# Research Papers — 2026-04 · bundle page 67 of 233 > Full-text markdown of papers #3301–3350 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/67 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/66.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/68.md) ### ChipCraftBrain: Validation-First RTL Generation via Multi-Agent Orchestration Authors: Cagri Eryilmaz Published: 2026-04-21 Categories: cs.AR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.19856v1 Large Language Models (LLMs) show promise for generating Register-Transfer Level (RTL) code from natural language specifications, but single-shot generation achieves only 60-65% functional correctness on standard benchmarks. Multi-agent approaches such as MAGE reach 95.9% on VerilogEval yet remain untested on harder industrial benchmarks such as NVIDIA's CVDP, lack synthesis awareness, and incur high API costs. We present ChipCraftBrain, a framework combining symbolic-neural reasoning with adaptive multi-agent orchestration for automated RTL generation. Four innovations drive the system: (1) adaptive orchestration over six specialized agents via a PPO policy over a 168-dim state (an alternative world-model MPC planner is also evaluated); (2) a hybrid symbolic-neural architecture that solves K-map and truth-table problems algorithmically while specialized agents handle waveform timing and general RTL; (3) knowledge-augmented generation from a 321-pattern base plus 971 open-source reference implementations with focus-aware retrieval; and (4) hierarchical specification decomposition into dependency-ordered sub-modules with interface synchronization. On VerilogEval-Human, ChipCraftBrain achieves 97.2% mean pass@1 (range 96.15-98.72% across 7 runs, best 154/156), on par with ChipAgents (97.4%, self-reported) and ahead of MAGE (95.9%). On a 302-problem non-agentic subset of CVDP spanning five task categories, we reach 94.7% mean pass@1 (286/302, averaged over 3 runs), a 36-60 percentage-point lift per category over the published single-shot baseline; we additionally lead three of four categories shared with NVIDIA's ACE-RTL despite using roughly 30x fewer per-problem attempts. A RISC-V SoC case study demonstrates hierarchical decomposition generating 8/8 lint-passing modules (689 LOC) validated on FPGA, where monolithic generation fails entirely. --- ### Is Four Enough? Automated Reasoning Approaches and Dual Bounds for Condorcet Dimensions of Elections Authors: Itai Zilberstein, Ratip Emin Berker, George Li, Ruben Martins Published: 2026-04-21 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2604.19851v1 In an election where $n$ voters rank $m$ candidates, a Condorcet winning set is a committee of $k$ candidates such that for any outside candidate, a majority of voters prefer some committee member. Condorcet's paradox shows that some elections admit no Condorcet winning sets with a single candidate (i.e., $k=1$), and the same can be shown for $k=2$. On the other hand, recent work proves that a set of size $k=5$ exists for every election. This leaves an important theoretical gap between the best known lower bound $(k\geq 3)$ and upper bound $(k \leq 5)$ for the number of candidates needed to guarantee existence. We aim to close the gap between the existence guarantees and impossibility results for Condorcet winning sets. We explore an automated reasoning approach to tighten these bounds. We design a mixed-integer linear program (MILP) to search for elections that would serve as counter-examples to conjectured bounds. We employ a number of optimizations, such as symmetry breaking, subsampling, and constraint generation, to enhance the search and model effectively infinite electorates. Furthermore, we analyze the dual of the linear programming relaxation as a path towards obtaining a new upper bound. Despite extensive search on moderate-sized elections, we fail to find any election requiring a committee larger than size 3. Motivated by our experimental results in this direction, we simplify the dual linear program and formulate a conjecture which, if true, implies that a winning set of size 4 always exists. Our automated reasoning results provide strong empirical evidence that the Condorcet dimension of any election may be smaller than currently known upper bounds, at least for small instances. We offer a general-purpose framework for searching elections in ranked voting and a new, concrete analytical path via duality toward proving that smaller committees suffice. --- ### Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere Authors: R. Abbasi, M. Ackermann, J. Adams, J. A. Aguilar, M. Ahlers, J. M. Alameddine, S. Ali, N. M. Amin, K. Andeen, C. Argüelles, Y. Ashida, S. Athanasiadou et al. Published: 2026-04-21 Categories: hep-ex, astro-ph.HE, astro-ph.IM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.19846v1 IceCube is a cubic-kilometer-scale neutrino detector located at the geographic South Pole. A precise directional reconstruction of IceCube neutrinos is vital for associations with astronomical objects. In this context, we discuss neural posterior estimation of the neutrino direction via a transformer encoder that maps to a normalizing flow on the 2-sphere. It achieves a new state-of-the-art angular resolution for the two main event morphologies in IceCube - tracks and showers - while being significantly faster than traditional B-spline-based likelihood reconstructions. All-sky scans can be performed within seconds rather than hours, and take constant computation time, regardless of whether the posterior extent is arc-minutes or spans the whole sky. We utilize a combination of $C^2$-smooth rational-quadratic splines, scale transformations and rotations to define a novel spherical normalizing-flow distribution whose parameters are predicted as a whole as the output of the transformer encoder. We test several structural choices diverting from the vanilla transformer architecture. In particular, we find dual residual streams, nonlinear QKV projection and a separate class token with its own cross-attention processing to boost test-time performance. The angular resolution for both showers and tracks improves substantially over the whole trained energy range from 100 GeV to 100 PeV. At 100 TeV deposited energy, for example, the median angular resolution improves by a factor of $1.3$ for throughgoing tracks, by a factor of $1.7$ for showers and by a factor of $2.5$ for starting tracks compared to state-of-the art likelihood reconstructions based on B-splines. While previous machine-learning (ML) efforts have managed to obtain competitive shower resolutions, this is the first time an ML-based method outperforms likelihood-based muon reconstructions above 100 GeV. --- ### Deconstructing Superintelligence: Identity, Self-Modification and Différance Authors: Elija Perrier Published: 2026-04-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.19845v4 Self-modification is routinely treated as constitutive of artificial superintelligence (\textbf{SI}), yet modification is a relative action requiring a \emph{supplement} outside the operation. We formalise this on an associative operator algebra $\mathcal{A}$ with update operator $\hat U$, difference operator $\hat D$, and self-representation operator $\hat R$, identifying the supplement with $\operatorname{Comm}(\hat U)$. A propagation theorem shows $(\hat U,\hat R)$ decomposes through $(\hat U,\hat D)$, so non-commutation propagates to self-representation. The liar paradox is the rank-one case $(\hat T,Π_L)=0$, and \emph{class $\mathbf{A}$} systems, in which $\hat U$ acts on $\hat D$, reproduce it at system scale, yielding a structure coinciding with Priest's inclosure schema and Derrida's \emph{différance}. Our results show that the strong self-modification taken to define superintelligence may undermine the persistent identity upon which such systems are premised. --- ### If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems Authors: Jiamin Chang, Minhui Xue, Ruoxi Sun, Shuchao Pang, Salil S. Kanhere, Hammond Pearce Published: 2026-04-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.19844v1 Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic lights are essential in-band signals that can and should influence agent behavior. However, similar signals could also be crafted to operate as misleading visual injections, overriding user intent and posing security risks. This duality creates a fundamental challenge: agents must respond to legitimate environmental cues while remaining robust to misleading ones. We refer to this tension as trust boundary confusion. To study this behavior, we design a dual-intent dataset and evaluation framework, through which we show that current LVLM-based agents fail to reliably balance this trade-off, either ignoring useful signals or following harmful ones. We systematically evaluate 7 LVLM agents across multiple embodied settings under both structure-based and noise-based visual injections. To address these vulnerabilities, we propose a multi-agent defense framework that separates perception from decision-making to dynamically assess the reliability of visual inputs. Our approach significantly reduces misleading behaviors while preserving correct responses and provides robustness guarantees under adversarial perturbations. The code of the evaluation framework and artifacts are made available at https://anonymous.4open.science/r/Visual-Prompt-Inject. --- ### Spatio-temporal modelling of electric vehicle charging demand Authors: Kaoutar Bouaachra, Yvenn Amara-Ouali, Yannig Goude, Raphaël Lachieze-Rey Published: 2026-04-21 Categories: stat.AP, cs.LG arXiv: https://arxiv.org/abs/2604.19841v1 Accurate forecasting of electric vehicle (EV) charging demand is critical for grid management and infrastructure planning. Yet the field continues to rely on legacy benchmarks; such as the Palo Alto (2020) dataset; that fail to reflect the scale and behavioral diversity of modern charging networks. To address this, we introduce a novel large-scale longitudinal dataset collected across Scotland (2022 2025), which release it as an open benchmark for the community. Building on this dataset, we formulate EV charging demand as a spatio-temporal latent Gaussian field and perform approximate Bayesian inference via Integrated Nested Laplace Approximation (INLA). The resulting model jointly captures spatial dependence, temporal dynamics, and covariate effects within a unified proba bilistic framework. On station-level forecasting tasks, our approach achieves competitive predictive accuracy against machine learning baselines, while additionally providing principled uncertainty quan tification and interpretable spatial and temporal decompositions properties that are essential for risk-aware infrastructure planning. --- ### Graph-Theoretic Models for the Prediction of Molecular Measurements Authors: Anna Niane, Prudence Djagba Published: 2026-04-21 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2604.19840v1 Graph-theoretic approaches offer simplicity, interpretability, and low computational cost for molecular property prediction. Among these, the model proposed by Mukwembi and Nyabadza, based on the external activity $D(G)$ and internal activity $ζ(G)$ indices, achieved strong results on a small flavonoid dataset. However, its ability to generalize to larger and chemically diverse datasets has not been tested. This study evaluates the baseline $D(G)$-$ζ(G)$ polynomial model on five benchmark datasets from MoleculeNet, covering biological activity (BACE, 1,513 molecules), lipophilicity (LogP synthetic, 14,610 molecules; LogP experimental, 753 molecules), aqueous solubility (ESOL, 1,128 molecules), and hydration free energy (SAMPL, 642 molecules). The baseline model achieves an average $R^2 = 0.24$, confirming limited transferability. To address this, a systematic enhancement framework is proposed, progressively incorporating Ridge regularization, additional graph descriptors, physicochemical properties, ensemble learning with Gradient Boosting, Lasso feature selection, and a hybrid approach combining topological indices with Morgan fingerprints. The enhanced models raise the average best $R^2$ to 0.79, with individual improvements ranging from 165\% to 274\%. All improvements are statistically significant ($p < 0.001$). A direct comparison with a Graph Convolutional Network under identical experimental conditions shows that the enhanced classical models match or outperform deep learning on all five datasets. Comparison with the recent GNN+PGM hybrid of Djagba et al.\ further confirms competitiveness, with the enhanced models achieving the best results on two datasets and tying on one. The entire framework requires no GPU, trains in under five minutes, and uses only open-source tools, making it accessible for researchers in resource-limited settings. --- ### Environmental Understanding Vision-Language Model for Embodied Agent Authors: Jinsik Bang, Jaeyeon Bae, Donggyu Lee, Siyeol Jung, Taehwan Kim Published: 2026-04-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.19839v1 Vision-language models (VLMs) have shown strong perception and reasoning abilities for instruction-following embodied agents. However, despite these abilities and their generalization performance, they still face limitations in environmental understanding, often failing on interactions or relying on environment metadata during execution. To address this challenge, we propose a novel framework named Environmental Understanding Embodied Agent (EUEA), which fine-tunes four core skills: 1) object perception for identifying relevant objects, 2) task planning for generating interaction subgoals, 3) action understanding for judging success likelihood, and 4) goal recognition for determining goal completion. By fine-tuning VLMs with EUEA skills, our framework enables more reliable task execution for instruction-following. We further introduce a recovery step that leverages these core skills and a group relative policy optimization (GRPO) stage that refines inconsistent skill predictions. The recovery step samples alternative actions to correct failure cases, and the GRPO stage refines inconsistent skill predictions. Across ALFRED tasks, our VLM significantly outperforms a behavior-cloning baseline, achieving an 8.86% improvement in average success rate. The recovery and GRPO stages provide an additional 3.03% gain, further enhancing overall performance. Finally, our skill-level analyses reveal key limitations in the environmental understanding of closed- and open-source VLMs and identify the capabilities necessary for effective agent-environment interaction. --- ### Resolving space-sharing conflicts in road user interactions through uncertainty reduction: An active inference-based computational model Authors: Julian F. Schumann, Johan Engström, Ran Wei, Shu-Yuan Liu, Jens Kober, Arkady Zgonnikov Published: 2026-04-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.19838v2 Understanding how road users resolve space-sharing conflicts is important both for traffic safety and the safe deployment of autonomous vehicles. While existing models have captured specific aspects of such interactions (e.g., explicit communication), a theoretically-grounded computational framework has been lacking. In this paper, we extend a previously developed active inference-based driver behavior model to simulate interactive behavior of two agents. Our model captures three complementary mechanisms for uncertainty reduction in interaction: (i) implicit communication via direct behavioral coupling, (ii) reliance on normative expectations (stop signs, priority rules, etc.), and (iii) explicit communication. In a simplified intersection scenario, we show that normative and explicit communication cues can increase the likelihood of a successful conflict resolution. However, this relies on agents acting as expected. In situations where another agent (intentionally or unintentionally) violates normative expectations or communicates misleading information, reliance on these cues may induce collisions. These findings illustrate how active inference can provide a novel framework for modeling road user interactions which is also applicable in other fields. --- ### Forage V2: Knowledge Evolution and Transfer in Autonomous Agent Organizations Authors: Huaqing Xie Published: 2026-04-21 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.19837v1 Autonomous agents operating in open-world tasks -- where the completion boundary is not given in advance -- face denominator blindness: they systematically underestimate the scope of the target space. Forage V1 addressed this through co-evolving evaluation (an independent Evaluator discovers what "complete" means) and method isolation (Evaluator and Planner cannot see each other's code). V2 extends the architecture from a single expedition to a learning organization: experience accumulates across runs, transfers across model capabilities, and institutional safeguards prevent knowledge degradation. We demonstrate two claims across three task types (web scraping, API queries, mathematical reasoning). Knowledge accumulation: over six runs, knowledge entries grow from 0 to 54, and denominator estimates stabilize as domain understanding deepens. Knowledge transfer: a weaker agent (Sonnet) seeded with a stronger agent's (Opus) knowledge narrows a 6.6pp coverage gap to 1.1pp, halves cost (9.40 to 5.13 USD), converges in half the rounds (mean 4.5 vs. 7.0), and three independent seeded runs arrive at exactly the same denominator estimate (266), suggesting organizational knowledge calibrates evaluation itself. V2's contribution is architectural: it designs institutions -- audit separation, contract protocols, organizational memory -- that make any agent more reliable upon entry. The accumulated experience is organizational, model-agnostic, and transferable, stored as readable documents that any future agent inherits regardless of provider or capability level. --- ### Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts Authors: Chaitanya Dwivedi, Binxuan Huang, Himanshu Gupta, Pratik Jayarao, Neeraj Varshney, Bing Yin Published: 2026-04-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.19835v2 Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters from per-token computation through sparse expert routing. Scaling laws show that under fixed active computation, model quality scales predictably with total parameters, and MoEs realize this by increasing expert count. However, training large MoEs is expensive, as memory requirements and inter-device communication both scale with total parameter count. We propose expert upcycling, a method for progressively expanding MoE capacity by increasing the number of experts during continued pre-training (CPT). Given a trained E-expert model, the upcycling operator constructs an mE-expert model through expert duplication and router extension while holding top-K routing fixed, preserving per-token inference cost. Duplication provides a warm initialization: the expanded model inherits the source checkpoint's learned representations, starting from a substantially lower loss than random initialization. Subsequent CPT then breaks the symmetry among duplicated experts to drive specialization. We formalize the upcycling operator and develop a theoretical framework decomposing the quality gap into a capacity term and an initialization term. We further introduce utility-based expert selection, which uses gradient-based importance scores to guide non-uniform duplication, more than tripling gap closure when CPT is limited. In our 7B-13B total parameter experiments, the upcycled model matches the fixed-size baseline on validation loss while saving 32% of GPU hours. Comprehensive ablations across model scales, activation ratios, MoE architectures, and training budgets yield a practical recipe for deploying expert upcycling, establishing it as a principled, compute-efficient alternative to training large MoE models from scratch. --- ### KD-Judge: A Knowledge-Driven Automated Judge Framework for Functional Fitness Movements on Edge Devices Authors: Shaibal Saha, Fan Li, Yunge Li, Arun Iyengar, Lucas Alves, Lanyu Xu Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19834v2 Functional fitness movements are widely used in training, competition, and health-oriented exercise programs, yet consistently enforcing repetition (rep) standards remains challenging due to subjective human judgment, time constraints, and evolving rules. Existing AI-based approaches mainly rely on learned scoring or reference-based comparisons and lack explicit rule-based approaches, limiting transparency and deterministic rep-level validation. To address these limitations, we propose KD-Judge, a novel knowledge-driven automated judging framework for functional fitness movements. It converts unstructured rulebook standards into executable, machine-readable representations using an LLM-based retrieval-augmented generation and chain-of-thought rule-structuring pipeline. The structured rules are then incorporated by a deterministic rule-based judging system with pose-guided kinematic reasoning to assess rep validity and temporal boundaries. To improve efficiency on edge devices, including a high-performance desktop and the resource-constrained Jetson AGX Xavier, we introduce a dual strategy caching mechanism that can be selectively applied to reduce redundant and unnecessary computation. Experiments demonstrate reliable rule-structuring performance and accurate rep-level assessment, with judgment evaluation conducted on the CFRep dataset, achieving faster-than-real-time execution (real-time factor (RTF) < 1). When the proposed caching strategy is enabled, the system achieves up to 3.36x and 15.91x speedups on resource-constrained edge device compared to the non-caching baseline for pre-recorded and live-streaming scenarios, respectively. These results show that KD-Judge enables transparent, efficient, and scalable rule-grounded rep-level analysis that can complement human judging in practice. --- ### Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items Authors: Mengting Chen, Zhengrui Chen, Yongchao Du, Zuan Gao, Taihang Hu, Jinsong Lan, Chao Lin, Yefeng Shen, Xingjian Wang, Zhao Wang, Zhengtao Wu, Xiaoli Xu et al. Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19748v3 Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-world demands. We present Tstars-Tryon 1.0, a commercial-scale virtual try-on system that is robust, realistic, versatile, and highly efficient. First, our system maintains a high success rate across challenging cases like extreme poses, severe illumination variations, motion blur, and other in-the-wild conditions. Second, it delivers highly photorealistic results with fine-grained details, faithfully preserving garment texture, material properties, and structural characteristics, while largely avoiding common AI-generated artifacts. Third, beyond apparel try-on, our model supports flexible multi-image composition (up to 6 reference images) across 8 fashion categories, with coordinated control over person identity and background. Fourth, to overcome the latency bottlenecks of commercial deployment, our system is heavily optimized for inference speed, delivering near real-time generation for a seamless user experience. These capabilities are enabled by an integrated system design spanning end-to-end model architecture, a scalable data engine, robust infrastructure, and a multi-stage training paradigm. Extensive evaluation and large-scale product deployment demonstrate that Tstars-Tryon1.0 achieves leading overall performance. To support future research, we also release a comprehensive benchmark. The model has been deployed at an industrial scale on the Taobao App, serving millions of users with tens of millions of requests. --- ### AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model Authors: Yutian Chen, Shi Guo, Renbiao Jin, Tianshuo Yang, Xin Cai, Yawen Luo, Mingxin Yang, Mulin Yu, Linning Xu, Tianfan Xue Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19747v1 Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing diffusion-based approaches mitigates this issues by synthesizing novel views, but they often condition on only one or two capture frames, which restricts geometric consistency and limits scalability to large or diverse scenes. We propose AnyRecon, a scalable framework for reconstruction from arbitrary and unordered sparse inputs that preserves explicit geometric control while supporting flexible conditioning cardinality. To support long-range conditioning, our method constructs a persistent global scene memory via a prepended capture view cache, and removes temporal compression to maintain frame-level correspondence under large viewpoint changes. Beyond better generative model, we also find that the interplay between generation and reconstruction is crucial for large-scale 3D scenes. Thus, we introduce a geometry-aware conditioning strategy that couples generation and reconstruction through an explicit 3D geometric memory and geometry-driven capture-view retrieval. To ensure efficiency, we combine 4-step diffusion distillation with context-window sparse attention to reduce quadratic complexity. Extensive experiments demonstrate robust and scalable reconstruction across irregular inputs, large viewpoint gaps, and long trajectories. --- ### CityRAG: Stepping Into a City via Spatially-Grounded Video Generation Authors: Gene Chou, Charles Herrmann, Kyle Genova, Boyang Deng, Songyou Peng, Bharath Hariharan, Jason Y. Zhang, Noah Snavely, Philipp Henzler Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19741v2 We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existing video generative models can produce a plausible sequence that is consistent with a text (T2V) or image (I2V) prompt. However, the capability to reconstruct the real world under arbitrary weather conditions and dynamic object configurations is essential for downstream applications including autonomous driving and robotics simulation. To this end, we present CityRAG, a video generative model that leverages large corpora of geo-registered data as context to ground generation to the physical scene, while maintaining learned priors for complex motion and appearance changes. CityRAG relies on temporally unaligned training data, which teaches the model to semantically disentangle the underlying scene from its transient attributes. Our experiments demonstrate that CityRAG can generate coherent minutes-long, physically grounded video sequences, maintain weather and lighting conditions over thousands of frames, achieve loop closure, and navigate complex trajectories to reconstruct real-world geography. --- ### Generalization at the Edge of Stability Authors: Mario Tuci, Caner Korkmaz, Umut Şimşekli, Tolga Birdal Published: 2026-04-21 Categories: cs.LG, cs.AI, cs.CV, stat.ML arXiv: https://arxiv.org/abs/2604.19740v1 Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior. Empirically, this regime often yields improved generalization performance, yet the underlying mechanism remains poorly understood. In this work, we represent stochastic optimizers as random dynamical systems, which often converge to a fractal attractor set (rather than a point) with a smaller intrinsic dimension. Building on this connection and inspired by Lyapunov dimension theory, we introduce a novel notion of dimension, coined the `sharpness dimension', and prove a generalization bound based on this dimension. Our results show that generalization in the chaotic regime depends on the complete Hessian spectrum and the structure of its partial determinants, highlighting a complexity that cannot be captured by the trace or spectral norm considered in prior work. Experiments across various MLPs and transformers validate our theory while also providing new insights into the recently observed phenomenon of grokking. --- ### Phase Transitions in the Fluctuations of Functionals of Random Neural Networks Authors: Simmaco Di Lillo, Leonardo Maini, Domenico Marinucci Published: 2026-04-21 Categories: math.PR, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.19738v2 We establish central and non-central limit theorems for sequences of functionals of the Gaussian output of an infinitely-wide random neural network on the d-dimensional sphere . We show that the asymptotic behaviour of these functionals as the depth of the network increases depends crucially on the fixed points of the covariance function, resulting in three distinct limiting regimes: convergence to the same functional of a limiting Gaussian field, convergence to a Gaussian distribution, convergence to a distribution in the Qth Wiener chaos. Our proofs exploit tools that are now classical (Hermite expansions, Diagram Formula, Stein-Malliavin techniques), but also ideas which have never been used in similar contexts: in particular, the asymptotic behaviour is determined by the fixed-point structure of the iterative operator associated with the covariance, whose nature and stability governs the different limiting regimes. --- ### Safe Continual Reinforcement Learning in Non-stationary Environments Authors: Austin Coursey, Abel Diaz-Gonzalez, Marcos Quinones-Grueiro, Gautam Biswas Published: 2026-04-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.19737v1 Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and, therefore, struggle in real-world non-stationary deployments where system dynamics and operating conditions can change unexpectedly. Moreover, RL controllers acting in physical environments must satisfy safety constraints throughout their learning and execution phases, rendering transient violations during adaptation unacceptable. Although continual RL and safe RL have each addressed non-stationarity and safety, respectively, their intersection remains comparatively unexplored, motivating the study of safe continual RL algorithms that can adapt over the system's lifetime while preserving safety. In this work, we systematically investigate safe continual reinforcement learning by introducing three benchmark environments that capture safety-critical continual adaptation and by evaluating representative approaches from safe RL, continual RL, and their combinations. Our empirical results reveal a fundamental tension between maintaining safety constraints and preventing catastrophic forgetting under non-stationary dynamics, with existing methods generally failing to achieve both objectives simultaneously. To address this shortcoming, we examine regularization-based strategies that partially mitigate this trade-off and characterize their benefits and limitations. Finally, we outline key open challenges and research directions toward developing safe, resilient learning-based controllers capable of sustained autonomous operation in changing environments. --- ### Generative Drifting for Conditional Medical Image Generation Authors: Zirong Li, Siyuan Mei, Weiwen Wu, Andreas Maier, Lina Gölz, Yan Xia Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19736v1 Conditional medical image generation plays an important role in many clinically relevant imaging tasks. However, existing methods still face a fundamental challenge in balancing inference efficiency, patient-specific fidelity, and distribution-level plausibility, particularly in high-dimensional 3D medical imaging. In this work, we propose GDM, a generative drifting framework that reformulates deterministic medical image prediction as a multi-objective learning problem to jointly promote distribution-level plausibility and patient-specific fidelity while retaining one-step inference. GDM extends drifting to 3D medical imaging through an attractive-repulsive drift that minimizes the discrepancy between the generator pushforward and the target distribution. To enable stable drifting-based learning in 3D volumetric data, GDM constructs a multi-level feature bank from a medical foundation encoder to support reliable affinity estimation and drifting field computation across complementary global, local, and spatial representations. In addition, a gradient coordination strategy in the shared output space improves optimization balance under competing distribution-level and fidelity-oriented objectives. We evaluate the proposed framework on two representative tasks, MRI-to-CT synthesis and sparse-view CT reconstruction. Experimental results show that GDM consistently outperforms a wide range of baselines, including GAN-based, flow-matching-based, and SDE-based generative models, as well as supervised regression methods, while improving the balance among anatomical fidelity, quantitative reliability, perceptual realism, and inference efficiency. These findings suggest that GDM provides a practical and effective framework for conditional 3D medical image generation. --- ### UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling Authors: Boyu Chen, Yi Chen, Lu Qiu, Jerry Bai, Yuying Ge, Yixiao Ge Published: 2026-04-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.19734v1 Scaling humanoid foundation models is bottlenecked by the scarcity of robotic data. While massive egocentric human data offers a scalable alternative, bridging the cross-embodiment chasm remains a fundamental challenge due to kinematic mismatches. We introduce UniT (Unified Latent Action Tokenizer via Visual Anchoring), a framework that establishes a unified physical language for human-to-humanoid transfer. Grounded in the philosophy that heterogeneous kinematics share universal visual consequences, UniT employs a tri-branch cross-reconstruction mechanism: actions predict vision to anchor kinematics to physical outcomes, while vision reconstructs actions to filter out irrelevant visual confounders. Concurrently, a fusion branch synergies these purified modalities into a shared discrete latent space of embodiment-agnostic physical intents. We validate UniT across two paradigms: 1) Policy Learning (VLA-UniT): By predicting these unified tokens, it effectively leverages diverse human data to achieve state-of-the-art data efficiency and robust out-of-distribution (OOD) generalization on both humanoid simulation benchmark and real-world deployments, notably demonstrating zero-shot task transfer. 2) World Modeling (WM-UniT): By aligning cross-embodiment dynamics via unified tokens as conditions, it realizes direct human-to-humanoid action transfer. This alignment ensures that human data seamlessly translates into enhanced action controllability for humanoid video generation. Ultimately, by inducing a highly aligned cross-embodiment representation (empirically verified by t-SNE visualizations revealing the convergence of human and humanoid features into a shared manifold), UniT offers a scalable path to distill vast human knowledge into general-purpose humanoid capabilities. --- ### FASTER: Value-Guided Sampling for Fast RL Authors: Perry Dong, Alexander Swerdlow, Dorsa Sadigh, Chelsea Finn Published: 2026-04-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.19730v1 Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampling multiple action candidates and selecting the best one. In this work, we propose FASTER, a method for getting the benefits of sampling-based test-time scaling of diffusion-based policies without the computational cost by tracing the performance gain of action samples back to earlier in the denoising process. Our key insight is that we can model the denoising of multiple action candidates and selecting the best one as a Markov Decision Process (MDP) where the goal is to progressively filter action candidates before denoising is complete. With this MDP, we can learn a policy and value function in the denoising space that predicts the downstream value of action candidates in the denoising process and filters them while maximizing returns. The result is a method that is lightweight and can be plugged into existing generative RL algorithms. Across challenging long-horizon manipulation tasks in online and batch-online RL, FASTER consistently improves the underlying policies and achieves the best overall performance among the compared methods. Applied to a pretrained VLA, FASTER achieves the same performance while substantially reducing training and inference compute requirements. Code is available at https://github.com/alexanderswerdlow/faster . --- ### FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning Authors: Abdulmoneam Ali, Ahmed Arafa Published: 2026-04-21 Categories: cs.LG, cs.IT, eess.SP arXiv: https://arxiv.org/abs/2604.19729v1 Personalized Federated Learning (PFL) aims to learn multiple task-specific models rather than a single global model across heterogeneous data distributions. Existing PFL approaches typically rely on iterative optimization-such as model update trajectories-to cluster users that need to accomplish the same tasks together. However, these learning-dynamics-based methods are inherently vulnerable to low-quality data and noisy labels, as corrupted updates distort clustering decisions and degrade personalization performance. To tackle this, we propose FB-NLL, a feature-centric framework that decouples user clustering from iterative training dynamics. By exploiting the intrinsic heterogeneity of local feature spaces, FB-NLL characterizes each user through the spectral structure of the covariances of their feature representations and leverages subspace similarity to identify task-consistent user groupings. This geometry-aware clustering is label-agnostic and is performed in a one-shot manner prior to training, significantly reducing communication overhead and computational costs compared to iterative baselines. Complementing this, we introduce a feature-consistency-based detection and correction strategy to address noisy labels within clusters. By leveraging directional alignment in the learned feature space and assigning labels based on class-specific feature subspaces, our method mitigates corrupted supervision without requiring estimation of stochastic noise transition matrices. In addition, FB-NLL is model-independent and integrates seamlessly with existing noise-robust training techniques. Extensive experiments across diverse datasets and noise regimes demonstrate that our framework consistently outperforms state-of-the-art baselines in terms of average accuracy and performance stability. --- ### VLA Foundry: A Unified Framework for Training Vision-Language-Action Models Authors: Jean Mercat, Sedrick Keh, Kushal Arora, Isabella Huang, Paarth Shah, Haruki Nishimura, Shun Iwase, Katherine Liu Published: 2026-04-21 Categories: cs.RO, cs.AI, cs.CV, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2604.19728v1 We present VLA Foundry, an open-source framework that unifies LLM, VLM, and VLA training in a single codebase. Most open-source VLA efforts specialize on the action training stage, often stitching together incompatible pretraining pipelines. VLA Foundry instead provides a shared training stack with end-to-end control, from language pretraining to action-expert fine-tuning. VLA Foundry supports both from-scratch training and pretrained backbones from Hugging Face. To demonstrate the utility of our framework, we train and release two types of models: the first trained fully from scratch through our LLM-->VLM-->VLA pipeline and the second built on the pretrained Qwen3-VL backbone. We evaluate closed-loop policy performance of both models on LBM Eval, an open-data, open-source simulator. We also contribute usability improvements to the simulator and the STEP analysis tools for easier public use. In the nominal evaluation setting, our fully-open from-scratch model is on par with our prior closed-source work and substituting in the Qwen3-VL backbone leads to a strong multi-task table top manipulation policy outperforming our baseline by a wide margin. The VLA Foundry codebase is available at https://github.com/TRI-ML/vla_foundry and all multi-task model weights are released on https://huggingface.co/collections/TRI-ML/vla-foundry. Additional qualitative videos are available on the project website https://tri-ml.github.io/vla_foundry. --- ### Benign Overfitting in Adversarial Training for Vision Transformers Authors: Jiaming Zhang, Meng Ding, Shaopeng Fu, Jingfeng Zhang, Di Wang Published: 2026-04-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.19724v1 Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulnerable to adversarial examples, much like Convolutional Neural Networks (CNNs). A common empirical defense strategy is adversarial training, yet the theoretical underpinnings of its robustness in ViTs remain largely unexplored. In this work, we present the first theoretical analysis of adversarial training under simplified ViT architectures. We show that, when trained under a signal-to-noise ratio that satisfies a certain condition and within a moderate perturbation budget, adversarial training enables ViTs to achieve nearly zero robust training loss and robust generalization error under certain regimes. Remarkably, this leads to strong generalization even in the presence of overfitting, a phenomenon known as \emph{benign overfitting}, previously only observed in CNNs (with adversarial training). Experiments on both synthetic and real-world datasets further validate our theoretical findings. --- ### Adaptive MSD-Splitting: Enhancing C4.5 and Random Forests for Skewed Continuous Attributes Authors: Jake Lee Published: 2026-04-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.19722v1 The discretization of continuous numerical attributes remains a persistent computational bottleneck in the induction of decision trees, particularly as dataset dimensions scale. Building upon the recently proposed MSD-Splitting technique -- which bins continuous data using the empirical mean and standard deviation to dramatically improve the efficiency and accuracy of the C4.5 algorithm -- we introduce Adaptive MSD-Splitting (AMSD). While standard MSD-Splitting is highly effective for approximately symmetric distributions, its rigid adherence to fixed one-standard-deviation cutoffs can lead to catastrophic information loss in highly skewed data, a common artifact in real-world biomedical and financial datasets. AMSD addresses this by dynamically adjusting the standard deviation multiplier based on feature skewness, narrowing intervals in dense regions to preserve discriminative resolution. Furthermore, we integrate AMSD into ensemble methods, specifically presenting the Random Forest-AMSD (RF-AMSD) framework. Empirical evaluations on the Census Income, Heart Disease, Breast Cancer, and Forest Covertype datasets demonstrate that AMSD yields a 2-4% accuracy improvement over standard MSD-Splitting, while maintaining near-identical O(N) time complexity reductions compared to the O(N log N) exhaustive search. Our Random Forest extension achieves state-of-the-art accuracy at a fraction of standard computational costs, confirming the viability of adaptive statistical binning in large-scale ensemble learning architectures. --- ### ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis Authors: Zhengwentai Sun, Keru Zheng, Chenghong Li, Hongjie Liao, Xihe Yang, Heyuan Li, Yihao Zhi, Shuliang Ning, Shuguang Cui, Xiaoguang Han Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19720v1 Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods often address these factors separately, resulting in limited controllability or reduced visual quality. We revisit this problem from an image-first perspective, where high-quality human appearance is learned via image generation and used as a prior for video synthesis, decoupling appearance modeling from temporal consistency. We propose a pose- and viewpoint-controllable pipeline that combines a pretrained image backbone with SMPL-X-based motion guidance, together with a training-free temporal refinement stage based on a pretrained video diffusion model. Our method produces high-quality, temporally consistent videos under diverse poses and viewpoints. We also release a canonical human dataset and an auxiliary model for compositional human image synthesis. Code and data are publicly available at https://github.com/Taited/ReImagine. --- ### Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views Authors: Feihao Fang, My T. Thai, Yuanyuan Lei Published: 2026-04-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.19716v1 Large Language Models (LLMs) still struggle with multi-step logical reasoning. Existing approaches either purely refine the reasoning chain in natural language form or attach a symbolic solver as an external module. In this work, we instead ask whether LLMs contain a shared internal logical subspace that simultaneously aligns natural-language and symbolic-language views of the reasoning process. Our hypothesis is that this logical subspace captures logical reasoning capabilities in LLMs that are shared across views while remaining independent of surface forms. To verify this, we employ Canonical Correlation Analysis on the paired residual activations from natural-language and symbolic-language reasoning chains, learning a low-dimensional subspace with maximum cross-view correlation. Furthermore, we design a training-free approach that steers LLMs reasoning chain along this logical subspace, thereby leveraging the complementary reasoning signals from both views. Experiments on four logical reasoning benchmarks demonstrate the effectiveness of our approach, improving accuracy by up to 11 percentage points and generalizing well on out-of-domain problems. --- ### A Network-Aware Evaluation of Distributed Energy Resource Control in Smart Distribution Systems Authors: Houchao Gan Published: 2026-04-21 Categories: cs.CV, eess.SY arXiv: https://arxiv.org/abs/2604.19715v1 Distribution networks with high penetration of Distributed Energy Resources (DERs) increasingly rely on communication networks to coordinate grid-interactive control. While many distributed control schemes have been proposed, they are often evaluated under idealized communication assumptions, making it difficult to assess their performance under realistic network conditions. This work presents an implementation-driven evaluation of a representative virtual power plant (VPP) dispatch algorithm using a co-simulation framework that couples a linearized distribution-system model with packet-level downlink emulation in ns-3. The study considers a modified IEEE~37-node feeder with high photovoltaic penetration and a primal--dual VPP dispatch that simultaneously targets feeder-head active power tracking and voltage regulation. Communication effects are introduced only on the downlink path carrying dual-variable updates, where per-DER packet delays and a hold-last-value strategy are modeled. Results show that, under ideal communication, the dispatch achieves close tracking of the feeder-head power reference while maintaining voltages within the prescribed limits at selected buses. When realistic downlink delay is introduced, the same controller exhibits large oscillations in feeder-head power and more frequent voltage limit violations. These findings highlight that distributed DER control performance can be strongly influenced by communication behavior and motivate evaluation frameworks that explicitly incorporate network dynamics into the assessment of grid-interactive control schemes. --- ### Ultrametric OGP - parametric RDT \emph{symmetric} binary perceptron connection Authors: Mihailo Stojnic Published: 2026-04-21 Categories: cs.LG, cond-mat.dis-nn, cs.IT, math.PR, stat.ML arXiv: https://arxiv.org/abs/2604.19712v1 In (97,99,100), an fl-RDT framework is introduced to characterize \emph{statistical computational gaps} (SCGs). Studying \emph{symmetric binary perceptrons} (SBPs), (100) obtained an \emph{algorithmic} threshold estimate $α_a\approx α_c^{(7)}\approx 1.6093$ at the 7th lifting level (for $κ=1$ margin), closely approaching $1.58$ local entropy (LE) prediction (18). In this paper, we further connect parametric RDT to overlap gap properties (OGPs), another key geometric feature of the solution space. Specifically, for any positive integer $s$, we consider $s$-level ultrametric OGPs ($ult_s$-OGPs) and rigorously upper-bound the associated constraint densities $α_{ult_s}$. To achieve this, we develop an analytical union-bounding program consisting of combinatorial and probabilistic components. By casting the combinatorial part as a convex problem and the probabilistic part as a nested integration, we conduct numerical evaluations and obtain that the tightest bounds at the first two levels, $\barα_{ult_1} \approx 1.6578$ and $\barα_{ult_2} \approx 1.6219$, closely approach the 3rd and 4th lifting level parametric RDT estimates, $α_c^{(3)} \approx 1.6576$ and $α_c^{(4)} \approx 1.6218$. We also observe excellent agreement across other key parameters, including overlap values and the relative sizes of ultrametric clusters. Based on these observations, we propose several conjectures linking $ult$-OGP and parametric RDT. Specifically, we conjecture that algorithmic threshold $α_a=\lim_{s\rightarrow\infty} α_{ult_s} = \lim_{s\rightarrow\infty} \barα{ult_s} = \lim_{r\rightarrow\infty} α_{c}^{(r)}$, and $α_{ult_s} \leq α_{c}^{(s+2)}$ (with possible equality for some (maybe even all) $s$). Finally, we discuss the potential existence of a full isomorphism connecting all key parameters of $ult$-OGP and parametric RDT. --- ### SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model Authors: Zewei Zhou, Ruining Yang, Xuewei, Qi, Yiluan Guo, Sherry X. Chen, Tao Feng, Kateryna Pistunova, Yishan Shen, Lili Su, Jiaqi Ma Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19710v1 Vision-Language-Action (VLA) models offer a promising autonomous driving paradigm for leveraging world knowledge and reasoning capabilities, especially in long-tail scenarios. However, existing VLA models often struggle with the high latency in action generation using an autoregressive generation framework and exhibit limited robustness. In this paper, we propose SpanVLA, a novel end-to-end autonomous driving framework, integrating an autoregressive reasoning and a flow-matching action expert. First, SpanVLA introduces an efficient bridge to leverage the vision and reasoning guidance of VLM to efficiently plan future trajectories using a flow-matching policy conditioned on historical trajectory initialization, which significantly reduces inference time. Second, to further improve the performance and robustness of the SpanVLA model, we propose a GRPO-based post-training method to enable the VLA model not only to learn from positive driving samples but also to learn how to avoid the typical negative behaviors and learn recovery behaviors. We further introduce mReasoning, a new real-world driving reasoning dataset, focusing on complex, reasoning-demanding scenarios and negative-recovery samples. Extensive experiments on the NAVSIM (v1 and v2) demonstrate the competitive performance of the SpanVLA model. Additionally, the qualitative results across diverse scenarios highlight the planning performance and robustness of our model. --- ### Face Anything: 4D Face Reconstruction from Any Image Sequence Authors: Umut Kocasari, Simon Giebenhain, Richard Shaw, Matthias Nießner Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19702v2 Accurate reconstruction and tracking of dynamic human faces from image sequences is challenging because non-rigid deformations, expression changes, and viewpoint variations occur simultaneously, creating significant ambiguity in geometry and correspondence estimation. We present a unified method for high-fidelity 4D facial reconstruction based on canonical facial point prediction, a representation that assigns each pixel a normalized facial coordinate in a shared canonical space. This formulation transforms dense tracking and dynamic reconstruction into a canonical reconstruction problem, enabling temporally consistent geometry and reliable correspondences within a single feed-forward model. By jointly predicting depth and canonical coordinates, our method enables accurate depth estimation, temporally stable reconstruction, dense 3D geometry, and robust facial point tracking within a single architecture. We implement this formulation using a transformer-based model that jointly predicts depth and canonical facial coordinates, trained using multi-view geometry data that non-rigidly warps into the canonical space. Extensive experiments on image and video benchmarks demonstrate state-of-the-art performance across reconstruction and tracking tasks, achieving approximately 3$\times$ lower correspondence error and faster inference than prior dynamic reconstruction methods, while improving depth accuracy by 16%. These results highlight canonical facial point prediction as an effective foundation for unified feed-forward 4D facial reconstruction. --- ### Epistemic orientation in parliamentary discourse is associated with deliberative democracy Authors: Segun Aroyehun, Stephan Lewandowsky, David Garcia Published: 2026-04-21 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2604.19699v3 The pursuit of truth is central to democratic deliberation and governance, yet political discourse reflects varying epistemic orientations, ranging from evidence-based reasoning grounded in verifiable information to intuition-based reasoning rooted in beliefs and subjective interpretation. We introduce a scalable approach to measure epistemic orientation using the Evidence--Minus--Intuition (EMI) score, derived from large language model (LLM) ratings and embedding-based semantic similarity. Applying this approach to 15 million parliamentary speech segments spanning 1946 to 2025 across seven countries, we examine temporal patterns in discourse and its association with deliberative democracy and governance. We find that EMI is positively associated with deliberative democracy within countries over time, with consistent relationships in both contemporaneous and lagged analyses. EMI is also positively associated with the transparency and predictable implementation of laws as a dimension of governance. These findings suggest that the epistemic nature of political discourse is crucial for both the quality of democracy and governance. --- ### On two ways to use determinantal point processes for Monte Carlo integration Authors: Guillaume Gautier, Rémi Bardenet, Michal Valko Published: 2026-04-21 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2604.19698v1 The standard Monte Carlo estimator $\widehat{I}_N^{\mathrm{MC}}$ of $\int fdω$ relies on independent samples from $ω$ and has variance of order $1/N$. Replacing the samples with a determinantal point process (DPP), a repulsive distribution, makes the estimator consistent, with variance rates that depend on how the DPP is adapted to $f$ and $ω$. We examine two existing DPP-based estimators: one by Bardenet & Hardy (2020) with a rate of $\mathcal{O}(N^{-(1+1/d)})$ for smooth $f$, but relying on a fixed DPP. The other, by Ermakov & Zolotukhin (1960), is unbiased with rate of order $1/N$, like Monte Carlo, but its DPP is tailored to $f$. We revisit these estimators, generalize them to continuous settings, and provide sampling algorithms. --- ### Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks Authors: Jing Jin, Hao Liu, Yan Bai, Yihang Lou, Zhenke Wang, Tianrun Yuan, Juntong Chen, Yongkang Zhu, Fanhu Zeng, Xuanyu Zhu, Tao Feng, Yige Xu Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19697v2 Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly verifiable feedback, but existing benchmarks often permit unimodal shortcuts due to modality redundancy and focus mainly on final-answer accuracy, overlooking the reasoning process itself. To address this challenge, we introduce StepSTEM: a graduate-level benchmark of 283 problems across mathematics, physics, chemistry, biology, and engineering for fine-grained evaluation of cross-modal reasoning in MLLMs. StepSTEM is constructed through a rigorous curation pipeline that enforces strict complementarity between textual and visual inputs. We further propose a general step-level evaluation framework for both text-only chain-of-thought and interleaved image-text reasoning, using dynamic programming to align predicted reasoning steps with multiple reference solutions. Experiments across a wide range of models show that current MLLMs still rely heavily on textual reasoning, with even Gemini 3.1 Pro and Claude Opus 4.6 achieving only 38.29% accuracy. These results highlight substantial headroom for genuine cross-modal STEM reasoning and position StepSTEM as a benchmark for fine-grained evaluation of multimodal reasoning. Source code is available at https://github.com/lll-hhh/STEPSTEM. --- ### Planning in entropy-regularized Markov decision processes and games Authors: Jean-Bastien Grill, Omar Darwiche Domingues, Pierre Ménard, Rémi Munos, Michal Valko Published: 2026-04-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.19695v1 We propose SmoothCruiser, a new planning algorithm for estimating the value function in entropy-regularized Markov decision processes and two-player games, given a generative model of the environment. SmoothCruiser makes use of the smoothness of the Bellman operator promoted by the regularization to achieve problem-independent sample complexity of order O~(1/epsilon^4) for a desired accuracy epsilon, whereas for non-regularized settings there are no known algorithms with guaranteed polynomial sample complexity in the worst case. --- ### A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding Authors: Shuai Wang, Hongyi Zhu, Jia-Hong Huang, Yixian Shen, Chengxi Zeng, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring Published: 2026-04-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.19689v1 Understanding artworks requires multi-step reasoning over visual content and cultural, historical, and stylistic context. While recent multimodal large language models show promise in artwork explanation, they rely on implicit reasoning and internalized knowl- edge, limiting interpretability and explicit evidence grounding. We propose A-MAR, an Agent-based Multimodal Art Retrieval framework that explicitly conditions retrieval on structured reasoning plans. Given an artwork and a user query, A-MAR first decomposes the task into a structured reasoning plan that specifies the goals and evidence requirements for each step. Retrieval is then conditionedon this plan, enabling targeted evidence selection and supporting step-wise, grounded explanations. To evaluate agent-based multi- modal reasoning within the art domain, we introduce ArtCoT-QA. This diagnostic benchmark features multi-step reasoning chains for diverse art-related queries, enabling a granular analysis that extends beyond simple final answer accuracy. Experiments on SemArt and Artpedia show that A-MAR consistently outperforms static, non planned retrieval and strong MLLM baselines in final explanation quality, while evaluations on ArtCoT-QA further demonstrate its advantages in evidence grounding and multi-step reasoning ability. These results highlight the importance of reasoning-conditioned retrieval for knowledge-intensive multimodal understanding and position A-MAR as a step toward interpretable, goal-driven AI systems, with particular relevance to cultural industries. The code and data are available at: https://github.com/ShuaiWang97/A-MAR. --- ### An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA Authors: Saransh Sharma, Pritika Ramu, Aparna Garimella, Koyel Mukherjee Published: 2026-04-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.19685v1 Answering open-ended questions remains challenging for AI systems because it requires synthesis, judgment, and exploration beyond factual retrieval, and users often refine answers through multiple iterations rather than accepting a single response. Existing QA benchmarks do not explicitly support this refinement process. To address this gap, we introduce a new task, document-grounded related insight generation, where the goal is to generate additional insights from a document collection that help improve, extend, or rethink an initial answer to an open-ended question, ultimately supporting richer user interaction and a better overall question answering experience. We curate and release SCOpE-QA (Scientific Collections for Open-Ended QA), a dataset of 3,000 open-ended questions across 20 research collections. We present InsightGen, a two-stage approach that first constructs a thematic representation of the document collection using clustering, and then selects related context based on neighborhood selection from the thematic graph to generate diverse and relevant insights using LLMs. Extensive evaluation on 3,000 questions using two generation models and two evaluation settings shows that InsightGen consistently produces useful, relevant, and actionable insights, establishing a strong baseline for this new task. --- ### PREF-XAI: Preference-Based Personalized Rule Explanations of Black-Box Machine Learning Models Authors: Salvatore Greco, Jacek Karolczak, Roman Słowiński, Jerzy Stefanowski Published: 2026-04-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.19684v1 Explainable artificial intelligence (XAI) has predominantly focused on generating model-centric explanations that approximate the behavior of black-box models. However, such explanations often overlook a fundamental aspect of interpretability: different users require different explanations depending on their goals, preferences, and cognitive constraints. Although recent work has explored user-centric and personalized explanations, most existing approaches rely on heuristic adaptations or implicit user modeling, lacking a principled framework for representing and learning individual preferences. In this paper, we consider Preference-Based Explainable Artificial Intelligence (PREF-XAI), a novel perspective that reframes explanation as a preference-driven decision problem. Within PREF-XAI, explanations are not treated as fixed outputs, but as alternatives to be evaluated and selected according to user-specific criteria. In the PREF-XAI perspective, here we propose a methodology that combines rule-based explanations with formal preference learning. User preferences are elicited through a ranking of a small set of candidate explanations and modeled via an additive utility function inferred using robust ordinal regression. Experimental results on real-world datasets show that PREF-XAI can accurately reconstruct user preferences from limited feedback, identify highly relevant explanations, and discover novel explanatory rules not initially considered by the user. Beyond the proposed methodology, this work establishes a connection between XAI and preference learning, opening new directions for interactive and adaptive explanation systems. --- ### IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow Authors: Zihao Fan, Xin Lu, Jie Xiao, Dong Li, Jie Huang, Xueyang Fu Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19680v1 In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from inefficient multi-step sampling and noise-residual coupling. To address this dilemma, we propose IR-Flow, a novel image restoration method based on Rectified Flow that serves as a unified framework bridging the gap between discriminative and generative paradigms. Specifically, we first construct multilevel data distribution flows, which expand the ability of models to learn from and adapt to various levels of degradation. Subsequently, cumulative velocity fields are proposed to learn transport trajectories across varying degradation levels, guiding intermediate states toward the clean target, while a multi-step consistency constraint is presented to enforce trajectory coherence and boost few-step restoration performance. We show that directly establishing a linear transport flow between degraded and clean image domains not only enables fast inference but also improves adaptability to out-of-distribution degradations. Extensive evaluations on deraining, denoising and raindrop removal tasks demonstrate that IR-Flow achieves competitive quantitative results with only a few sampling steps, offering an efficient and flexible framework that maintains an excellent distortion-perception balance. Our code is available at https://github.com/fanzh03/IR-Flow. --- ### MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation Authors: Liyang Li, Wen Wang, Canyu Zhao, Tianjian Feng, Zhiyue Zhao, Hao Chen, Chunhua Shen Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19679v3 Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within a single model. However, existing controllable generation frameworks are typically restricted to video-only control. This restricts comprehensive controllability and often leads to suboptimal cross-modal alignment. To bridge this gap, we present MMControl, which enables users to perform Multi-Modal Control in joint audio-video generation. MMControl introduces a dual-stream conditional injection mechanism. It incorporates both visual and acoustic control signals, including reference images, reference audio, depth maps, and pose sequences, into a joint generation process. These conditions are injected through bypass branches into a joint audio-video Diffusion Transformer, enabling the model to simultaneously generate identity-consistent video and timbre-consistent audio under structural constraints. Furthermore, we introduce modality-specific guidance scaling, which allows users to independently and dynamically adjust the influence strength of each visual and acoustic condition at inference time. Extensive experiments demonstrate that MMControl achieves fine-grained, composable control over character identity, voice timbre, body pose, and scene layout in joint audio-video generation. --- ### Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation Authors: Nurkhan Laiyk, Gerard I. Gállego, Javier Ferrando, Fajri Koto Published: 2026-04-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.19678v2 Function vectors (FVs) are vector representations of tasks extracted from model activations during in-context learning. While prior work has shown that multilingual model representations can be language-agnostic, it remains unclear whether the same holds for function vectors. We study whether FVs exhibit language-agnosticity, using machine translation as a case study. Across three decoder-only multilingual LLMs, we find that translation FVs extracted from a single English$\to$X direction transfer to other target languages, consistently improving the rank of correct translation tokens across multiple unseen languages. We further find that the highest-gain tokens span multiple languages and that translation FVs across directions share most of their top-ranked heads, indicating that the FV encodes a largely language-agnostic translation signal rather than a language-pair-specific mapping. --- ### Learning Hybrid-Control Policies for High-Precision In-Contact Manipulation Under Uncertainty Authors: Hunter L. Brown, Geoffrey Hollinger, Stefan Lee Published: 2026-04-21 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.19677v1 Reinforcement learning-based control policies have been frequently demonstrated to be more effective than analytical techniques for many manipulation tasks. Commonly, these methods learn neural control policies that predict end-effector pose changes directly from observed state information. For tasks like inserting delicate connectors which induce force constraints, pose-based policies have limited explicit control over force and rely on carefully tuned low-level controllers to avoid executing damaging actions. In this work, we present hybrid position-force control policies that learn to dynamically select when to use force or position control in each control dimension. To improve learning efficiency of these policies, we introduce Mode-Aware Training for Contact Handling (MATCH) which adjusts policy action probabilities to explicitly mirror the mode selection behavior in hybrid control. We validate MATCH's learned policy effectiveness using fragile peg-in-hole tasks under extreme localization uncertainty. We find MATCH substantially outperforms pose-control policies -- solving these tasks with up to 10% higher success rates and 5x fewer peg breaks than pose-only policies under common types of state estimation error. MATCH also demonstrates data efficiency equal to pose-control policies, despite learning in a larger and more complex action space. In over 1600 sim-to-real experiments, we find MATCH succeeds twice as often as pose policies in high noise settings (33% vs.~68%) and applies ~30% less force on average compared to variable impedance policies on a Franka FR3 in laboratory conditions. --- ### MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention Authors: Zhi Chen, Runze Hu, Le Zhang Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19675v2 Flow matching has recently emerged as a principled framework for learning continuous-time transport maps, enabling efficient ODE-based sampling without relying on stochastic diffusion processes. While generative modeling has shown promise for medical image segmentation, particularly in capturing uncertainty and complex anatomical variability, existing approaches are predominantly based on diffusion models, which require iterative sampling and incur substantial computational overhead. In this work, we propose MedFlowSeg, a conditional flow matching framework that formulates medical image segmentation as learning a time-dependent vector field that transports a simple prior distribution to the target segmentation distribution. Compared to diffusion-based methods, our formulation enables more efficient inference through solving an ordinary differential equation, while preserving the flexibility of generative modeling. To effectively incorporate conditional information, we introduce a dual-conditioning mechanism. Specifically, we propose a Dual-Branch Spatial Attention (DB-SA) module to inject multi-frequency structural priors, and a Frequency-Aware Attention (FA-Attention) module to model interactions between spatial and spectral representations via discrepancy-aware fusion and time-dependent modulation. These components improve the alignment between noisy intermediate states and clean semantic features, leading to better structural consistency and boundary delineation. We conduct extensive experiments across multiple medical imaging modalities, where MedFlowSeg consistently outperforms prior state-of-the-art (SOTA) baselines, including diffusion-based and flow-based methods. --- ### InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement Authors: Nikita Kister, Pradyumna YM, István Sárándi, Jiayi Wang, Anna Khoreva, Gerard Pons-Moll Published: 2026-04-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.19673v2 Training embodied agents to understand 3D scenes as humans do requires large-scale data of people meaningfully interacting with diverse environments, yet such data is scarce. Real-world capture is costly and limited to controlled settings, while existing synthetic datasets rely on simple geometric heuristics, ignoring rich scene context. In contrast, 2D foundation models trained at internet scale have acquired commonsense knowledge of human-environment interactions. To transfer this knowledge to 3D, we introduce InHabit, an automatic and scalable data generator for populating 3D scenes with interacting humans. InHabit follows a render-generate-lift principle: given a rendered 3D scene, a vision-language model proposes contextually meaningful actions, an image-editing model inserts a human, and an optimization procedure lifts the edited result into physically plausible SMPL-X bodies aligned with the scene geometry. Applied to Habitat-Matterport3D, InHabit produces InHabitants, the first large-scale photorealistic 3D human-scene interaction dataset, with 78K samples across $\sim$800 building-scale scenes with complete 3D geometry, SMPL-X bodies, and images. Augmenting standard training data with InHabitants improves RGB-based 3D human-scene reconstruction and contact estimation, and in a perceptual user study our data is preferred in 78% of cases over prior art. --- ### Budgeted Online Influence Maximization Authors: Pierre Perrault, Jennifer Healey, Zheng Wen, Michal Valko Published: 2026-04-21 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.19672v1 We introduce a new budgeted framework for online influence maximization, considering the total cost of an advertising campaign instead of the common cardinality constraint on a chosen influencer set. Our approach better models the real-world setting where the cost of influencers varies and advertisers want to find the best value for their overall social advertising budget. We propose an algorithm assuming an independent cascade diffusion model and edge level semi-bandit feedback, and provide both theoretical and experimental results. Our analysis is also valid for the cardinality constraint setting and improves the state of the art regret bound in this case. --- ### Multi-Cycle Spatio-Temporal Adaptation in Human-Robot Teaming Authors: Alex Cuellar, Michael Hagenow, Julie Shah Published: 2026-04-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.19670v1 Effective human-robot teaming is crucial for the practical deployment of robots in human workspaces. However, optimizing joint human-robot plans remains a challenge due to the difficulty of modeling individualized human capabilities and preferences. While prior research has leveraged the multi-cycle structure of domains like manufacturing to learn an individual's tendencies and adapt plans over repeated interactions, these techniques typically consider task-level and motion-level adaptation in isolation. Task-level methods optimize allocation and scheduling but often ignore spatial interference in close-proximity scenarios; conversely, motion-level methods focus on collision avoidance while ignoring the broader task context. This paper introduces RAPIDDS, a framework that unifies these approaches by modeling an individual's spatial behavior (motion paths) and temporal behavior (time required to complete tasks) over multiple cycles. RAPIDDS then jointly adapts task schedules and steers diffusion models of robot motions to maximize efficiency and minimize proximity accounting for these individualized models. We demonstrate the importance of this dual adaptation through an ablation study in simulation and a physical robot scenario using a 7-DOF robot arm. Finally, we present a user study (n=32) showing significant plan improvement compared to non-adaptive systems across both objective metrics, such as efficiency and proximity, and subjective measures, including fluency and user preference. See this paper's companion video at: https://youtu.be/55Q3lq1fINs. --- ### HardNet++: Nonlinear Constraint Enforcement in Neural Networks Authors: Andrea Goertzen, Kaveh Alim, Youngjae Min, Navid Azizan Published: 2026-04-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.19669v2 Enforcing constraint satisfaction in neural network outputs is critical for safety, reliability, and physical fidelity in many control and decision-making applications. While soft-constrained methods penalize constraint violations during training, they do not guarantee constraint adherence during inference. Other approaches guarantee constraint satisfaction via a projection layer, but often rely on the existence of a tractable projection onto the feasible set, limiting their utility in more general problem settings. Many real-world problems of interest are nonlinear and lack the special structure admitting a tractable projection, motivating the development of methods that can enforce general nonlinear constraints. To this end, we introduce HardNet++, a constraint-satisfaction method that enforces linear and nonlinear equality and inequality constraints. Our approach iteratively adjusts the network output via damped local linearizations of the constraints. Each iteration is differentiable, admitting an end-to-end training framework, where the constraint satisfaction layer is active during training. We show that under certain regularity conditions, this procedure enforces nonlinear constraint satisfaction to arbitrary tolerance. Finally, we demonstrate tight constraint adherence without loss of optimality in a learning-for-optimization context, where we apply this method to a nonlinear model predictive control problem. --- ### Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language Authors: Yi Zhong, Buqiang Xu, Yijun Wang, Zifei Shan, Shuofei Qiao, Guozhou Zheng, Ningyu Zhang Published: 2026-04-21 Categories: cs.CL, cs.AI, cs.CV, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2604.19667v2 At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely constructed through manual engineering: developers must carefully design workflows, write prompts for each step, and repeatedly revise the logic as requirements evolve -- making development costly, time-consuming, and error-prone. To study whether large language models can automate this multi-round interaction process, we introduce Chat2Workflow, a benchmark for generating executable visual workflows directly from natural language, and propose a robust agentic baseline to improve performance. The benchmark is built from a large collection of real-world business workflows, with each instance designed so that the generated workflow can be transformed and directly deployed to practical workflow platforms such as Dify and Coze. Experimental results show that while state-of-the-art language models can often capture high-level intent, they struggle to generate correct, stable, and executable workflows, especially given complex and evolving requirements. Although our agentic baseline yields up to 6.05% resolve rate gains, the remaining real-world gap positions Chat2Workflow as a foundation for advancing industrial-grade automation. Code is available at https://github.com/zjunlp/Chat2Workflow. --- ### From Top-1 to Top-K: A Reproducibility Study and Benchmarking of Counterfactual Explanations for Recommender Systems Authors: Quang-Huy Nguyen, Thanh-Hai Nguyen, Khac-Manh Thai, Duc-Hoang Pham, Huy-Son Nguyen, Cam-Van Thi Nguyen, Masoud Mansoury, Duc-Trong Le, Hoang-Quynh Le Published: 2026-04-21 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.19663v1 Counterfactual explanations (CEs) provide an intuitive way to understand recommender systems by identifying minimal modifications to user-item interactions that alter recommendation outcomes. Existing CE methods for recommender systems, however, have been evaluated under heterogeneous protocols, using different datasets, recommenders, metrics, and even explanation formats, which hampers reproducibility and fair comparison. Our paper systematically reproduces, re-implement, and re-evaluate eleven state-of-the-art CE methods for recommender systems, covering both native explainers (e.g., LIME-RS, SHAP, PRINCE, ACCENT, LXR, GREASE) and specific graph-based explainers originally proposed for GNNs. Here, a unified benchmarking framework is proposed to assess explainers along three dimensions: explanation format (implicit vs. explicit), evaluation level (item-level vs. list-level), and perturbation scope (user interaction vectors vs. user-item interaction graphs). Our evaluation protocol includes effectiveness, sparsity, and computational complexity metrics, and extends existing item-level assessments to top-K list-level explanations. Through extensive experiments on three real-world datasets and six representative recommender models, we analyze how well previously reported strengths of CE methods generalize across diverse setups. We observe that the trade-off between effectiveness and sparsity depends strongly on the specific method and evaluation setting, particularly under the explicit format; in addition, explainer performance remains largely consistent across item level and list level evaluations, and several graph-based explainers exhibit notable scalability limitations on large recommender graphs. Our results refine and challenge earlier conclusions about the robustness and practicality of CE generation methods in recommender systems: https://github.com/L2R-UET/CFExpRec. --- ### Disentangling Damage from Operational Variability: A Label-Free Self-Supervised Representation Learning Framework for Output-Only Structural Damage Identification Authors: Xudong Jian, Charikleia Stoura, Simon Scandella, Eleni Chatzi Published: 2026-04-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.19658v1 Damage identification is a core task in structural health monitoring. In practice, however, its reliability is often compromised by confounding non-damage effects, such as variations in excitation and environmental conditions, which can induce changes comparable to or larger than those caused by structural damage. To address this challenge, this study proposes a self-supervised label-free disentangled representation learning framework for robust vibration-based structural damage identification. The proposed framework employs an autoencoder with two latent representations to learn directly from raw vibration acceleration signals. A self-supervised invariance regularization, implemented via Variance-Invariance-Covariance Regularization (VICReg), is imposed on one latent representation using baseline data where structural damage is assumed constant but operational and environmental conditions vary. In addition, a frequency-domain constraint is introduced to enforce agreement between the power spectral density reconstructed from the latent representation and that computed from the corresponding input time series. Together, these mechanisms promote disentanglement, enabling the learned representation to be sensitive to damage-related characteristics while remaining invariant to nuisance variability. The framework is trained in a fully end-to-end and label-free manner, requiring no prior information on damage, excitation, or environmental conditions, making it well-suited for real-world applications. Its effectiveness is validated on two distinct real-world vibration datasets, including a bridge and a gearbox. The results demonstrate robustness to operational variability, strong generalization capability, and good performance in both damage detection and quantification. ---