# Research Papers — 2026-04 · bundle page 172 of 233 > Full-text markdown of papers #8551–8600 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/172 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/171.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/173.md) ### Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation Authors: Qian Ma, Sarah Rajtmajer Published: 2026-04-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.07486v3 Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy and utility. We propose Realistic and Privacy-Preserving Synthetic Data Generation (RPSG), which uses private seeds and integrates privacy-preserving strategies, including a formal differential privacy (DP) mechanism in the candidate selection, to generate realistic synthetic data. Comprehensive experiments against state-of-the-art private synthetic data generation methods demonstrate that RPSG achieves high fidelity to private data while providing strong privacy protection. --- ### ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training Authors: Yu Liang, Liangxin Liu, Longzheng Wang, Yan Wang, Yueyang Zhang, Long Xia, Zhiyuan Sun, Daiting Shi Published: 2026-04-08 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.07484v2 Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering greater representational capacity and flexibility than traditional scalar reward models. However, GRMs face two major challenges: reliance on costly human-annotated data restricts scalability, and self-training approaches often suffer from instability and vulnerability to reward hacking. To address these issues, we propose ConsistRM, a self-training framework that enables effective and stable GRM training without human annotations. ConsistRM incorporates the Consistency-Aware Answer Reward, which produces reliable pseudo-labels with temporal consistency, thereby providing more stable model optimization. Moreover, the Consistency-Aware Critique Reward is introduced to assess semantic consistency across multiple critiques and allocates fine-grained and differentiated rewards. Experiments on five benchmark datasets across four base models demonstrate that ConsistRM outperforms vanilla Reinforcement Fine-Tuning (RFT) by an average of 1.5%. Further analysis shows that ConsistRM enhances output consistency and mitigates position bias caused by input order, highlighting the effectiveness of consistency-aware rewards in improving GRMs. Our implementation is available at https://github.com/yuliangCarmelo/ConsistRM. --- ### Active Reward Machine Inference From Raw State Trajectories Authors: Mohamad Louai Shehab, Antoine Aspeel, Necmiye Ozay Published: 2026-04-08 Categories: cs.RO, cs.AI, cs.FL arXiv: https://arxiv.org/abs/2604.07480v1 Reward machines are automaton-like structures that capture the memory required to accomplish a multi-stage task. When combined with reinforcement learning or optimal control methods, they can be used to synthesize robot policies to achieve such tasks. However, specifying a reward machine by hand, including a labeling function capturing high-level features that the decisions are based on, can be a daunting task. This paper deals with the problem of learning reward machines directly from raw state and policy information. As opposed to existing works, we assume no access to observations of rewards, labels, or machine nodes, and show what trajectory data is sufficient for learning the reward machine in this information-scarce regime. We then extend the result to an active learning setting where we incrementally query trajectory extensions to improve data (and indirectly computational) efficiency. Results are demonstrated with several grid world examples. --- ### SMFD-UNet: Semantic Face Mask Is The Only Thing You Need To Deblur Faces Authors: Abduz Zami Published: 2026-04-08 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2604.07477v1 For applications including facial identification, forensic analysis, photographic improvement, and medical imaging diagnostics, facial image deblurring is an essential chore in computer vision allowing the restoration of high-quality images from blurry inputs. Often based on general picture priors, traditional deblurring techniques find it difficult to capture the particular structural and identity-specific features of human faces. We present SMFD-UNet (Semantic Mask Fusion Deblurring UNet), a new lightweight framework using semantic face masks to drive the deblurring process, therefore removing the need for high-quality reference photos in order to solve these difficulties. First, our dual-step method uses a UNet-based semantic mask generator to directly extract detailed facial component masks (e.g., eyes, nose, mouth) straight from blurry photos. Sharp, high-fidelity facial images are subsequently produced by integrating these masks with the blurry input using a multi-stage feature fusion technique within a computationally efficient UNet framework. We created a randomized blurring pipeline that roughly replicates real-world situations by simulating around 1.74 trillion deterioration scenarios, hence guaranteeing resilience. Examined on the CelebA dataset, SMFD-UNet shows better performance than state-of-the-art models, attaining higher Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) while preserving satisfactory naturalness measures, including NIQE, LPIPS, and FID. Powered by Residual Dense Convolution Blocks (RDC), a multi-stage feature fusion strategy, efficient and effective upsampling techniques, attention techniques like CBAM, post-processing techniques, and the lightweight design guarantees scalability and efficiency, enabling SMFD-UNet to be a flexible solution for developing facial image restoration research and useful applications. --- ### When Switching Algorithms Helps: A Theoretical Study of Online Algorithm Selection Authors: Denis Antipov, Carola Doerr Published: 2026-04-08 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2604.07473v1 Online algorithm selection (OAS) aims to adapt the optimization process to changes in the fitness landscape and is expected to outperform any single algorithm from a given portfolio. Although this expectation is supported by numerous empirical studies, there are currently no theoretical results proving that OAS can yield asymptotic speedups (apart from some artificial examples for hyper-heuristics). Moreover, theory-based guidelines for when and how to switch between algorithms are largely missing. In this paper, we present the first theoretical example in which switching between two algorithms -- the $(1+λ)$ EA and the $(1+(λ,λ))$ GA -- solves the OneMax problem asymptotically faster than either algorithm used in isolation. We show that an appropriate choice of population sizes for the two algorithms allows the optimum to be reached in $O(n\log\log n)$ expected time, faster than the $Θ(n\sqrt{\frac{\log n \log\log\log n}{\log\log n}})$ runtime of the best of these two algorithms with optimally tuned parameters. We first establish this bound under an idealized switching rule that changes from the $(1+λ)$ to the $(1+(λ,λ))$ GA at the optimal time. We then propose a realistic switching strategy that achieves the same performance. Our analysis combines fixed-start and fixed-target perspectives, illustrating how different algorithms dominate at different stages of the optimization process. This approach offers a promising path toward a deeper theoretical understanding of OAS. --- ### Scalable Joint Resource Allocation for SLO-Constrained LLM Inference in Heterogeneous GPU Clouds Authors: Jiaming Cheng, Duong Tung Nguyen Published: 2026-04-08 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2604.07472v2 Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism configuration, and workload routing under latency, accuracy, memory, and budget constraints. While mixed-integer linear programming (MILP) can model this problem, its computational cost limits frequent re-optimization under demand variability. Existing heuristics often optimize individual components separately and may become infeasible when system-wide constraints are enforced. This paper presents a scalable framework for SLO-constrained LLM inference. We formulate the problem as an MILP with a two-phase delay model capturing both prefill and autoregressive decoding under tensor and pipeline parallelism. To solve it efficiently, we develop two constraint-aware heuristics: a Greedy Heuristic (GH) and an Adaptive Greedy Heuristic (AGH). AGH extends GH through multi-start construction, local search, and GPU consolidation. Both methods maintain feasibility through parallelism-aware filtering, cost-based ranking, and adaptive parallelism scaling. Experiments based on the Azure LLM Inference Trace show that GH generates feasible solutions within one second, while AGH achieves near-optimal performance within three seconds and scales to large instances where exact solvers fail to converge. Under out-of-sample stress with up to 1.5x delay and accuracy inflation, AGH degrades gracefully through provisioned headroom, yielding substantially lower cost and SLO violations than cost-minimal MILP solutions. Across synthetic and real Azure workloads, AGH maintains SLO compliance at significantly lower cost than exact MILP solutions. These results demonstrate that high-quality allocations provide substantial robustness to demand variability while enabling rapid adaptation to workload changes. --- ### M-ArtAgent: Evidence-Based Multimodal Agent for Implicit Art Influence Discovery Authors: Hanyi Liu, Zhonghao Jiu, Minghao Wang, Yuhang Xie, Heran Yang Published: 2026-04-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.07468v1 Implicit artistic influence, although visually plausible, is often undocumented and thus poses a historically constrained attribution problem: resemblance is necessary but not sufficient evidence. Most prior systems reduce influence discovery to embedding similarity or label-driven graph completion, while recent multimodal large language models (LLMs) remain vulnerable to temporal inconsistency and unverified attributions. This paper introduces M-ArtAgent, an evidence-based multimodal agent that reframes implicit influence discovery as probabilistic adjudication. It follows a four-phase protocol consisting of Investigation, Corroboration, Falsification, and Verdict governed by a Reasoning and Acting (ReAct)-style controller that assembles verifiable evidence chains from images and biographies, enforces art-historical axioms, and subjects each hypothesis to adversarial falsification via a prompt-isolated critic. Two theory-grounded operators, StyleComparator for Wolfflin formal analysis and ConceptRetriever for ICONCLASS-based iconographic grounding, ensure that intermediate claims are formally auditable. On the balanced WikiArt Influence Benchmark-100 (WIB-100) of 100 artists and 2,000 directed pairs, M-ArtAgent achieves 83.7% positive-class F1, 0.666 Matthews correlation coefficient (MCC), and 0.910 area under the receiver operating characteristic curve (ROC-AUC), with leakage-control and robustness checks confirming that the gains persist when explicit influence phrases are masked. By coupling multimodal perception with domain-constrained falsification, M-ArtAgent demonstrates that implicit influence analysis benefits from historically grounded adjudication rather than pattern matching alone. --- ### Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yorùbá Authors: Opeyemi Osakuade, Simon King Published: 2026-04-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.07467v1 Discrete speech units (DSUs) are derived by quantising representations from models trained using self-supervised learning (SSL). They are a popular representation for a wide variety of spoken language tasks, including those where prosody matters. DSUs are especially convenient for tasks where text and speech are jointly modelled, such as text-to-speech and multimodal dialogue systems. But we have found that DSUs encode suprasegmental information less reliably than segmental structure, which we demonstrate in this work using lexical tone, though this limitation likely extends to other suprasegmental features such as prosody. Our investigations using the tone languages Mandarin and Yorùbá show that the SSL latent representations themselves do encode tone, yet DSUs obtained using quantisation tend to prioritise phonetic structure, which makes lexical tone less reliably encoded. This remains true for a variety of quantisation methods, not only the most common, K-means. We conclude that current DSU quantisation strategies have limitations for suprasegmental features, which suggests a need for new, tone-aware (or prosody-aware) techniques in speech representation learning. We point towards a potential form of the solution by performing K-means clustering once to encode phonetic information, then again on the residual representation, which better encodes lexical tone. --- ### Cross-Tokenizer LLM Distillation through a Byte-Level Interface Authors: Avyav Kumar Singh, Yen-Chen Wu, Alexandru Cioba, Alberto Bernacchia, Davide Buffelli Published: 2026-04-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.07466v2 Cross-tokenizer distillation (CTD), the transfer of knowledge from a teacher to a student language model when the two use different tokenizers, remains a largely unsolved problem. Existing approaches rely on heuristic strategies to align mismatched vocabularies, introducing considerable complexity. In this paper, we propose a simple but effective baseline called Byte-Level Distillation (BLD) which enables CTD by operating at a common interface across tokenizers: the byte level. In more detail, we convert the teacher's output distribution to byte-level probabilities, attach a lightweight byte-level decoder head to the student, and distill through this shared byte-level interface. Despite its simplicity, BLD performs competitively with--and on several benchmarks surpasses--significantly more sophisticated CTD methods, across a range of distillation tasks with models from 1B to 8B parameters. Our results suggest that the byte level is a natural common ground for cross-tokenizer knowledge transfer, while also highlighting that consistent improvements across all tasks and benchmarks remain elusive, underscoring that CTD is still an open problem. --- ### Virtual Dummies: Enabling Scalable FDR-Controlled Variable Selection via Sequential Sampling of Null Features Authors: Taulant Koka, Jasin Machkour, Daniel P. Palomar, Michael Muma Published: 2026-04-08 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2604.07464v1 High-dimensional variable selection, particularly in genomics, requires error-controlling procedures that scale to millions of predictors. The Terminating-Random Experiments (T-Rex) selector achieves false discovery rate (FDR) control by aggregating results of early terminated random experiments, each combining original predictors with i.i.d. synthetic null variables (dummies). At biobank scales, however, explicit dummy augmentation requires terabytes of memory. We demonstrate that this bottleneck is not fundamental. Formalizing the information flow of forward selection through a filtration, we show that compatible selectors interact with unselected dummies solely through projections onto an adaptively evolving low-dimensional subspace. For rotationally invariant dummy distributions, we derive an adaptive stick-breaking construction sampling these projections from their exact conditional distribution given the selection history, thereby eliminating dummy matrix materialization. We prove a pathwise universality theorem: under mild delocalization conditions, selection paths driven by generic standardized i.i.d. dummies converge to the same Gaussian limit. We instantiate the theory through Virtual Dummy LARS (VD-LARS), reducing memory and runtime by several orders of magnitude while preserving the exact selection law and FDR guarantees of the T-Rex selector. Experiments on realistic genome-wide association study data confirm that VD-T-Rex controls FDR and achieves power at scales where all competing methods either fail or time out. --- ### CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection Authors: Ziyang Cheng, Haoyu Wei, Hang Yin, Xiuwei Xu, Bingyao Yu, Jie Zhou, Jiwen Lu Published: 2026-04-08 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.07457v1 While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global end-effector poses remains fragile against Out-of-Distribution (OOD) inputs induced by sensor noise or infeasible user commands. To improve robustness against these perturbations without sacrificing task performance and continuity, we propose Competence Manifold Projection (CMP). Specifically, we utilize a Frame-Wise Safety Scheme that transforms the infinite-horizon safety constraint into a computationally efficient single-step manifold inclusion. To instantiate this competence manifold, we employ a Lower-Bounded Safety Estimator that distinguishes unmastered intentions from the training distribution. We then introduce an Isomorphic Latent Space (ILS) that aligns manifold geometry with safety probability, enabling efficient O(1) seamless defense against arbitrary OOD intents. Experiments demonstrate that CMP achieves up to a 10-fold survival rate improvement in typical OOD scenarios where baselines suffer catastrophic failure, incurring under 10% tracking degradation. Notably, the system exhibits emergent ``best-effort'' generalization behaviors to progressively accomplish OOD goals by adhering to the competence boundaries. Result videos are available at: https://shepherd1226.github.io/CMP. --- ### Munkres' General Topology Autoformalized in Isabelle/HOL Authors: Dustin Bryant, Jonathan Julián Huerta y Munive, Cezary Kaliszyk, Josef Urban Published: 2026-04-08 Categories: cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2604.07455v1 We describe an experiment in LLM-assisted autoformalization that produced over 85,000 lines of Isabelle/HOL code covering all 39 sections of Munkres' Topology (general topology, Chapters 2--8), from topological spaces through dimension theory. The LLM-based coding agents (initially ChatGPT 5.2 and then Claude Opus 4.6) used 24 active days for that. The formalization is complete: all 806 formal results are fully proved with zero sorry's. Proved results include the Tychonoff theorem, the Baire category theorem, the Nagata--Smirnov and Smirnov metrization theorems, the Stone--Čech compactification, Ascoli's theorem, the space-filling curve, and others. The methodology is based on a "sorry-first" declarative proof workflow combined with bulk use of sledgehammer - two of Isabelle major strengths. This leads to relatively fast autoformalization progress. We analyze the resulting formalization in detail, analyze the human--LLM interaction patterns from the session log, and briefly compare with related autoformalization efforts in Megalodon, HOL Light, and Naproche. The results indicate that LLM-assisted formalization of standard mathematical textbooks in Isabelle/HOL is quite feasible, cheap and fast, even if some human supervision is useful. --- ### HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Authors: Tencent Robotics X, HY Vision Team, :, Xumin Yu, Zuyan Liu, Ziyi Wang, He Zhang, Yongming Rao, Fangfu Liu, Yani Zhang, Ruowen Zhao, Oran Wang et al. Published: 2026-04-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07430v1 We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents. To bridge the gap between general Vision-Language Models (VLMs) and the demands of embodied agents, our models are developed to enhance the core capabilities required by embodied intelligence: spatial and temporal visual perception, alongside advanced embodied reasoning for prediction, interaction, and planning. The HY-Embodied-0.5 suite comprises two primary variants: an efficient model with 2B activated parameters designed for edge deployment, and a powerful model with 32B activated parameters targeted for complex reasoning. To support the fine-grained visual perception essential for embodied tasks, we adopt a Mixture-of-Transformers (MoT) architecture to enable modality-specific computing. By incorporating latent tokens, this design effectively enhances the perceptual representation of the models. To improve reasoning capabilities, we introduce an iterative, self-evolving post-training paradigm. Furthermore, we employ on-policy distillation to transfer the advanced capabilities of the large model to the smaller variant, thereby maximizing the performance potential of the compact model. Extensive evaluations across 22 benchmarks, spanning visual perception, spatial reasoning, and embodied understanding, demonstrate the effectiveness of our approach. Our MoT-2B model outperforms similarly sized state-of-the-art models on 16 benchmarks, while the 32B variant achieves performance comparable to frontier models such as Gemini 3.0 Pro. In downstream robot control experiments, we leverage our robust VLM foundation to train an effective Vision-Language-Action (VLA) model, achieving compelling results in real-world physical evaluations. Code and models are open-sourced at https://github.com/Tencent-Hunyuan/HY-Embodied. --- ### GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents Authors: Mingyu Ouyang, Siyuan Hu, Kevin Qinghong Lin, Hwee Tou Ng, Mike Zheng Shou Published: 2026-04-08 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.07429v1 Towards an embodied generalist for real-world interaction, Multimodal Large Language Model (MLLM) agents still suffer from challenging latency, sparse feedback, and irreversible mistakes. Video games offer an ideal testbed with rich visual observations and closed-loop interaction, demanding fine-grained perception, long-horizon planning, and precise control. However, systematically evaluating these capabilities is currently hindered by heterogeneous action interfaces and heuristic verification. To this end, we introduce GameWorld, a benchmark designed for standardized and verifiable evaluation of MLLMs as generalist game agents in browser environments. Two game agent interfaces are studied: (i) computer-use agents that directly emit keyboard and mouse controls, and (ii) generalist multimodal agents that act in a semantic action space via deterministic Semantic Action Parsing. GameWorld contains 34 diverse games and 170 tasks, each paired with state-verifiable metrics for outcome-based evaluation. The results across 18 model-interface pairs suggest that even the best performing agent is far from achieving human capabilities on video games. Extensive experiments of repeated full-benchmark reruns demonstrate the robustness of the benchmark, while further studies on real-time interaction, context-memory sensitivity, and action validity expose more challenges ahead for game agents. Together, by offering a standardized, verifiable, and reproducible evaluation framework, GameWorld lays a robust foundation for advancing research on multimodal game agents and beyond. The project page is at https://gameworld-bench.github.io. --- ### Regret-Aware Policy Optimization: Environment-Level Memory for Replay Suppression under Delayed Harm Authors: Prakul Sunil Hiremath Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07428v1 Safety in reinforcement learning (RL) is typically enforced through objective shaping while keeping environment dynamics stationary with respect to observable state-action pairs. Under delayed harm, this can lead to replay: after a washout period, reintroducing the same stimulus under matched observable conditions reproduces a similar harmful cascade. We introduce the Replay Suppression Diagnostic (RSD), a controlled exposure-decay-replay protocol that isolates this failure mode under frozen-policy evaluation. We show that, under stationary observable transition kernels, replay cannot be structurally suppressed without inducing a persistent shift in replay-time action distributions. Motivated by platform-mediated systems, we propose Regret-Aware Policy Optimization (RAPO), which augments the environment with persistent harm-trace and scar fields and applies a bounded, mass-preserving transition reweighting to reduce reachability of historically harmful regions. On graph diffusion tasks (50-1000 nodes), RAPO suppresses replay, reducing re-amplification gain (RAG) from 0.98 to 0.33 on 250-node graphs while retaining 82\% of task return. Disabling transition deformation only during replay restores re-amplification (RAG 0.91), isolating environment-level deformation as the causal mechanism. --- ### Personalizing Text-to-Image Generation to Individual Taste Authors: Anne-Sofie Maerten, Juliane Verwiebe, Shyamgopal Karthik, Ameya Prabhu, Johan Wagemans, Matthias Bethge Published: 2026-04-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07427v1 Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for "average" human appeal, they fail to capture the inherent subjectivity of aesthetic judgment. In this work, we introduce a novel dataset and predictive framework, called PAMELA, designed to model personalized image evaluations. Our dataset comprises 70,000 ratings across 5,000 diverse images generated by state-of-the-art models (Flux 2 and Nano Banana). Each image is evaluated by 15 unique users, providing a rich distribution of subjective preferences across domains such as art, design, fashion, and cinematic photography. Leveraging this data, we propose a personalized reward model trained jointly on our high-quality annotations and existing aesthetic assessment subsets. We demonstrate that our model predicts individual liking with higher accuracy than the majority of current state-of-the-art methods predict population-level preferences. Using our personalized predictor, we demonstrate how simple prompt optimization methods can be used to steer generations towards individual user preferences. Our results highlight the importance of data quality and personalization to handle the subjectivity of user preferences. We release our dataset and model to facilitate standardized research in personalized T2I alignment and subjective visual quality assessment. --- ### GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control Authors: Prakul Sunil Hiremath Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07426v1 Model-based reinforcement learning (MBRL) improves sample efficiency by optimizing policies inside imagined rollouts, but long-horizon planning degrades when model errors compound and imagined trajectories drift off the training manifold. We introduce GIRL (Generative Imagination Reinforcement Learning), a latent world-model framework that addresses this failure mode with two key components. First, a cross-modal grounding signal derived from a frozen foundation model (DINOv2) anchors the latent transition prior to a semantically consistent embedding space, penalizing inconsistent or implausible predictions. Second, an uncertainty-adaptive trust-region bottleneck interprets the KL regularizer as the Lagrange multiplier of a constrained optimization problem, restricting imagination drift within a learned region calibrated by Expected Information Gain and a Relative Performance Loss signal. We re-derive a value-gap bound using the Performance Difference Lemma and Integral Probability Metrics, yielding a bound that remains informative as the discount factor approaches one and connects the objective to real-environment regret. Experiments across three benchmark suites, including DeepMind Control, Adroit Hand Manipulation, and Meta-World with visual distractors, show that GIRL reduces latent rollout drift by 38 to 61 percent across tasks relative to DreamerV3, improves asymptotic return, and requires fewer environment interactions on long-horizon tasks. GIRL also outperforms TD-MPC2 on sparse-reward and high-contact settings under standard evaluation metrics. A distilled-prior variant reduces inference overhead and improves computational efficiency relative to the full model. --- ### An Analysis of Artificial Intelligence Adoption in NIH-Funded Research Authors: Navapat Nananukul, Mayank Kejriwal Published: 2026-04-08 Categories: cs.AI, cs.CY, cs.MA arXiv: https://arxiv.org/abs/2604.07424v1 Understanding the landscape of artificial intelligence (AI) and machine learning (ML) adoption across the National Institutes of Health (NIH) portfolio is critical for research funding strategy, institutional planning, and health policy. The advent of large language models (LLMs) has fundamentally transformed research landscape analysis, enabling researchers to perform large-scale semantic extraction from thousands of unstructured research documents. In this paper, we illustrate a human-in-the-loop research methodology for LLMs to automatically classify and summarize research descriptions at scale. Using our methodology, we present a comprehensive analysis of 58,746 NIH-funded biomedical research projects from 2025. We show that: (1) AI constitutes 15.9% of the NIH portfolio with a 13.4% funding premium, concentrated in discovery, prediction, and data integration across disease domains; (2) a critical research-to-deployment gap exists, with 79% of AI projects remaining in research/development stages while only 14.7% engage in clinical deployment or implementation; and (3) health disparities research is severely underrepresented at just 5.7% of AI-funded work despite its importance to NIH's equity mission. These findings establish a framework for evidence-based policy interventions to align the NIH AI portfolio with health equity goals and strategic research priorities. --- ### OpenPRC: A Unified Open-Source Framework for Physics-to-Task Evaluation in Physical Reservoir Computing Authors: Yogesh Phalak, Wen Sin Lor, Apoorva Khairnar, Benjamin Jantzen, Noel Naughton, Suyi Li Published: 2026-04-08 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2604.07423v1 Physical Reservoir Computing (PRC) leverages the intrinsic nonlinear dynamics of physical substrates, mechanical, optical, spintronic, and beyond, as fixed computational reservoirs, offering a compelling paradigm for energy-efficient and embodied machine learning. However, the practical workflow for developing and evaluating PRC systems remains fragmented: existing tools typically address only isolated parts of the pipeline, such as substrate-specific simulation, digital reservoir benchmarking, or readout training. What is missing is a unified framework that can represent both high-fidelity simulated trajectories and real experimental measurements through the same data interface, enabling reproducible evaluation, analysis, and physics-aware optimization across substrates and data sources. We present OpenPRC, an open-source Python framework that fills this gap through a schema-driven physics-to-task pipeline built around five modules: a GPU-accelerated hybrid RK4-PBD physics engine (demlat), a video-based experimental ingestion layer (openprc.vision), a modular learning layer (reservoir), information-theoretic analysis and benchmarking tools (analysis), and physics-aware optimization (optimize). A universal HDF5 schema enforces reproducibility and interoperability, allowing GPU-simulated and experimentally acquired trajectories to enter the same downstream workflow without modification. Demonstrated capabilities include simulations of Origami tessellations, video-based trajectory extraction from a physical reservoir, and a common interface for standardized PRC benchmarking, correlation diagnostics, and capacity analysis. The longer-term vision is to serve as a standardizing layer for the PRC community, compatible with external physics engines including PyBullet, PyElastica, and MERLIN. --- ### Multimodal Large Language Models for Multi-Subject In-Context Image Generation Authors: Yucheng Zhou, Dubing Chen, Huan Zheng, Jianbing Shen Published: 2026-04-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.07422v1 Recent advances in text-to-image (T2I) generation have enabled visually coherent image synthesis from descriptions, but generating images containing multiple given subjects remains challenging. As the number of reference identities increases, existing methods often suffer from subject missing and semantic drift. To address this problem, we propose MUSIC, the first MLLM specifically designed for \textbf{MU}lti-\textbf{S}ubject \textbf{I}n-\textbf{C}ontext image generation. To overcome the data scarcity, we introduce an automatic and scalable data generation pipeline that eliminates the need for manual annotation. Furthermore, we enhance the model's understanding of multi-subject semantic relationships through a vision chain-of-thought (CoT) mechanism, guiding step-by-step reasoning from subject images to semantics and generation. To mitigate identity entanglement and manage visual complexity, we develop a novel semantics-driven spatial layout planning method and demonstrate its test-time scalability. By incorporating complex subject images during training, we improve the model's capacity for chained reasoning. In addition, we curate MSIC, a new benchmark tailored for multi-subject in-context generation. Experimental results demonstrate that MUSIC significantly surpasses other methods in both multi- and single-subject scenarios. --- ### SPAMoE: Spectrum-Aware Hybrid Operator Framework for Full-Waveform Inversion Authors: Zhenyu Wang, Peiyuan Li, Yongxiang Shi, Ruoyu Wu, Chenfei Liao, Lei Zhang Published: 2026-04-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.07421v3 Full-waveform inversion (FWI) is pivotal for reconstructing high-resolution subsurface velocity models but remains computationally intensive and ill-posed. While deep learning approaches promise efficiency, existing Convolutional Neural Networks (CNNs) and single-paradigm Neural Operators (NOs) struggle with one fundamental issue: frequency entanglement of multi-scale geological features. To address this challenge, we propose Spectral-Preserving Adaptive MoE (SPAMoE), a novel spectrum-aware framework for solving inverse problems with complex multi-scale structures. Our approach introduces a Spectral-Preserving DINO Encoder that enforces a lower bound on the high-to-low frequency energy ratio of the encoded representation, mitigating high-frequency collapse and stabilizing subsequent frequency-domain modeling. Furthermore, we design a novel Spectral Decomposition and Routing mechanism that dynamically assigns frequency bands to a Mixture-of-Experts (MoE) ensemble comprising FNO, MNO, and LNO. On the ten OpenFWI sub-datasets, experiments show that SPAMoE reduces the average MAE by 44.4% relative to the best officially reported OpenFWI baseline, thereby establishing a new architectural framework for learning-based full-waveform inversion. Our code and data are available at https://github.com/zhenyuwang12366/SPAMoE --- ### Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking Authors: Chao Zhang, Shuai Lin, ChengLei Dai, Ye Qian, Fan Mingyang, Yi Zhang, Yi Wang, Jingwei Zhuo Published: 2026-04-08 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.07420v1 Kuaishou serves over 400 million daily active users, processing hundreds of millions of search queries daily against a repository of tens of billions of short videos. As the final decision layer, the reranking stage determines user experience by optimizing whole-page utility. While traditional score-and-sort methods fail to capture combinatorial dependencies, Generative Reranking offers a superior paradigm by directly modeling the permutation probability. However, deploying Generative Reranking in such a high-stakes environment faces a fundamental dual dilemma: 1) the structural trade-off where Autoregressive (AR) models offer superior Sequential modeling but suffer from prohibitive latency, versus Non-Autoregressive (NAR) models that enable efficiency but lack dependency capturing; 2) the optimization gap where Supervised Learning faces challenges in directly optimizing whole-page utility, while Reinforcement Learning (RL) struggles with instability in high-throughput data streams. To resolve this, we propose Dual-Rerank, a unified framework designed for industrial reranking that bridges the structural gap via Sequential Knowledge Distillation and addresses the optimization gap using List-wise Decoupled Reranking Optimization (LDRO) for stable online RL. Extensive A/B testing on production traffic demonstrates that Dual-Rerank achieves State-of-the-Art performance, significantly improving User satisfaction and Watch Time while drastically reducing inference latency compared to AR baselines. --- ### Bayesian Optimization for Mixed-Variable Problems in the Natural Sciences Authors: Yuhao Zhang, Ti John, Matthias Stosiek, Patrick Rinke Published: 2026-04-08 Categories: cs.LG, cond-mat.mtrl-sci, physics.comp-ph arXiv: https://arxiv.org/abs/2604.07416v1 Optimizing expensive black-box objectives over mixed search spaces is a common challenge across the natural sciences. Bayesian optimization (BO) offers sample-efficient strategies through probabilistic surrogate models and acquisition functions. However, its effectiveness diminishes in mixed or high-cardinality discrete spaces, where gradients are unavailable and optimizing the acquisition function becomes computationally demanding. In this work, we generalize the probabilistic reparameterization (PR) approach of Daulton et al. to handle non-equidistant discrete variables, enabling gradient-based optimization in fully mixed-variable settings with Gaussian process (GP) surrogates. With real-world scientific optimization tasks in mind, we conduct systematic benchmarks on synthetic and experimental objectives to obtain an optimized kernel formulations and demonstrate the robustness of our generalized PR method. We additionally show that, when combined with a modified BO workflow, our approach can efficiently optimize highly discontinuous and discretized objective landscapes. This work establishes a practical BO framework for addressing fully mixed optimization problems in the natural sciences, and is particularly well suited to autonomous laboratory settings where noise, discretization, and limited data are inherent. --- ### SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval Authors: Roxana Petcu, Evangelos Kanoulas, Maarten de Rijke Published: 2026-04-08 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.07415v1 Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or predetermined reasoning path, they remain challenging. Recent approaches train models using reinforcement learning on the model's outcome, showing promise in improving how models handle complex information. We introduce SubSearch, a specialized framework that shifts from outcome-only supervision to intermediate reward signals that incentivize planning high-quality reasoning. Unlike previous work on process reward modeling, which focuses on training a separate reward model with annotated trajectories by either human annotators or large LLM judges, SubSearch directly optimizes the generator using intrinsic process rewards, which we define as internally-derived rewards, eliminating the need for external supervision, and moving towards autonomous information-intensive reasoning. Experiments on seven benchmarks show that rewarding intermediate reasoning steps with intrinsic rewards leads to more robust reasoning traces in both QA and multi-hop QA datasets over using only outcome rewards. SubSearch can help in building reasoning traces that allow agents to better integrate search engines for complex query answering, while offering a data-efficient alternative to supervised process modeling. --- ### FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios Authors: Xiangru Jian, Hao Xu, Wei Pang, Xinjian Zhao, Chengyu Tao, Qixin Zhang, Xikun Zhang, Chao Zhang, Guanzhi Deng, Alex Xue, Juan Du, Tianshu Yu et al. Published: 2026-04-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.07413v2 The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to transition from simple perception to autonomous execution, yet current evaluations fail to reflect the rigorous demands of real-world manufacturing environments. Progress is hindered by data scarcity and a lack of fine-grained domain semantics in existing datasets. To bridge this gap, we introduce FORGE. Wefirst construct a high-quality multimodal dataset that combines real-world 2D images and 3D point clouds, annotated with fine-grained domain semantics (e.g., exact model numbers). We then evaluate 18 state-of-the-art MLLMs across three manufacturing tasks, namely workpiece verification, structural surface inspection, and assembly verification, revealing significant performance gaps. Counter to conventional understanding, the bottleneck analysis shows that visual grounding is not the primary limiting factor. Instead, insufficient domain-specific knowledge is the key bottleneck, setting a clear direction for future research. Beyond evaluation, we show that our structured annotations can serve as an actionable training resource: supervised fine-tuning of a compact 3B-parameter model on our data yields up to 90.8% relative improvement in accuracy on held-out manufacturing scenarios, providing preliminary evidence for a practical pathway toward domain-adapted manufacturing MLLMs. The code and datasets are available at https://ai4manufacturing.github.io/forge-web. --- ### Physics-informed neural operators for the in situ characterization of locally reacting sound absorbers Authors: Jonas M. Schmid, Johannes D. Schmid, Martin Eser, Steffen Marburg Published: 2026-04-08 Categories: cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2604.07412v1 Accurate knowledge of acoustic surface admittance or impedance is essential for reliable wave-based simulations, yet its in situ estimation remains challenging due to noise, model inaccuracies, and restrictive assumptions of conventional methods. This work presents a physics-informed neural operator approach for estimating frequency-dependent surface admittance directly from near-field measurements of sound pressure and particle velocity. A deep operator network is employed to learn the mapping from measurement data, spatial coordinates, and frequency to acoustic field quantities, while simultaneously inferring a globally consistent surface admittance spectrum without requiring an explicit forward model. The governing acoustic relations, including the Helmholtz equation, the linearized momentum equation, and Robin boundary conditions, are embedded into the training process as physics-based regularization, enabling physically consistent and noise-robust predictions while avoiding frequency-wise inversion. The method is validated using synthetically generated data from a simulation model for two planar porous absorbers under semi free-field conditions across a broad frequency range. Results demonstrate accurate reconstruction of both real and imaginary admittance components and reliable prediction of acoustic field quantities. Parameter studies confirm improved robustness to noise and sparse sampling compared to purely data-driven approaches, highlighting the potential of physics-informed neural operators for in situ acoustic material characterization. --- ### Reinforcement Learning with Reward Machines for Sleep Control in Mobile Networks Authors: Kristina Levina, Nikolaos Pappas, Athanasios Karapantelakis, Aneta Vulgarakis Feljan, Jendrik Seipp Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07411v1 Energy efficiency in mobile networks is crucial for sustainable telecommunications infrastructure, particularly as network densification continues to increase power consumption. Sleep mechanisms for the components in mobile networks can reduce energy use, but deciding which components to put to sleep, when, and for how long while preserving quality of service (QoS) remains a difficult optimisation problem. In this paper, we utilise reinforcement learning with reward machines (RMs) to make sleep-control decisions that balance immediate energy savings and long-term QoS impact, i.e. time-averaged packet drop rates for deadline-constrained traffic and time-averaged minimum-throughput guarantees for constant-rate users. A challenge is that time-averaged constraints depend on cumulative performance over time rather than immediate performance. As a result, the effective reward is non-Markovian, and optimal actions depend on operational history rather than the instantaneous system state. RMs account for the history dependence by maintaining an abstract state that explicitly tracks the QoS constraint violations over time. Our framework provides a principled, scalable approach to energy management for next-generation mobile networks under diverse traffic patterns and QoS requirements. --- ### GAN-based Domain Adaptation for Image-aware Layout Generation in Advertising Poster Design Authors: Chenchen Xu, Min Zhou, Tiezheng Ge, Weiwei Xu Published: 2026-04-08 Categories: cs.LG, eess.IV arXiv: https://arxiv.org/abs/2604.07409v1 Layout plays a crucial role in graphic design and poster generation. Recently, the application of deep learning models for layout generation has gained significant attention. This paper focuses on using a GAN-based model conditioned on images to generate advertising poster graphic layouts, requiring a dataset of paired product images and layouts. To address this task, we introduce the Content-aware Graphic Layout Dataset (CGL-Dataset), consisting of 60,548 paired inpainted posters with annotations and 121,000 clean product images. The inpainting artifacts introduce a domain gap between the inpainted posters and clean images. To bridge this gap, we design two GAN-based models. The first model, CGL-GAN, uses Gaussian blur on the inpainted regions to generate layouts. The second model combines unsupervised domain adaptation by introducing a GAN with a pixel-level discriminator (PD), abbreviated as PDA-GAN, to generate image-aware layouts based on the visual texture of input images. The PD is connected to shallow-level feature maps and computes the GAN loss for each input-image pixel. Additionally, we propose three novel content-aware metrics to assess the model's ability to capture the intricate relationships between graphic elements and image content. Quantitative and qualitative evaluations demonstrate that PDA-GAN achieves state-of-the-art performance and generates high-quality image-aware layouts. --- ### Conservation Law Breaking at the Edge of Stability: A Spectral Theory of Non-Convex Neural Network Optimization Authors: Daniel Nobrega Medeiros Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07405v1 Why does gradient descent reliably find good solutions in non-convex neural network optimization, despite the landscape being NP-hard in the worst case? We show that gradient flow on L-layer ReLU networks without bias preserves L-1 conservation laws C_l = ||W_{l+1}||_F^2 - ||W_l||_F^2, confining trajectories to lower-dimensional manifolds. Under discrete gradient descent, these laws break with total drift scaling as eta^alpha where alpha is approximately 1.1-1.6 depending on architecture, loss function, and width. We decompose this drift exactly as eta^2 * S(eta), where the gradient imbalance sum S(eta) admits a closed-form spectral crossover formula with mode coefficients c_k proportional to e_k(0)^2 * lambda_{x,k}^2, derived from first principles and validated for both linear (R=0.85) and ReLU (R>0.80) networks. For cross-entropy loss, softmax probability concentration drives exponential Hessian spectral compression with timescale tau = Theta(1/eta) independent of training set size, explaining why cross-entropy self-regularizes the drift exponent near alpha=1.0. We identify two dynamical regimes separated by a width-dependent transition: a perturbative sub-Edge-of-Stability regime where the spectral formula applies, and a non-perturbative regime with extensive mode coupling. All predictions are validated across 23 experiments. --- ### Score Shocks: The Burgers Equation Structure of Diffusion Generative Models Authors: Krisanu Sarkar Published: 2026-04-08 Categories: cond-mat.stat-mech, cs.LG, math.AP, stat.ML arXiv: https://arxiv.org/abs/2604.07404v1 We analyze the score field of a diffusion generative model through a Burgers-type evolution law. For VE diffusion, the heat-evolved data density implies that the score obeys viscous Burgers in one dimension and the corresponding irrotational vector Burgers system in $\R^d$, giving a PDE view of \emph{speciation transitions} as the sharpening of inter-mode interfaces. For any binary decomposition of the noised density into two positive heat solutions, the score separates into a smooth background and a universal $\tanh$ interfacial term determined by the component log-ratio; near a regular binary mode boundary this yields a normal criterion for speciation. In symmetric binary Gaussian mixtures, the criterion recovers the critical diffusion time detected by the midpoint derivative of the score and agrees with the spectral criterion of Biroli, Bonnaire, de~Bortoli, and Mézard (2024). After subtracting the background drift, the inter-mode layer has a local Burgers $\tanh$ profile, which becomes global in the symmetric Gaussian case with width $σ_τ^2/a$. We also quantify exponential amplification of score errors across this layer, show that Burgers dynamics preserves irrotationality, and use a change of variables to reduce the VP-SDE to the VE case, yielding a closed-form VP speciation time. Gaussian-mixture formulas are verified to machine precision, and the local theorem is checked numerically on a quartic double-well. --- ### Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity Authors: Yucheng Zhou, Jianbing Shen Published: 2026-04-08 Categories: cs.LG, eess.IV arXiv: https://arxiv.org/abs/2604.07402v1 Autoregressive models have shown superior performance and efficiency in image generation, but remain constrained by high computational costs and prolonged training times in video generation. In this study, we explore methods to accelerate training for autoregressive video generation models through empirical analyses. Our results reveal that while training on fewer video frames significantly reduces training time, it also exacerbates error accumulation and introduces inconsistencies in the generated videos. To address these issues, we propose a Local Optimization (Local Opt.) method, which optimizes tokens within localized windows while leveraging contextual information to reduce error propagation. Inspired by Lipschitz continuity, we propose a Representation Continuity (ReCo) strategy to improve the consistency of generated videos. ReCo utilizes continuity loss to constrain representation changes, improving model robustness and reducing error accumulation. Extensive experiments on class- and text-to-video datasets demonstrate that our approach achieves superior performance to the baseline while halving the training cost without sacrificing quality. --- ### Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory Authors: Tatiana Petrova, Evgeny Polyachenko, Radu State Published: 2026-04-08 Categories: cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2604.07401v2 We study the thermodynamic memory capacity of modern Hopfield networks (Dense Associative Memory models) with continuous states under geometric constraints, extending classical analyses of pairwise associative memory. We derive thermodynamic phase boundaries for Dense Associative Memory networks with exponential capacity $M = e^{αN}$, comparing Gaussian (LSE) and Epanechnikov (LSR) kernels. For continuous neurons on an $N$-sphere, the geometric entropy depends solely on the spherical geometry, not the kernel. In the sharp-kernel regime, the maximum theoretical capacity $α= 0.5$ is achieved at zero temperature; below this threshold, a critical line separates retrieval from non-retrieval. The two kernels differ qualitatively in their phase boundary structure: for LSE, a critical line exists at all loads $α> 0$. For LSR, the finite support introduces a threshold $α_{\text{th}}$ below which no spurious patterns contribute to the noise floor, and no critical line exists -- retrieval is perfect at any temperature. These results advance the theory of high-capacity associative memory and clarify fundamental limits of retrieval robustness in modern attention-like memory architectures. --- ### Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge Authors: Wonseon Lim, Jaesung Lee, Dae-Won Kim Published: 2026-04-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.07399v1 Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is parameter-efficient and achieves competitive accuracy, prior work has focused mainly on accuracy or inference-time performance, often overlooking the memory and computational costs of on-device training. In this paper, we propose CPS-Prompt, a critical patch-aware sparse prompting framework that explicitly targets training-time memory usage and computational cost by integrating critical patch sampling (CPS) for task-aware token reduction and decoupled prompt and classifier training (DPCT) to reduce backpropagation overhead. Experiments on three public benchmarks and real edge hardware show that CPS-Prompt improves peak memory, training time, and energy efficiency by about 1.6x over the balanced CODA-Prompt baseline, while maintaining accuracy within 2% of the state-of-the-art C-Prompt on average and remaining competitive with CODA-Prompt in accuracy. The code is available at https://github.com/laymond1/cps-prompt. --- ### Breaking the Illusion of Identity in LLM Tooling Authors: Marek Miller Published: 2026-04-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.07398v1 Large language models (LLMs) in research and development toolchains produce output that triggers attribution of agency and understanding -- a cognitive illusion that degrades verification behavior and trust calibration. No existing mitigation provides a systematic, deployable constraint set for output register. This paper proposes seven output-side rules, each targeting a documented linguistic mechanism, and validates them empirically. In 780 two-turn conversations (constrained vs. default register, 30 tasks, 13 replicates, 1560 API calls), anthropomorphic markers dropped from 1233 to 33 (>97% reduction, p < 0.001), outputs were 49% shorter by word count, and adapted AnthroScore confirmed the shift toward machine register (-1.94 vs. -0.96, p < 0.001). The rules are implemented as a configuration-file system prompt requiring no model modification; validation uses a single model (Claude Sonnet 4). Output quality under the constrained register was not evaluated. The mechanism is extensible to other domains. --- ### Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training Authors: Jinhong Lin, Pan Wang, Zitong Zhan, Lin Zhang, Pedro Morgado Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07397v1 A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a curriculum strategy that schedules training images from simple to complex without modifying the model or loss. Each image is scored offline by a semantic-aware complexity metric combining foreground dominance (how much of the image salient objects occupy) and foreground typicality (how closely the salient content matches learned visual prototypes). A temperature-controlled sampler then prioritizes low-complexity images early and anneals toward uniform sampling. On ImageNet 256x256 with SiT backbones (S/2 to XL/2), Data Warmup improves IS by up to 6.11 and FID by up to 3.41, reaching baseline quality tens of thousands of iterations earlier. Reversing the curriculum (exposing hard images first) degrades performance below the uniform baseline, confirming that the simple-to-complex ordering itself drives the gains. The method combines with orthogonal accelerators such as REPA and requires only ~10 minutes of one-time preprocessing with zero per-iteration overhead. --- ### SHIELD: A Segmented Hierarchical Memory Architecture for Energy-Efficient LLM Inference on Edge NPUs Authors: Jintao Zhang, Xuanyao Fong Published: 2026-04-08 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2604.07396v2 Large Language Model (LLM) inference on edge Neural Processing Units (NPUs) is fundamentally constrained by limited on-chip memory capacity. Although high-density embedded DRAM (eDRAM) is attractive for storing activation workspaces, its periodic refresh consumes substantial energy. Prior work has primarily focused on reducing off-chip traffic or optimizing refresh for persistent Key-Value (KV) caches, while transient and error-resilient Query and Attention Output (QO) activations are largely overlooked. We propose SHIELD, a lifecycle-aware segmented eDRAM architecture that jointly exploits temporal residency and bit-level sensitivity in bfloat16 (BF16) activations. SHIELD isolates the sign and exponent fields from the mantissa, disables refresh for transient QO mantissas, and applies relaxed refresh to persistent KV mantissas. Across multiple LLMs and inference scenarios, SHIELD reduces eDRAM refresh energy by 35% relative to a standard-refresh baseline while preserving accuracy on WikiText-2, PIQA, and ARC-Easy. --- ### A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring Authors: Wenze Wang, Mehdi Hosseinzadeh, Feras Dayoub Published: 2026-04-08 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.07395v1 Robotic manipulation systems that follow language instructions often execute grasp primitives in a largely single-shot manner: a model proposes an action, the robot executes it, and failures such as empty grasps, slips, stalls, timeouts, or semantically wrong grasps are not surfaced to the decision layer in a structured way. Inspired by agentic loops in digital tool-using agents, we reformulate language-guided grasping as a bounded embodied agent operating over grounded execution states, where physical actions expose an explicit tool-state stream. We introduce a physical agentic loop that wraps an unmodified learned manipulation primitive (grasp-and-lift) with (i) an event-based interface and (ii) an execution monitoring layer, Watchdog, which converts noisy gripper telemetry into discrete outcome labels using contact-aware fusion and temporal stabilization. These outcome events, optionally combined with post-grasp semantic verification, are consumed by a deterministic bounded policy that finalizes, retries, or escalates to the user for clarification, guaranteeing finite termination. We validate the resulting loop on a mobile manipulator with an eye-in-hand D405 camera, keeping the underlying grasp model unchanged and evaluating representative scenarios involving visual ambiguity, distractors, and induced execution failures. Results show that explicit execution-state monitoring and bounded recovery enable more robust and interpretable behavior than open-loop execution, while adding minimal architectural overhead. For the source code and demo refer to our project page: https://wenzewwz123.github.io/Agentic-Loop/ --- ### Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference Authors: Quantong Qiu, Zhiyi Hong, Yi Yang, Haitian Wang, Kebin Liu, Qingqing Dang, Juntao Li, Min Zhang Published: 2026-04-08 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.07394v2 The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce Flux Attention, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight Layer Router into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8$\times$A800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to $2.8\times$ and $2.0\times$ in the prefill and decode stages. --- ### Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference Authors: Quantong Qiu, Zhiyi Hong, Yi Yang, Haitian Wang, Kebin Liu, Qingqing Dang, Juntao Li, Min Zhang Published: 2026-04-08 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.07394v1 The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce Flux Attention, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight Layer Router into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8$\times$A800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to $2.8\times$ and $2.0\times$ in the prefill and decode stages. --- ### DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting Authors: Yeran Zhang, Pengwei Yang, Guoqing Wang, Tianyu Li Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07393v3 Accurate forecasting of industrial time series requires balancing predictive accuracy with physical plausibility under non-stationary operating conditions. Existing data-driven models often achieve strong statistical performance but struggle to respect regime-dependent interaction structures and transport delays inherent in real-world systems. To address this challenge, we propose DSPR (Dual-Stream Physics-Residual Networks), a forecasting framework that explicitly decouples stable temporal patterns from regime-dependent residual dynamics. The first stream models the statistical temporal evolution of individual variables. The second stream focuses on residual dynamics through two key mechanisms: an Adaptive Window module that estimates flow-dependent transport delays, and a Physics-Guided Dynamic Graph that incorporates physical priors to learn time-varying interaction structures while suppressing spurious correlations. Experiments on four industrial benchmarks spanning heterogeneous regimes demonstrate that DSPR consistently improves forecasting accuracy and robustness under regime shifts while maintaining strong physical plausibility. It achieves state-of-the-art predictive performance, with Mean Conservation Accuracy exceeding 99% and Total Variation Ratio reaching up to 97.2%. Beyond forecasting, the learned interaction structures and adaptive lags provide interpretable insights that are consistent with known domain mechanisms, such as flow-dependent transport delays and wind-to-power scaling behaviors. These results suggest that architectural decoupling with physics-consistent inductive biases offers an effective path toward trustworthy industrial time-series forecasting. Furthermore, DSPR's demonstrated robust performance in long-term industrial deployment bridges the gap between advanced forecasting models and trustworthy autonomous control systems. --- ### Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making Authors: Zhaowen Fan, Rongchao Zhang, Yunxiang Han Published: 2026-04-08 Categories: cs.LG, cs.IR, cs.RO arXiv: https://arxiv.org/abs/2604.07392v3 Autonomous agents operating in dynamic environments increasingly demand decision-making systems that are both efficient and interpretable. Hence we propose the Event-Retrieve-Action (ERA) framework, an alternative formulation for embodied decision-making that bridges the gap between black-box imitation and interpretable memory retrieval while enabling online refinement without retraining. The environment is represented as structured semantic events encoded into an interpretable latent representation, and decisions are generated by retrieving relevant prior experiences from a knowledge bank of event-action pairs. Final actions are produced through weighted aggregation of retrieved maneuvers, enabling transparent and physically consistent decision-making. Experiments in UAV navigation demonstrate real-time performance and adaptive behavior in dynamic environments as a representative embodied decision-making application scenario. --- ### A Graph Foundation Model for Wireless Resource Allocation Authors: Yucheng Sheng, Jiacheng Wang, Le Liang, Hao Ye, Shi Jin Published: 2026-04-08 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2604.07390v1 The aggressive densification of modern wireless networks necessitates judicious resource allocation to mitigate severe mutual interference. However, classical iterative algorithms remain computationally prohibitive for real-time applications requiring rapid responsiveness. While recent deep learning-based methods show promise, they typically function as task-specific solvers lacking the flexibility to adapt to different objectives and scenarios without expensive retraining. To address these limitations, we propose a graph foundation model for resource allocation (GFM-RA) based on a pre-training and fine-tuning paradigm to extract unified representations, thereby enabling rapid adaptation to different objectives and scenarios. Specifically, we introduce an interference-aware Transformer architecture with a bias projector that injects interference topologies into global attention mechanisms. Furthermore, we develop a hybrid self-supervised pre-training strategy that synergizes masked edge prediction with negative-free Teacher-Student contrastive learning, enabling the model to capture transferable structural representations from massive unlabeled datasets. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art performance and scales effectively with increased model capacity. Crucially, leveraging its unified representations, the foundation model exhibits exceptional sample efficiency, enabling robust few-shot adaptation to diverse and unsupervised downstream objectives in out-of-distribution (OOD) scenarios. These results demonstrate the promise of pre-trained foundation models for adaptable wireless resource allocation and provide a strong foundation for future research on generalizable learning-based wireless optimization. --- ### Domain-Aware Hybrid Quantum Learning via Correlation-Guided Circuit Design for Crime Pattern Analytics Authors: Niloy Das, Apurba Adhikary, Sheikh Salman Hassan, Tanvir Zaman Khan, Yu Qiao, Zhu Han, Choong Seon Hong Published: 2026-04-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.07389v3 Crime pattern analysis is critical for law enforcement and predictive policing, yet the surge in criminal activities from rapid urbanization creates high-dimensional, imbalanced datasets that challenge traditional classification methods. This study presents a quantum-classical comparison framework for crime analytics, evaluating four computational paradigms: quantum models, classical baseline machine learning models, and two hybrid quantum-classical architectures. Using 16-year crime statistics, we systematically assess classification performance and computational efficiency under rigorous cross-validation methods. Experimental results show that quantum-inspired approaches, particularly QAOA, achieve up to 84.6% accuracy, while requiring fewer trainable parameters than classical baselines, suggesting practical advantages for memory-constrained edge deployment. The proposed correlation-aware circuit design demonstrates the potential of incorporating domain-specific feature relationships into quantum models. Furthermore, hybrid approaches exhibit competitive training efficiency, making them suitable candidates for resource-constrained environments. The framework's low computational overhead and compact parameter footprint suggest potential advantages for wireless sensor network deployments in smart city surveillance systems, where distributed nodes perform localized crime analytics with minimal communication costs. Our findings provide a preliminary empirical assessment of quantum-enhanced machine learning for structured crime data and motivate further investigation with larger datasets and realistic quantum hardware considerations. --- ### Domain-Aware Hybrid Quantum Learning via Correlation-Guided Circuit Design for Crime Pattern Analytics Authors: Niloy Das, Apurba Adhikary, Sheikh Salman Hassan, Yu Qiao, Zhu Han, Tharmalingam Ratnarajah, Choong Seon Hong Published: 2026-04-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.07389v2 Crime pattern analysis is critical for law enforcement and predictive policing, yet the surge in criminal activities from rapid urbanization creates high-dimensional, imbalanced datasets that challenge traditional classification methods. This study presents a quantum-classical comparison framework for crime analytics, evaluating four computational paradigms: quantum models, classical baseline machine learning models, and two hybrid quantum-classical architectures. Using 16-year crime statistics, we systematically assess classification performance and computational efficiency under rigorous cross-validation methods. Experimental results show that quantum-inspired approaches, particularly QAOA, achieve up to 84.6% accuracy, while requiring fewer trainable parameters than classical baselines, suggesting practical advantages for memory-constrained edge deployment. The proposed correlation-aware circuit design demonstrates the potential of incorporating domain-specific feature relationships into quantum models. Furthermore, hybrid approaches exhibit competitive training efficiency, making them suitable candidates for resource-constrained environments. The framework's low computational overhead and compact parameter footprint suggest potential advantages for wireless sensor network deployments in smart city surveillance systems, where distributed nodes perform localized crime analytics with minimal communication costs. Our findings provide a preliminary empirical assessment of quantum-enhanced machine learning for structured crime data and motivate further investigation with larger datasets and realistic quantum hardware considerations. --- ### A Self-Calibrating Framework for Analog Circuit Sizing Using LLM-Derived Analytical Equations Authors: Antonio J. Bujana, Aydin I. Karsilayan Published: 2026-04-08 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2604.07387v2 We present a design automation framework for analog circuit sizing that produces calibrated, topology-specific analytical equations from raw circuit netlists. A large language model (LLM) derives a complete Python sizing function in which each device dimension is traceable to a specific design rationale - a form of interpretable output absent from existing optimization-based and LLM-based sizing methods. A deterministic calibration loop extracts process-dependent parameters from a single DC operating point simulation, while a prediction-error feedback mechanism compensates for analytical inaccuracies. We validate the framework on circuits ranging from 8 to 30 transistors - spanning two-stage Miller-compensated, current-mirror, folded cascode, nested Miller-compensated, and complementary class-AB output topologies - across three process nodes (40 nm, 90 nm, 180 nm). On matched-specification benchmarks, including the class-AB opamp case, the framework converges in 2-7 simulations. Despite large initial prediction errors, convergence depends on the measurement-feedback architecture, not prediction accuracy. The one-shot calibration automatically captures process-dependent variations, enabling cross-node portability without modification, retraining, or per-process characterization. --- ### Playing DOOM with 1.3M Parameters: Specialized Small Models vs Large Language Models for Real-Time Game Control Authors: David Golchinfar, Daryoush Vaziri, Alexander Marquardt Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07385v1 We present SauerkrautLM-Doom-MultiVec, a 1.3 million parameter model that plays the classic first-person shooter DOOM in real time, outperforming large language models up to 92,000x its size, including Nemotron-120B, Qwen3.5-27B, and GPT-4o-mini. Our model combines a ModernBERT encoder with hash embeddings, depth-aware token representations, and an attention pooling classification head to select game actions from ASCII frame representations at 31ms per decision. Trained on just 31,000 human gameplay demonstrations, it achieves 178 frags in 10 episodes (17.8 per episode) in the defend_the_center scenario, more than all tested LLMs combined (13 frags total). All agents receive equivalent input: ASCII frames and depth maps. Despite having 92,000x fewer parameters than Nemotron-120B, our model is the only agent that actively engages enemies rather than purely evading them. These results demonstrate that small, task-specific models trained on domain-appropriate data can decisively outperform general-purpose LLMs at real-time control tasks, at a fraction of the inference cost, with deployment capability on consumer hardware. --- ### Decisions and Deployment: The Five-Year SAHELI Project (2020-2025) on Restless Multi-Armed Bandits for Improving Maternal and Child Health Authors: Shresth Verma, Arpan Dasgupta, Neha Madhiwalla, Aparna Taneja, Milind Tambe Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07384v1 Maternal and child health is a critical concern around the world. In many global health programs disseminating preventive care and health information, limited healthcare worker resources prevent continuous, personalised engagement with vulnerable beneficiaries. In such scenarios, it becomes crucial to optimally schedule limited live-service resources to maximise long-term engagement. To address this fundamental challenge, the multi-year SAHELI project (2020-2025), in collaboration with partner NGO ARMMAN, leverages AI to allocate scarce resources in a maternal and child health program in India. The SAHELI system solves this sequential resource allocation problem using a Restless Multi-Armed Bandit (RMAB) framework. A key methodological innovation is the transition from a traditional Two-Stage "predict-then-optimize" approach to Decision-Focused Learning (DFL), which directly aligns the framework's learning method with the ultimate goal of maximizing beneficiary engagement. Empirical evaluation through large-scale randomized controlled trials demonstrates that the DFL policy reduced cumulative engagement drops by 31% relative to the current standard of care, significantly outperforming the Two-Stage model. Crucially, the studies also confirmed that this increased program engagement translates directly into statistically significant improvements in real-world health behaviors, notably the continued consumption of vital iron and calcium supplements by new mothers. Ultimately, the SAHELI project provides a scalable blueprint for applying sequential decision-making AI to optimize resource allocation in health programs. --- ### SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective Authors: Yuyao Wang, Min Yang, Meng Chen, Weiming Huang, Yilong Yin, Yongshun Gong Published: 2026-04-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.07383v2 Cross-city transfer improves prediction in label-scarce cities by leveraging labeled data from other cities, but it becomes challenging when cities adopt incompatible partitions and no ground-truth region correspondences exist. Existing approaches either rely on heuristic region matching, which is often sensitive to anchor choices, or perform distribution-level alignment that leaves correspondences implicit and can be unstable under strong heterogeneity. We propose SCOT, a cross-city representation learning framework that learns explicit soft correspondences between unequal region sets via Sinkhorn-based entropic optimal transport. SCOT further sharpens transferable structure with an OT-weighted contrastive objective and stabilizes optimization through a cycle-style reconstruction regularizer. For multi-source transfer, SCOT aligns each source and the target to a shared prototype hub using balanced entropic transport guided by a target-induced prototype prior. Across real-world cities and tasks, SCOT consistently improves transfer accuracy and robustness, while the learned transport couplings and hub assignments provide interpretable diagnostics of alignment quality. --- ### Latent Structure of Affective Representations in Large Language Models Authors: Benjamin J. Choi, Melanie Weber Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07382v2 The geometric structure of latent representations in large language models (LLMs) is an active area of research, driven in part by its implications for model transparency and AI safety. Existing literature has focused mainly on general geometric and topological properties of the learnt representations, but due to a lack of ground-truth latent geometry, validating the findings of such approaches is challenging. Emotion processing provides an intriguing testbed for probing representational geometry, as emotions exhibit both categorical organization and continuous affective dimensions, which are well-established in the psychology literature. Moreover, understanding such representations carries safety relevance. In this work, we investigate the latent structure of affective representations in LLMs using geometric data analysis tools. We present three main findings. First, we show that LLMs learn coherent latent representations of affective emotions that align with widely used valence--arousal models from psychology. Second, we find that these representations exhibit nonlinear geometric structure that can nonetheless be well-approximated linearly, providing empirical support for the linear representation hypothesis commonly assumed in model transparency methods. Third, we demonstrate that the learned latent representation space can be leveraged to quantify uncertainty in emotion processing tasks. Our findings suggest that LLMs acquire affective representations with geometric structure paralleling established models of human emotion, with practical implications for model interpretability and safety. --- ### The Lifecycle of the Spectral Edge: From Gradient Learning to Weight-Decay Compression Authors: Yongzhong Xu Published: 2026-04-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.07380v1 We decompose the spectral edge -- the dominant direction of the Gram matrix of parameter updates -- into its gradient and weight-decay components during grokking in two sequence tasks (Dyck-1 and SCAN). We find a sharp two-phase lifecycle: before grokking the edge is gradient-driven and functionally active; at grokking, gradient and weight decay align, and the edge becomes a compression axis that is perturbation-flat yet ablation-critical (>4000x more impactful than random directions). Three universality classes emerge (functional, mixed, compression), predicted by the gap flow equation. Nonlinear probes show information is re-encoded, not lost (MLP $R^2=0.99$ where linear $R^2=0.86$), and removing weight decay post-grok reverses compression while preserving the algorithm. ---