a velocity-consistency objective, with no negatives and no synthetic anomalies, so that normal trajectories are locally smooth and aligned. At test time, a Mahalanobis positional score and a velocity-bank directional score are combined multiplicatively, flagging points that are simultaneously off-distribution and dynamically atypical. Despite its simplicity, VACE achieves state-of-the-art performance on TSB-AD-M under rigorous evaluation, significantly outperforming more complex methods trained on substantially larger budgets. --- ### B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation Authors: Mario Markov, Stefan Maria Ailuro, Mohammad Mahdi, Luc Van Gool, Danda Pani Paudel Published: 2026-05-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.23500v2 Segmentation is a fundamental task in computer vision, underpinning pixel-level scene understanding and serving as a cornerstone for applications ranging from autonomous perception to medical image analysis. For complex referring segmentation, recent methods pair large vision-language models with segmentation decoders: the former analyzes the image and prompt, while the latter predicts the target mask. Although reinforcement learning improves reasoning-intensive vision-language systems, trainable tools such as segmentation decoders are typically optimized separately with differentiable objectives, and the principled integration of such objectives into reinforcement learning remains underexplored. Thus, we introduce group relative tool optimization (GRTO), a mathematically grounded framework for jointly optimizing a policy with differentiable tool use. GRTO reuses group relative policy optimization (GRPO) rollouts to optimize the auxiliary tool objective, letting decoder gradients complement policy rewards. Further, we derive Bootstrapped-GRTO (B-GRTO), a pre-training method that cheaply bootstraps the tool, leading to faster convergence and superior performance. Across three challenging referring segmentation settings, B-GRTO results in substantial improvements over plain GRPO, matching or surpassing domain-specific state-of-the-art methods. This demonstrates the value of unifying reinforcement learning with differentiable auxiliary objectives for reasoning-intensive segmentation. --- ### Asking For An Old Friend: Diagnosing and Mitigating Temporal Failure Modes in LLM-based Statutory Question Answering Authors: Max Prior, Andreas Schultz, Matthias Grabmair Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23497v2 Large language models are increasingly used for legal research, yet their fixed training cutoffs and reliance on static parametric knowledge are at odds with the evolving nature of statutory law. We study two temporal failure modes: post-cutoff staleness, where models apply superseded rules after legislative amendments, and recency bias, where models prefer newer provisions even when a historical version governs the fact pattern. To this end, we present a benchmark of 312 expert-validated, time-sensitive German statutory QA pairs spanning three categories: Post-Cutoff Amendment Questions, Pre-Amendment Questions, and Multi-Provision Pre-Amendment Questions. We evaluate five LLMs by OpenAI, Anthropic and DeepSeek under four inference settings: Vanilla, Web-search, and two retrieval-augmented variants that enforce temporal validity via a fact date extraction and version filtering. Using an LLM-as-a-judge validated against human expert ratings, we find severe degradation in the Vanilla post-cutoff setting. Both RAG approaches substantially improve performance across all question types, while web search yields unstable gains and exhibits a marked recency bias on historically anchored tasks. Our results indicate that reliable legal QA requires treating temporal validity as a hard constraint. --- ### Asking For An Old Friend: Diagnosing and Mitigating Temporal Failure Modes in LLM-based Statutory Question Answering Authors: Max Prior, Andreas Schultz, Matthias Grabmair Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23497v1 Large language models are increasingly used for legal research, yet their fixed training cutoffs and reliance on static parametric knowledge are at odds with the evolving nature of statutory law. We study two temporal failure modes: post-cutoff staleness, where models apply superseded rules after legislative amendments, and recency bias, where models prefer newer provisions even when a historical version governs the fact pattern. To this end, we present a benchmark of 312 expert-validated, time-sensitive German statutory QA pairs spanning three categories: Post-Cutoff Amendment Questions, Pre-Amendment Questions, and Multi-Provision Pre-Amendment Questions. We evaluate five LLMs by OpenAI, Anthropic and DeepSeek under four inference settings: Vanilla, Web-search, and two retrieval-augmented variants that enforce temporal validity via a fact date extraction and version filtering. Using an LLM-as-a-judge validated against human expert ratings, we find severe degradation in the Vanilla post-cutoff setting. Both RAG approaches substantially improve performance across all question types, while web search yields unstable gains and exhibits a marked recency bias on historically anchored tasks. Our results indicate that reliable legal QA requires treating temporal validity as a hard constraint. --- ### EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation Authors: Aristotelis Lazaridis, Dylan Bates, Aman Sharma, Brian King, Vincent Lu, Jack FitzGerald Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.23493v1 On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution drift, and consequently, regression in general tasks. On-Policy Self-Distillation (OPSD) is an efficient use-case of OPD, which is appealing as it requires only a single model as a student and teacher, and it also has the benefit of providing privileged context that is a absent at inference time (e.g. a persona, a private fact, or a worked solution) to the teacher during the training process. The challenge in this approach is that the privileged information can change model behavior more than intended: it can modify reasoning, degrade general capabilities, and affect performance indicators like response length, style, or local token preferences. Consequently, OPSD may train the student on side effects rather than a desired, transferable behavior. In this paper, we study this problem in a rare-token/identity setting and propose EviDence GuidEd On-Policy Distillation (EDGE-OPD), a modification of OPSD with two distinct characteristics: a) it uses guided rollouts to inject privileged-context behavior to the student at sampling time, so that the rare target behavior is actually present in the on-policy data, and b) it applies an evidence mask: the student is updated only at token positions where the privileged context supports the sampled token, rather than on every token in the rollout. We empirically show that OPSD (and its variant RLSD, with and without a verifier) completely fail to learn a target identity, while the integration of guided rollouts allows them to succeed. Additionally, mask-region ablations show that the persona signal is localized to the positive-evidence tail, allows us to draw valuable insights about efficient knowledge transfer and preservation of general purpose capabilities. --- ### CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test Authors: Zhangyi Hu, Chenhui Liu, Tian Huang, Jindong Li, Yang Yang, Jiemin Wu, Zining Zhong, Menglin Yang, Yutao Yue Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.23491v2 Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signals from the Code-UT execution matrix to iteratively prune or fix weak codes and refresh or replace unreliable UTs, letting the two pools co-evolve. Finally, when multiple codes remain tied at the highest pass count, it picks the final code from the largest output-consensus cluster, since correct codes agree on the same inputs while wrong codes diverge. Experiments on four challenging benchmarks show that CoSPlay on Qwen2.5-7B-Instruct improves average BoN from 22.1% to 33.2% and UT accuracy from 14.6% to 78.3%, matching or surpassing the RLVR model CURE-7B. When applied to CURE-7B, it further improves BoN by 5.7%. CoSPlay also generalizes across diverse backbones and outperforms GT-free TTS baselines under comparable token budgets, with continued gains as the budget scales up. These results suggest a scalable inference strategy for competitive code generation without any GT data. --- ### Multimodal Distribution Matching for Vision-Language Dataset Distillation Authors: Jongoh Jeong, Hoyong Kwon, Minseok Kim, Kuk-Jin Yoon Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23482v1 Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve representation quality and cross-modal alignment under tight compute and memory budgets, yet prior methods often require heavy computes and overlook their correlations. To address this, we present Multimodal Distribution Matching (MDM), a geometry-aware framework for efficient and generalizable multimodal distillation. Specifically, MDM integrates complementary components at the data, model, and loss levels. At the data level, it initializes synthetic image-text pairs by sampling from clusters in the joint embedding space. At the model level, it forms a mixed teacher by interpolating independently fine-tuned models in weight space according to their angular deviation from the pretrained anchor. At the loss level, it matches joint distributions on the unit hypersphere using a geometry-aware matching objective that exploits the joint features in the cross-modal agreement and discrepancy directions along with symmetric contrastive learning. Across image-text retrieval benchmarks with cross-architecture evaluation, MDM yields compact synthetic sets that preserve multimodal semantics, substantially reduce distillation cost, and remain robust across architectures. --- ### PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction Authors: Yu Luo, Xiaogang Zhu, Shan Zeng, Wei Xiang, Thomas Francis Bishop, Zhiyong Wang, Kun Hu Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23478v1 Accurate crop yield prediction is crucial for sustainable agriculture and global food security. While existing methods are predominantly developed for single-crop prediction, they often struggle to generalize across diverse crop types, without addressing the unique crop phenological responses that are dynamically modulated by complex weather patterns. In this paper, we propose PhenoYieldNet, a multi-crop yield prediction framework that learns crop-specific phenology by explicitly modeling their responses with temporal drivers. Specifically, we develop a crop-aware temporal decoder consisting of a Crop Phenology Bank (CPB) and a Crop Phenology Attention (CPA) module. The CPB integrates a set of learnable embeddings, which leverage a query to guide the CPA module to learn the most relevant phenology patterns for the specific crop. And the CPA module explicitly captures multi-scale trend and variation components to construct temporal contexts, enabling the model to dynamically adjust the attention across different phenological stages. To learn robust and generalizable features for multi-crop prediction, the encoder is initialized with a pre-trained foundation model, and further adapted via a self-supervised Temporal Contrastive Adaptation strategy to align with agricultural temporal dynamics. Extensive experiments conducted on multi-crop datasets indicate that our proposed method significantly outperforms state-of-the-art methods, exhibiting strong generalization capabilities across different regions and crops. --- ### Non-normal spectral signatures of instability in neural network training dynamics Authors: Souvik Ghosh Published: 2026-05-22 Categories: cs.LG, cond-mat.dis-nn, cond-mat.mtrl-sci, math.OC arXiv: https://arxiv.org/abs/2605.23476v1 Training instabilities in deep networks - loss spikes, oscillatory convergence, and gradient pathologies - are empirically prevalent but lack a rigorous operator-theoretic explanation. We show that the linearized update operators for practically used optimizers are generically non-normal: for Adam, non-normality is controlled by the commutator (H, M) between the Hessian and the diagonal adaptive preconditioner, while for SGD with momentum it arises from the augmented state-space structure of the update map. Applying non-normal stability theory to these operators, we derive a conservative pseudospectral precursor bound in which κ(V) serves as an early-warning indicator of transient amplification even when the spectral radius remains below one, and we establish that exceptional points of the update operator appear as the κ(V) -> \infty limiting case of this framework. Numerical experiments on two-layer networks confirm that the spectral radius ρ(J) provides no separation between stable and unstable training phases while κ(V) separates them by approximately one order of magnitude, complementing the classical sharpness criterion with a continuous severity measure of non-normal amplification. These results establish non-Hermitian operator theory as a useful and underexplored framework for neural network optimization stability, offering a diagnostic language and proof-of-concept benchmark for understanding adaptive optimization stability. --- ### Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dimension Authors: Hong Qian, Xiang Shu, Xiang Xia, Xuhui Liu, Yangde Fu, Bei Liang, Huibin Wang, Liang Dou Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.23473v2 Bayesian optimization is widely employed for optimizing complex black-box functions but struggles with the curse of dimensionality. Random embedding, as a dimension reduction strategy, simplifies tasks that possess the effective dimension by optimizing within a low-dimensional subspace. However, determining the effective dimension of a task in advance remains a significant challenge, which influences the selection of the subspace dimensionality and the optimization performance. Traditional methods use fixed subspace dimensions provided by experts or rely on trial and error to estimate subspace dimensions with resources consumed. To this end, this paper proposes an automated random embedding for high-dimensional Bayesian optimization with unknown effective dimension, called Dynamic Shared Embedding Bayesian Optimization (DSEBO). DSEBO starts with a low dimension and switches to a higher subspace if the solutions in the current subspace show preliminary convergence. DSEBO dynamically determines the dimension of the next subspace based on the quality of the solutions in different subspaces and shares the queried solutions with the new subspace for a better initialization. Theoretically, we derive a regret bound for DSEBO and demonstrate that DSEBO can better balance approximation and optimization errors. Extensive experiments on functions with dimensionality of varying magnitudes and real-world tasks with unknown effective dimensions reveal that, compared with state-of-the-art methods, alternating optimization across different subspaces results in significant improvements in high-dimensional optimization, both in terms of optimization regret and time. --- ### Rethinking Transfer Learning for Industrial Inspection: DINOv3 vs. ImageNet Pretraining Across RGB and X-ray Tasks Authors: Mehdi Gharbage, Céline Teulière, Pierre Bouges, Thierry Chateau Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23472v1 Vision foundation models pretrained on web-scale data have recently shown strong transfer capabilities on many downstream tasks, but their effectiveness for industrial visual inspection remains unclear. Industrial data differ substantially from web-data and often require fine-grained dense prediction, raising the question of whether modern self-supervised pretraining can improve over the conventional transfer-learning paradigm based on supervised ImageNet initialization. In this work, we compare ConvNeXt backbones pretrained with supervised ImageNet classification or DINOv3 distillation, and relate them to the conventional ResNet-50 baseline. We evaluate semantic segmentation, instance segmentation, and object detection across four downstream datasets spanning RGB surface-defect inspection and X-ray defect detection. We further study both frozen and fully finetuned adaptation regimes. Our results show that DINOv3 offers no clear advantage in frozen transfer, but provides a stronger initialization after full finetuning on RGB tasks, yielding faster convergence and better final performance. Under X-ray modality shift, however, supervised ImageNet pretraining remains more effective in both frozen and finetuned settings. Overall, our findings suggest that modern vision foundation models are promising for supervised RGB industrial inspection, but their transferability is strongly conditioned by downstream adaptation and target modality. --- ### CBANet: A Compact Attention-Based CNN-BiLSTM Network for Aggressive Driving Event Detection Authors: Hanadi Alhamdan, Ghadah Alosaimi, Amir Atapour-Abarghouei, Farshad Arvin Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.23471v1 Aggressive driving is a major cause of traffic accidents and poses a serious threat to road safety. Although deep learning methods have shown promising results in detecting risky driving behaviours from vehicle sensor data, their performance in real-world conditions is often limited by severe data imbalance, large variability between drivers, and the lack of physically interpretable vehicle dynamics representations. In this paper, we propose an enhanced deep learning framework for aggressive driving detection using multivariate vehicle dynamics signals. Instead of relying solely on raw measurements, the proposed approach constructs engineered dynamic features that capture steering, acceleration, and braking behaviour. To address the extreme rarity of aggressive events in naturalistic driving data, we introduce a stable training strategy that combines controlled SMOTE-based oversampling with a class-weighted loss formulation, and evaluates focal loss variants for imbalance handling. Furthermore, a safety-oriented decision strategy based on class-specific threshold calibration is adopted to better reflect the asymmetric risks of missed detections and false alarms in real-world applications. The proposed framework is evaluated on a newly collected naturalistic driving dataset. Extensive experiments show that the proposed method consistently outperforms standard deep learning baselines with significant improvements in minority-class recall and safety-critical F-score metrics while maintaining practical computational efficiency. Code: \url {https://github.com/halhamdan/CBANet} --- ### Learning Individual Dynamics from Sparse Cross-Sectional Snapshots Authors: Christian Lagemann, Kai Lagemann, Steven L. Brunton, Sach Mukherjee Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2605.23470v1 Predicting how a dynamical unit evolves over time - how an individual ages, an epidemic spreads, or a physical system degrades - typically requires dense longitudinal tracking. When only extremely sparse or entirely cross-sectional data is available, inferring individualized, continuous-time trajectories is fundamentally ill-posed. Existing methods force a strict compromise: sequence models (e.g. latent ODEs) require dense longitudinal data, while cross-sectional methods (e.g. optimal transport, flow matching-based) map aggregate populations, losing individual dynamics. In this paper, we demonstrate that this dichotomy can be broken. We introduce CADENCE, a principled probabilistic framework that recovers continuous individual trajectories from isolated snapshots by anchoring latent dynamics to static, individual-level contexts. We provide novel identifiability guarantees for single-timepoint trajectory inference. By combining a score-based spatial encoder (bijective Probability Flow ODE) to eliminate diffeomorphic ambiguities with a Soft Mixture-of-Experts (SMoE) router, we show that individual dynamical parameters and routing function are jointly identifiable. Across a suite of benchmarks spanning physical systems to real-world biological data, CADENCE, trained strictly on extremely sparse snapshots with context structure, matches or exceeds the performance of state-of-the-art sequential models trained on dense, full-trajectory data. --- ### S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning Authors: Dai Shi, Luke Thompson, Linhan Luo, Lequan Lin, Andi Han, Junbin Gao, José Miguel Hernández Lobato Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23467v1 Message-passing neural networks (MPNNs) often suffer from an information bottleneck when capturing long-range dependencies, leading to the oversquashing (OSQ) phenomenon. Alongside spatial connectivity enrichment (e.g., rewiring), recent studies have shown that spectral filtering can yield strong long-range learning outcomes, as spectral operators enable global information mixing that alleviates OSQ. These approaches achieve this either by stabilizing the Jacobian energies in deep propagation or by guaranteeing OSQ mitigation under strong theoretical assumptions. We revisit these conclusions and show that the associated Jacobian sensitivity lower bound is generally difficult to achieve in practice. We then propose S$^3$GNN, which mitigates OSQ without such restrictive assumptions by lightweightly reintroducing omitted components with substantially lower computational complexity, while standard stability constraints on feature transformations remain effective under our new dynamics. Extensive experiments across diverse domains (e.g., long-range benchmarks, KGQA, and mesh-based fluid dynamics) demonstrate that S$^3$GNN achieves up to an order-of-magnitude error reduction with up to 50\% fewer parameters. Our code can be found in https://github.com/EEthanShi/S3-GNN.git. --- ### Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization Authors: Alexander Long, Chamin Hewa Koneputugodage, Thalaiyasingam Ajanthan, Yan Zuo, Gil Avraham, Violetta Shevchenko, Hadi Mohaghegh Dolatabadi, Sameera Ramasinghe Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23464v1 We consider a decentralized setup in which the participants collaboratively train and serve a large neural network, and where each participant only processes a subset of the model. In this setup, we explore the possibility of unmaterializable weights, where a full weight set is never available to any one participant. We introduce Unextractable Protocol Models (UPMs): a training and inference framework that leverages the sharded model setup to ensure model shards (i.e., subsets) held by participants are incompatible at different time steps. UPMs periodically inject time-varying, random, invertible transforms at participant boundaries; preserving the overall network function yet rendering cross-time assemblies incoherent. On Qwen-2.5-0.5B and Llama-3.2-1B, 10,000 transforms leave FP32 perplexity unchanged ($Δ$PPL $< 0.01$; Jensen-Shannon drift $< 4 \times 10^{-5}$), and we show how to control growth for lower precision datatypes. Applying a transform every 30s adds 3% latency, 0.1% bandwidth, and 10% GPU-memory overhead at inference, while training overhead falls to 1.6% time and $< 1$% memory. We consider several attacks, showing that the requirements of direct attacks are impractical and easy to defend against, and that gradient-based fine-tuning of stitched partitions consumes $\geq 60$% of the tokens required to train from scratch. By enabling models to be collaboratively trained yet not extracted, UPMs make it practical to embed programmatic incentive mechanisms in community-driven decentralized training. --- ### AI Assurance: A Comprehensive Testing Strategy for Enterprise AI Systems Authors: Chitra Badagi, Divye Singh, Animesh Sen, Adinath Shirsath Published: 2026-05-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.23459v1 Enterprise AI systems, built on large language models, retrieval pipelines and autonomous agents, introduce a class of risks that traditional software quality assurance was never designed to address. These systems are probabilistic, context-sensitive and emergent: they cannot be verified to be correct in the classical sense, but only evaluated with increasing confidence. This paper presents a comprehensive assurance strategy for enterprise AI systems built around three key principles: first, that AI testing should focus on continuous risk reduction rather than strict correctness verification; second, that evaluation must be treated as a core engineering discipline alongside development; and third, that failures in AI assurance can lead to organizational impacts that are fundamentally different from those seen in traditional deterministic software systems. We introduce a structured AI Failure Taxonomy, propose a revised five-layer AI Assurance Pyramid and provide operational guidance on evaluation-driven development, RAG system testing, model lifecycle management and governance. The goal is to equip engineering leaders and practitioners with a strategy that is both philosophically grounded and operationally deployable. --- ### One-Forcing: Towards Stable One-Step Autoregressive Video Generation Authors: Jiaqi Feng, Justin Cui, Yuanhao Ban, Cho-Jui Hsieh Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23458v2 Recent advances in autoregressive diffusion-based video generation have substantially improved the quality of real-time video synthesis. However, most existing methods still require multiple denoising steps, while reducing sampling to a single step often leads to severe quality degradation: trajectory-based consistency distillation methods often produce videos with weak dynamics, whereas DMD-based methods, such as Self-Forcing, tend to generate blurry frames. We attribute this limitation to the teacher trajectories exhibiting highly concentrated curvature near the high-noise endpoint, which poses a fundamental geometric challenge for one-step distillation under the consistency distillation framework. To address these limitations, we propose One-Forcing, a simple yet effective approach that augments the DMD objective with an auxiliary GAN loss for high-quality and efficient one-step video generation. We further find that framewise autoregression stabilizes adversarial training, enabling higher-quality generation with substantially fewer training iterations than chunkwise autoregression. Experiments on VBench show that One-Forcing achieves a total score of 83.76, establishing state-of-the-art performance among one-step causal video generation methods while remaining competitive with strong multi-step approaches. --- ### One-Forcing: Towards Stable One-Step Autoregressive Video Generation Authors: Jiaqi Feng, Justin Cui, Yuanhao Ban, Cho-Jui Hsieh Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23458v1 Recent advances have substantially improved real-time interactive video generation in the autoregressive regime. However, most existing few-step autoregressive video generation methods, often distilled from a corresponding many-step teacher, default to a 4-step sampling configuration, which still incurs considerable latency during deployment and suffers from severe quality degradation when the number of sampling steps is further reduced, particularly in the one-step setting. Trajectory-style consistency distillation methods often produce videos with weak dynamics, while DMD-based approaches, such as Self-Forcing, tend to yield blurry frames. To address this challenge, we propose One-Forcing, a simple yet effective approach which augments the DMD objective with an auxiliary GAN loss for high-quality and efficient one-step video generation. Experiments on VBench show that One-Forcing achieves a total score of 83.76, establishing state-of-the-art performance among one-step causal video generation methods and remaining competitive with strong many-step approaches. We further demonstrate that one-step framewise autoregressive generation can be achieved stably with merely one-third of the training cost of the chunkwise model, a setting that prior methods have failed to achieve successfully. --- ### ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning Authors: Xiaoyuan Li, Keqin Bao, Moxin Li, Yubo Ma, Yichang Zhang, Wenjie Wang, Fuli Feng, Dayiheng Liu Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23454v2 Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existing approaches often rely on expert-written rubrics and manually constructed question sets, while fixed task-level rubrics may fail to capture the evaluation requirements of individual questions. We propose ARES (Automated Rubric synthEsis for Scalable RL), a framework for automatically constructing rubric-based RL data at scale. Starting from raw pretraining documents, ARES converts source knowledge into self-contained question-answer pairs and co-generates question-specific weighted rubrics, enabling instance-level reward supervision for open-ended responses. To improve diversity and quality, ARES conditions generation on domain labels and persona information, and applies validation filters for question self-containment, answer faithfulness, and rubric validity. Using ARES, we construct 100K rubric-annotated instances across ten domains. Experiments on seven benchmarks show that rubric-based RL trained with ARES, outperforms continual pretraining, supervised fine-tuning, and binary-reward RL, with the largest gains on multi-dimensional open-ended tasks such as healthcare and instruction following. --- ### Class-Dependent Hybrid Data Augmentation for Multiclass Migraine Classification under Severe Class Imbalance Authors: Elvin Somón, Miguel A. Gutiérrez-Naranjo Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23453v2 We conducted a reproducibility-oriented re-evaluation of prior migraine classification studies, correcting for data leakage and metric bias. We then introduced (i) a clinically motivated aggregation of two hemiplegic subtypes following ICHD-3 §1.2.3, (ii) a class-dependent hybrid augmentation strategy that assigns generation methods based on per-class sample size, and (iii) the concept of fidelity asymmetry, motivating proportionally constrained growth as an alternative to full class balance. Experiments were performed on a dataset of 400 patients across seven migraine subtypes under a two-stage protocol, including the six-class configuration described above. Models were evaluated using stratified 5-fold cross-validation with macro-averaged F1 as the primary metric. Correcting methodological flaws reduces previously inflated performance estimates, with the corrected macro-F1 baseline standing at 0.71. The proposed framework consistently outperformed individual augmenters in macro-F1 averaged across the eight evaluated classifiers (0.862 vs. 0.836 for Gaussian Copula, 0.815 for CTGAN, and 0.801 for the no-augmentation baseline), and achieved its peak result of 0.914 with FT-Transformer under proportional augmentation. The no-augmentation FT-Transformer baseline (0.896) shows that, at the per-classifier ceiling, clinically motivated class aggregation accounts for most of the absolute improvement; the framework's principal measurable contribution is the gain in average robustness across classifiers, highlighting the dominant role of problem formulation. --- ### Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention Authors: Bingtian Qiao, Yue Shi, Yingjie Zhou, Yong Guo, Guangtao Zhai, Jiezhang Cao Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23451v1 Real-world image super-resolution aims to recover high-quality images from complex and unknown real-world degradations. However, existing generative Real-ISR methods largely inherit the dense latent representations and quadratic-cost global modeling paradigm developed for high-resolution image synthesis, causing computation, memory usage, and inference latency to scale unfavorably with resolution and thus limiting practical deployment. We argue that the key bottleneck lies not in insufficient restoration priors, but in excessive token redundancy and costly token interactions during high-resolution restoration. Motivated by this observation, we revisit Real-ISR from the perspectives of compact latent representation and linear-complexity modeling, and propose SANA-SR, an efficient one-step restoration framework. Specifically, SANA-SR employs a deep compression autoencoder with a 32x compression ratio to drastically reduce latent tokens while preserving restoration-relevant structures and textures. On top of this compact latent space, we introduce a linear-attention DiT with LoRA fine-tuning, enabling efficient high-resolution restoration with linear-complexity token mixing. Extensive experiments on all benchmark datasets demonstrate that SANA-SR achieves highly competitive and often superior quantitative performance against existing methods, while restoring clearer and more realistic textures. Moreover, after pruning, the deployed model runs in 0.019s with 407.95G MACs and 344M parameters, highlighting its strong potential for practical mobile deployment. ---