# Research Papers — 2026-04 · bundle page 114 of 233 > Full-text markdown of papers #5651–5700 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/114 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/113.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/115.md) ### Tracking the Temporal Dynamics of News Coverage of Catastrophic and Violent Events Authors: Emily Lugos, Maurício Gruppi Published: 2026-04-15 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2604.14315v1 The modern news cycle has been fundamentally reshaped by the rapid exchange of information online. As a result, media framing shifts dynamically as new information, political responses, and social reactions emerge. Understanding how these narratives form, propagate, and evolve is essential for interpreting public discourse during moments of crisis. In this study, we examine the temporal and semantic dynamics of reporting for violent and catastrophic events using a large-scale corpus of 126,602 news articles collected from online publishers. We quantify narrative change through publication volume, semantic drift, semantic dispersion, and term relevance. Our results show that sudden events of impact exhibit structured and predictable news-cycle patterns characterized by rapid surges in coverage, early semantic drift, and gradual declines toward the baseline. In addition, our results indicate the terms that are driving the temporal patterns. --- ### DharmaOCR: Specialized Small Language Models for Structured OCR that outperform Open-Source and Commercial Baselines Authors: Gabriel Pimenta de Freitas Cardoso, Caio Lucas da Silva Chacon, Jonas Felipe da Fonseca Oliveira, Paulo Henrique de Medeiros Araujo Published: 2026-04-15 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.14314v1 This manuscript introduces DharmaOCR Full and Lite, a pair of specialized small language models (SSLMs) for structured OCR that jointly optimize transcription quality, generation stability, and inference cost. It also presents DharmaOCR-Benchmark, a benchmark that covers printed, handwritten, and legal/administrative documents, and proposes a unified evaluation protocol that measures fidelity and structure while explicitly tracking text degeneration as a first-class benchmark metric (alongside unit cost). Beyond reporting degeneration rates, the manuscript empirically shows degeneration is not merely a quality failure, since it materially worsens production performance by increasing response time, reducing throughput, and inflating computational cost due to abnormally long generations. To the best of the author's knowledge, as a methodological contribution, this is the first application of Direct Preference Optimization (DPO) for OCR, explicitly using degenerate generations as rejected examples to penalize looping behavior. Combined with Supervised Fine-Tuning (SFT) for enforcing a strict JSON schema (header, margin, footer, and text), DPO consistently reduces degeneration rate across model families (up to 87.6% relative) while preserving or improving extraction quality. The resulting models, namely, DharmaOCR Full (7B) and DharmaOCR Lite (3B), set a new state-of-the-art on DharmaOCR-Benchmark, outperforming each open-source and commercial baseline model evaluated regarding extraction quality, reaching 0.925 and 0.911 scores with 0.40% and 0.20% degeneration rates. AWQ quantization reduced up to 22% per-page cost with negligible quality loss, enabling a strong quality-cost trade-off in comparison to proprietary OCR APIs and open-source alternatives. --- ### Aerial Multi-Functional RIS in Fluid Antennas-Aided Full-Duplex Networks: A Self-Optimized Hybrid Deep Reinforcement Learning Approach Authors: Li-Hsiang Shen, Yu-Quan Zheng Published: 2026-04-15 Categories: cs.IT, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2604.14309v2 To address high data traffic demands of sixth-generation (6G) networks, this paper proposes a novel architecture that integrates autonomous aerial vehicles (AAVs) and multi-functional reconfigurable intelligent surfaces (MF-RISs) as AM-RIS in fluid antenna (FA)-assisted full-duplex (FD) networks. The AM-RIS provides hybrid functionalities, including signal reflection, amplification, and energy harvesting (EH), potentially improving both signal coverage and sustainability. Meanwhile, FA facilitates fine-grained spatial adaptability at FD-enabled base station (BS), which complements residual self-interference (SI) suppression. We aim at maximizing the overall energy efficiency (EE) by jointly optimizing transmit DL beamforming at BS, UL user power, configuration of AM-RIS, and positions of the FA and AM-RIS. Owing to the hybrid continuous-discrete parameters and high dimensionality of the intractable problem, we have conceived a self-optimized multi-agent hybrid deep reinforcement learning (DRL) framework (SOHRL), which integrates multi-agent deep Q-networks (DQN) and multi-agent proximal policy optimization (PPO), respectively handling discrete and continuous actions. To enhance self-adaptability, an attention-driven state representation and meta-level hyperparameter optimization are incorporated, enabling multi-agents to autonomously adjust learning hyperparameters. Simulation results validate the effectiveness of the proposed AM-RIS-enabled FA-aided FD networks empowered by SOHRL algorithm. The results reveal that SOHRL outperforms benchmarks of the case without attention mechanism and conventional hybrid/multi-agent/standalone DRL. Moreover, AM-RIS in FD achieves the highest EE compared to half-duplex, conventional rigid antenna arrays, partial EH, and conventional RIS without amplification, highlighting its potential as a compelling solution for EE-aware wireless networks. --- ### EuropeMedQA Study Protocol: A Multilingual, Multimodal Medical Examination Dataset for Language Model Evaluation Authors: Francesco Andrea Causio, Vittorio De Vita, Olivia Riccomi, Michele Ferramola, Federico Felizzi, Alessandro Tosi, Antonio Cristiano, Lorenzo De Mori, Chiara Battipaglia, Melissa Sawaya, Luigi De Angelis, Marcello Di Pumpo et al. Published: 2026-04-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.14306v2 While Large Language Models (LLMs) have demonstrated high proficiency on English-centric medical examinations, their performance often declines when faced with non-English languages and multimodal diagnostic tasks. This study protocol describes the development of EuropeMedQA, the first comprehensive, multilingual, and multimodal medical examination dataset sourced from official regulatory exams in Italy, France, Spain, and Portugal. Following FAIR data principles and SPIRIT-AI guidelines, we describe a rigorous curation process and an automated translation pipeline for comparative analysis. We evaluate contemporary multimodal LLMs using a zero-shot, strictly constrained prompting strategy to assess cross-lingual transfer and visual reasoning. EuropeMedQA aims to provide a contamination-resistant benchmark that reflects the complexity of European clinical practices and fosters the development of more generalizable medical AI. --- ### Combining Bayesian and Frequentist Inference for Laboratory-Specific Performance Guarantees in Copy Number Variation Detection Authors: Austin Talbot, Alex V. Kotlar, Yue Ke Published: 2026-04-15 Categories: stat.ME, cs.LG, q-bio.GN, stat.AP arXiv: https://arxiv.org/abs/2604.14305v1 Targeted amplicon panels are widely used in oncology diagnostics, but providing per-gene performance guarantees for copy number variant (CNV) detection remains challenging due to amplification artifacts, process-mismatch heterogeneity, and limited validation sample sizes. While Bayesian CNV callers naturally quantify per-sample uncertainty, translating this into the frequentist population-level guarantees required for clinical validation, coverage rates, false-positive bounds, and minimum detectable copy-number changes, is a fundamentally different inferential problem. We show empirically that even robust Bayesian credible intervals, including coarsened posteriors and sandwich-adjusted intervals, are severely miscalibrated on panels with small amplicon counts per gene. To address this, we propose a hybrid framework that evaluates Bayesian posterior functionals on validation samples and models the resulting squared losses with a Gamma distribution, yielding tolerance intervals with valid frequentist coverage. Three components make the method practical under real-world constraints: (1) imputation that removes the influence of true CNV-positive samples without requiring known ground truth, (2) regularization to address small sample variability, and (3) evidence-based stratification on the log model evidence to accommodate non-exchangeable noise profiles arising from process mismatch. Evaluated on two targeted amplicon panels using leave-one-out cross-validation, the proposed method achieves single-digit mean absolute coverage error across all genes under both process-matched and unmatched conditions, whereas Bayesian comparators exhibit mean absolute errors exceeding 60\% on clinically relevant genes such as ERBB2. --- ### Geometrically Consistent Multi-View Scene Generation from Freehand Sketches Authors: Ahmed Bourouis, Savas Ozkan, Andrea Maracani, Yi-Zhe Song, Mete Ozay Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14302v2 We tackle a new problem: generating geometrically consistent multi-view scenes from a single freehand sketch. Freehand sketches are the most geometrically impoverished input one could offer a multi-view generator. They convey scene intent through abstract strokes while introducing spatial distortions that actively conflict with any consistent 3D interpretation. No prior method attempts this; existing multi-view approaches require photographs or text, while sketch-to-3D methods need multiple views or costly per-scene optimisation. We address three compounding challenges; absent training data, the need for geometric reasoning from distorted 2D input, and cross-view consistency, through three mutually reinforcing contributions: (i) a curated dataset of $\sim$9k sketch-to-multiview samples, constructed via an automated generation and filtering pipeline; (ii) Parallel Camera-Aware Attention Adapters (CA3) that inject geometric inductive biases into the video transformer; and (iii) a Sparse Correspondence Supervision Loss (CSL) derived from Structure-from-Motion reconstructions. Our framework synthesizes all views in a single denoising process without requiring reference images, iterative refinement, or per-scene optimization. Our approach significantly outperforms state-of-the-art two-stage baselines, improving realism (FID) by over 60% and geometric consistency (Corr-Acc) by 23%, while providing up to a 3.7$\times$ inference speedup. --- ### Quantum-inspired tensor networks in machine learning models Authors: Guillermo Valverde, Igor García-Olaizola, Giannicola Scarpa, Alejandro Pozas-Kerstjens Published: 2026-04-15 Categories: cs.LG, cs.AI, quant-ph arXiv: https://arxiv.org/abs/2604.14287v1 Tensor networks were developed in the context of many-body physics as compressed representations of multiparticle quantum states. These representations mitigate the exponential complexity of many-body systems by capturing only the most relevant dependencies. Due to the formal similarity between quantum entanglement and statistical correlations, tensor networks have recently been integrated in machine learning, operating both as alternative learning architectures and as decompositions of components of neural networks. The expectation is that the theoretical understanding of tensor networks developed within quantum many-body physics leads to novel methods that offer advantages in terms of computational efficiency, explainability, or privacy. Here we review the use of tensor networks in the context of machine learning, providing a critical assessment of the state of the art, the potential advantages, and the challenges that must be overcome. --- ### HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Authors: Team HY-World, Chenjie Cao, Xuhui Zuo, Zhenwei Wang, Yisu Zhang, Junta Wu, Zhenyang Liu, Yuning Gong, Yang Liu, Bo Yuan, Chao Zhang, Coopers Li et al. Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14268v1 We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prompts, single-view images, multi-view images, and videos, and produces 3D world representations. With text or single-view image inputs, the model performs world generation, synthesizing high-fidelity, navigable 3D Gaussian Splatting (3DGS) scenes. This is achieved through a four-stage method: a) Panorama Generation with HY-Pano 2.0, b) Trajectory Planning with WorldNav, c) World Expansion with WorldStereo 2.0, and d) World Composition with WorldMirror 2.0. Specifically, we introduce key innovations to enhance panorama fidelity, enable 3D scene understanding and planning, and upgrade WorldStereo, our keyframe-based view generation model with consistent memory. We also upgrade WorldMirror, a feed-forward model for universal 3D prediction, by refining model architecture and learning strategy, enabling world reconstruction from multi-view images or videos. Also, we introduce WorldLens, a high-performance 3DGS rendering platform featuring a flexible engine-agnostic architecture, automatic IBL lighting, efficient collision detection, and training-rendering co-design, enabling interactive exploration of 3D worlds with character support. Extensive experiments demonstrate that HY-World 2.0 achieves state-of-the-art performance on several benchmarks among open-source approaches, delivering results comparable to the closed-source model Marble. We release all model weights, code, and technical details to facilitate reproducibility and support further research on 3D world models. --- ### Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization Authors: Junzhe Wang, Zhiheng Xi, Yajie Yang, Hao Luo, Shihan Dou, Tao Gui, Qi Zhang Published: 2026-04-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14267v2 Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for training such agents, existing approaches face key limitations: process supervision often suffers from unstable value estimation, whereas outcome supervision struggles with credit assignment due to sparse, trajectory-level rewards. To bridge this gap, we propose Contribution-Weighted GRPO (CW-GRPO), a framework that integrates process supervision into group relative policy optimization. Instead of directly optimizing process rewards, CW-GRPO employs an LLM judge to assess the retrieval utility and reasoning correctness at each search round, producing per-round contribution scores. These scores are used to rescale outcome-based advantages along the trajectory, enabling fine-grained credit assignment without sacrificing optimization stability. Experiments on multiple knowledge-intensive benchmarks show that CW-GRPO outperforms standard GRPO by 5.0% on Qwen3-8B and 6.3% on Qwen3-1.7B, leading to more effective search behaviors. Additional analysis reveals that successful trajectories exhibit concentrated contributions in specific rounds, providing empirical insight into search agent tasks. --- ### Reinforcement Learning via Value Gradient Flow Authors: Haoran Xu, Kaiwen Hu, Somayeh Sojoudi, Amy Zhang Published: 2026-04-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14265v1 We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by erroneous out-of-distribution extrapolation. Existing methods either rely on reparameterized policy gradient, which are difficult to scale to large generative models, or on reject sampling, which can be overly conservative when attempting to move beyond the behavior support. In this paper, we propose Value Gradient Flow (VGF), a scalable new paradigm for behavior-regularized RL. VGF casts behavior-regularized RL as an optimal transport problem that maps the reference distribution to the value-induced optimal policy distribution. We solve this transport problem via discrete gradient flow, where value gradients guide particles initialized from the reference distribution. Our analysis shows that VGF imposes regularization implicitly by controlling the transport budget. VGF eliminates explicit policy parameterization while remaining expressive and flexible, this enables adaptive test-time scaling by adjusting the transport budget. Extensive experiments demonstrate that VGF significantly outperforms prior methods, achieving state-of-the-art results on offline RL benchmarks (D4RL, OGBench) and LLM RL tasks. Code and runs can be found at https://ryanxhr.github.io/vgf. --- ### A deep learning framework for glomeruli segmentation with boundary attention Authors: Behnaz Elhaminia, Catherine King, Jiaqi Lv, Lorraine Harper, Paul Moss, Owen Cain, Dimitrios Chanouzas, Shan E Ahmed Raza Published: 2026-04-15 Categories: q-bio.TO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.14263v1 Accurate detection and segmentation of glomeruli in kidney tissue are essential for diagnostic applications. Traditional deep learning methods primarily rely on semantic segmentation, which often fails to precisely delineate adjacent glomeruli. To address this challenge, we propose a novel glomerulus detection and segmentation model that emphasises boundary separation. Leveraging pathology foundation models, the proposed U-Net-based architecture incorporates a specialised attention decoder designed to highlight critical regions and improve instancelevel segmentation. Experimental evaluations demonstrate that our approach surpasses state-of-the-art methods in both Dice score and Intersection over Union, indicating superior performance in glomerular delineation. --- ### GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models Authors: Yangyue Wang, Harshvardhan Sikka, Yash Mathur, Tony Zhou, Jinu Nyachhyon, Pranav Guruprasad Published: 2026-04-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14262v2 GUI grounding models report over 85% accuracy on standard benchmarks, yet drop 27-56 percentage points when instructions require spatial reasoning rather than direct element naming. Current benchmarks miss this because they evaluate each screenshot once with a single fixed instruction. We introduce GUI-Perturbed, a controlled perturbation framework that independently varies visual scenes and instructions to measure grounding robustness. Evaluating three 7B models from the same architecture lineage, we find that relational instructions cause systematic accuracy collapse across all models, a 70% browser zoom produces statistically significant degradation, and rank-8 LoRA fine-tuning with augmented data degrades performance rather than improving it. By perturbing along independent axes, GUI-Perturbed isolates which specific capability axes are affected-spatial reasoning, visual robustness, reasoning calibration-providing diagnostic signal that aggregate benchmarks cannot. We release the dataset, augmentation pipeline, and a fine-tuned model. --- ### ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents Authors: Zhuofeng Li, Yi Lu, Dongfu Jiang, Haoxiang Zhang, Yuyang Bai, Chuan Li, Yu Wang, Shuiwang Ji, Jianwen Xie, Yu Zhang Published: 2026-04-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.14261v1 The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate superficial, formulaic comments lacking substantive, evidence-grounded feedback. We attribute this to the underutilization of two key components of human reviewing: explicit rubrics and contextual grounding in existing work. To address this, we introduce REVIEWBENCH, a benchmark evaluating review text according to paper-specific rubrics derived from official guidelines, the paper's content, and human-written reviews. We further propose REVIEWGROUNDER, a rubric-guided, tool-integrated multi-agent framework that decomposes reviewing into drafting and grounding stages, enriching shallow drafts via targeted evidence consolidation. Experiments on REVIEWBENCH show that REVIEWGROUNDER, using a Phi-4-14B-based drafter and a GPT-OSS-120B-based grounding stage, consistently outperforms baselines with substantially stronger/larger backbones (e.g., GPT-4.1 and DeepSeek-R1-670B) in both alignment with human judgments and rubric-based review quality across 8 dimensions. The code is available \href{https://github.com/EigenTom/ReviewGrounder}{here}. --- ### Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay Authors: Qianyu Chen, Shujian Yu Published: 2026-04-15 Categories: q-bio.TO, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2604.14259v1 Functional magnetic resonance imaging (fMRI) is widely used for studying and diagnosing brain disorders, with functional connectivity (FC) matrices providing powerful representations of large-scale neural interactions. However, existing diagnostic models are trained either on a single site or under full multi-site access, making them unsuitable for real-world scenarios where clinical data arrive sequentially from different institutions. This results in limited generalization and severe catastrophic forgetting. This paper presents the first continual learning framework specifically designed for fMRI-based diagnosis across heterogeneous clinical sites. Our framework introduces a structure-aware variational autoencoder that synthesizes realistic FC matrices for both patient and control groups. Built on this generative backbone, we develop a multi-level knowledge distillation strategy that aligns predictions and graph representations between new-site data and replayed samples. To further enhance efficiency, we incorporate a hierarchical contextual bandit scheme for adaptive replay sampling. Experiments on multi-site datasets for major depressive disorder (MDD), schizophrenia (SZ), and autism spectrum disorder (ASD) show that the proposed generative model enhances data augmentation quality, and the overall continual learning framework substantially outperforms existing methods in mitigating catastrophic forgetting. Our code is available at https://github.com/4me808/FORGE. --- ### GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification Authors: Wangjie Gan, Miao Pan, Linbo Xi, Wenqi Zhang, Jintao Chen, Jianwei Yin, Xuhong Zhang Published: 2026-04-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.14258v3 Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we provide a training-dynamics analysis showing that SFT can be interpreted as a special case of policy gradient optimization with an extremely sparse implicit reward and unstable inverse-probability weighting, which together lead to single-path dependency, entropy collapse, and gradient explosion. Motivated by this diagnosis, we propose Group Fine-Tuning (GFT), a unified post-training framework that addresses these intrinsic limitations through two mechanisms: Group Advantage Learning, which constructs diverse response groups and derives normalized contrastive supervision to alleviate reward sparsity, and Dynamic Coefficient Rectification, which adaptively bounds inverse-probability weights to stabilize optimization while preserving efficient knowledge injection. Experiments demonstrate that GFT consistently surpasses SFT-based methods and yields policies that integrate more smoothly with subsequent RL training. --- ### Evaluation of Agents under Simulated AI Marketplace Dynamics Authors: To Eun Kim, Alireza Salemi, Hamed Zamani, Fernando Diaz Published: 2026-04-15 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.14256v1 Modern information access ecosystems consist of mixtures of systems, such as retrieval systems and large language models, and increasingly rely on marketplaces to mediate access to models, tools, and data, making competition between systems inherent to deployment. In such settings, outcomes are shaped not only by benchmark quality but also by competitive pressure, including user switching, routing decisions, and operational constraints. Yet evaluation is still largely conducted on static benchmarks with accuracy-focused measures that assume systems operate in isolation. This mismatch makes it difficult to predict post-deployment success and obscures competitive effects such as early-adoption advantages and market dominance. We introduce Marketplace Evaluation, a simulation-based paradigm that evaluates information access systems as participants in a competitive marketplace. By simulating repeated interactions and evolving user and agent preferences, the framework enables longitudinal evaluation and marketplace-level metrics, such as retention and market share, that complement and can extend beyond traditional accuracy-based metrics. We formalize the framework and outline a research agenda, motivated by business and economics, around marketplace simulation, metrics, optimization, and adoption in evaluation campaigns like TREC. --- ### Formalizing Kantian Ethics: Formula of the Universal Law Logic (FULL) Authors: Taylor Olson Published: 2026-04-15 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2604.14254v1 The field of machine ethics aims to build Artificial Moral Agents (AMAs) to better understand morality and make AI agents safer. To do so, many approaches encode human moral intuition as a set of axioms on actions e.g., do not harm, you must help others. However, this introduces (at least) two limitations for future AMAs. First, it does not consider the agent's purposes in performing the action. Second, it assumes that we humans can enumerate our moral intuition. This paper explores formalizing a moral procedure that alleviates these two limitations. We specifically consider Kantian ethics and present a multi-sorted quantified modal logic we call the Formula of the Universal Law Logic (FULL). The FULL formalizes Kant's first formulation of the categorical imperative, the Formula of the Universal Law (FUL), and concepts such as causality and agency. We demonstrate on three cases from Kantian ethics that the FULL can reason to evaluate agents' actions for certain purposes without built-in moral intuition, given that it has sufficient (non-normative) background knowledge. Therefore, the FULL is a contribution towards more robust and autonomous AMAs, and a more formal understanding of Kantian ethics. --- ### Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades Authors: Edoardo Pona, Milad Kazemi, Mehran Hosseini, Yali Du, David Watson, Osvaldo Simeone, Nicola Paoletti Published: 2026-04-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.14251v2 Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive expert. Existing cascades delegate based on probe uncertainty, but uncertainty is a poor proxy for the utility of an expert call, as it ignores whether the expert would actually improve the prediction. To address this problem, we introduce Calibrate-Then-Delegate (CTD), a model-cascade approach that provides probabilistic guarantees on either computation cost or safety performance while enabling instance-level (streaming) decisions. CTD builds on a novel delegation value (DV) probe, a lightweight model operating on the same internal representations as the safety probe that predicts the benefit of replacing the probe score with the expert score after an expert call. CTD calibrates a threshold on the DV signal using held-out data and multiple hypothesis testing, yielding finite-sample guarantees while optimising the complementary objective. Evaluated on four safety datasets using learned-attention probes, CTD improves over uncertainty-based delegation over much of the budget range, avoids unnecessary expert calls, and extracts positive-value subsets even from groups where the expert score is worse than the probe score on average. Ablations across four probe architectures show that these findings are not specific to any particular architecture. --- ### Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades Authors: Edoardo Pona, Milad Kazemi, Mehran Hosseini, Yali Du, David Watson, Osvaldo Simeone, Nicola Paoletti Published: 2026-04-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.14251v1 Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive expert. Existing cascades delegate based on probe uncertainty, but uncertainty is a poor proxy for delegation benefit, as it ignores whether the expert would actually correct the error. To address this problem, we introduce Calibrate-Then-Delegate (CTD), a model-cascade approach that provides probabilistic guarantees on the computation cost while enabling instance-level (streaming) decisions. CTD builds on a novel delegation value (DV) probe, a lightweight model operating on the same internal representations as the safety probe that directly predicts the benefit of escalation. To enforce budget constraints, CTD calibrates a threshold on the DV signal using held-out data via multiple hypothesis testing, yielding finite-sample guarantees on the delegation rate. Evaluated on four safety datasets, CTD consistently outperforms uncertainty-based delegation at every budget level, avoids harmful over-delegation, and adapts budget allocation to input difficulty without requiring group labels. --- ### Metric-Aware Principal Component Analysis (MAPCA):A Unified Framework for Scale-Invariant Representation Learning Authors: Michael Leznik Published: 2026-04-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.14249v1 We introduce Metric-Aware Principal Component Analysis (MAPCA), a unified framework for scale-invariant representation learning based on the generalised eigenproblem max Tr(W^T Sigma W) subject to W^T M W = I, where M is a symmetric positive definite metric matrix. The choice of M determines the representation geometry. The canonical beta-family M(beta) = Sigma^beta, beta in (0,1), provides continuous spectral bias control between standard PCA (beta=0) and output whitening (beta=1), with condition number kappa(beta) = (lambda_1/lambda_p)^(1-beta) decreasing monotonically to isotropy. The diagonal metric M = D = diag(Sigma) recovers Invariant PCA (IPCA), a method rooted in Frisch (1928) diagonal regression, as a distinct member of the broader framework. We prove that scale invariance holds if and only if the metric transforms as M_tilde = CMC under rescaling C, a condition satisfied exactly by IPCA but not by the general beta-family at intermediate values. Beyond its classical interpretation, MAPCA provides a geometric language that unifies several self-supervised learning objectives. Barlow Twins and ZCA whitening correspond to beta=1 (output whitening); VICReg's variance term corresponds to the diagonal metric. A key finding is that W-MSE, despite being described as a whitening-based method, corresponds to M = Sigma^{-1} (beta = -1), outside the spectral compression range entirely and in the opposite spectral direction to Barlow Twins. This distinction between input and output whitening is invisible at the level of loss functions and becomes precise only within the MAPCA framework. --- ### Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations Authors: Wentao Hu, Yanbo Zhai, Xiaohui Hu, Mingkuan Zhao, Shanhong yu, Xue Liu, Kaidong Yu, Shuangyong Song, Xuelong Li Published: 2026-04-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14246v2 Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hallucinations, particularly when processing long-tail knowledge. We identify that this fragility stems from static Top-$k$ routing: routers tend to favor high-frequency patterns over rare factual associations. Consequently, ``specialist experts'' possessing critical long-tail knowledge are often assigned low gating scores and remain ``dormant'' -- under-prioritized for specific tokens despite their proven causal importance on other inputs. To address this, we propose Counterfactual Routing (CoR), a training-free inference framework designed to awaken these dormant experts. CoR integrates layer-wise perturbation analysis with the Counterfactual Expert Impact (CEI) metric to dynamically shift computational resources from syntax-dominant to knowledge-intensive layers while maintaining a constant total activation count, effectively retrieving causally decisive experts via virtual ablation. Extensive experiments on TruthfulQA, FACTOR, and TriviaQA demonstrate that CoR improves factual accuracy by 3.1\% on average without increasing the inference budget, establishing a superior Pareto frontier compared to static scaling strategies. --- ### Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees Authors: Sourav Ganguly, Kartik Pandit, Arnob Ghosh Published: 2026-04-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14243v2 Real-world decision-making systems operate in environments where state transitions depend not only on the agent's actions, but also on \textbf{exogenous factors outside its control}--competing agents, environmental disturbances, or strategic adversaries--formally, $s_{h+1} = f(s_h, a_h, \bar{a}_h)+ω_h$ where $\bar{a}_h$ is the adversary/external action, $a_h$ is the agent's action, and $ω_h$ is an additive noise. Ignoring such factors can yield policies that are optimal in isolation but \textbf{fail catastrophically in deployment}, particularly when safety constraints must be satisfied. Standard Constrained MDP formulations assume the agent is the sole driver of state evolution, an assumption that breaks down in safety-critical settings. Existing robust RL approaches address this via distributional robustness over transition kernels, but do not explicitly model the \textbf{strategic interaction} between agent and exogenous factor, and rely on strong assumptions about divergence from a known nominal model. We model the exogenous factor as an \textbf{adversarial policy} $\barπ$ that co-determines state transitions, and ask how an agent can remain both optimal and safe against such an adversary. \emph{To the best of our knowledge, this is the first work to study safety-constrained RL under explicit adversarial dynamics}. We propose \textbf{Robust Hallucinated Constrained Upper-Confidence RL} (\texttt{RHC-UCRL}), a model-based algorithm that maintains optimism over both agent and adversary policies, explicitly separating epistemic from aleatoric uncertainty. \texttt{RHC-UCRL} achieves sub-linear regret and constraint violation guarantees. --- ### Polyformer: a generative framework for thermodynamic modeling of polymeric molecules Authors: Alessio Valentini, David Pekker, Chungwen Liang, Todd Martinez, Swagatam Mukhopadhyay Published: 2026-04-15 Categories: q-bio.BM, cond-mat.stat-mech, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2604.14241v2 The classic paradigm of structural biology is that the sequence of a biomolecule (protein, nucleic acid, lipid, etc) determines its conformation (shape) which determines its biological function. Protein folding programs like AlphaFold address this paradigm by predicting the single best conformation given a sequence that defines the molecule. However, biomolecules are not static structures, and their conformational ensemble determines their function. We present the Polyformer -- a generative framework for thermodynamic modeling of polymeric molecules. Given the sequence and temperature (or another thermodynamic variable), the Polyformer generates conformations faithful to the molecule's thermodynamic conformational ensemble. It is the first generative model that solves three problems simultaneously: how does a molecule fold, what is its conformational ensemble, and how does the conformational ensemble change as we change physical temperature. As a concrete test case, we apply Polyformer to protein domains with 50-111 residues and report good agreement of model predictions to Molecular Dynamics (MD) trajectories. --- ### Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making Authors: Pramudita Satria Palar, Paul Saves, Muhammad Daffa Robani, Nicolas Verstaevel, Moncef Garouani, Julien Aligon, Koji Shimoyama, Joseph Morlier, Benoit Gaudou Published: 2026-04-15 Categories: cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.14240v1 The simulation of complex systems increasingly relies on sophisticated but fundamentally opaque computational black-box simulators. Surrogate models play a central role in reducing the computational cost of complex systems simulations across a wide range of scientific and engineering domains. Notwithstanding, they inevitably inherit and often exacerbate this black-box nature, obscuring how input variables drive physical responses. Conversely, Explainable Artificial Intelligence (XAI) offers powerful tools to unpack these models. Yet, XAI methods struggle with engineering-specific constraints, such as highly correlated inputs, dynamical systems, and rigorous reliability requirements. Consequently, surrogate modeling and XAI have largely evolved as distinct fields of research, despite their strong complementarity. To reconnect these approaches, this state-of-the-art survey provides a structured perspective that maps existing XAI techniques onto the various stages of surrogate modeling workflows for design and exploration. To ground this synthesis, we draw upon illustrative applications across both equation-based simulations and agent-based modeling. We survey a broad spectrum of techniques, highlighting their strengths for revealing interactions and supporting human comprehension. Finally, we identify pressing open challenges, including the explainability of dynamical systems and the handling of mixed-variable systems, and propose a research agenda to make explainability a core, embedded element of simulation-driven workflows from model construction through decision-making. By transforming opaque emulators into explainable tools, this agenda empowers practitioners to move beyond accelerating simulations to extracting actionable insights from complex system behaviors. --- ### TOPCELL: Topology Optimization of Standard Cell via LLMs Authors: Zhan Song, Yu-Tung Liu, Chen Chen, Guoheng Sun, Jiaqi Yin, Chia-tung Ho, Ang Li, Haoxing Ren, Cunxi Yu Published: 2026-04-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.14237v1 Transistor topology optimization is a critical step in standard cell design, directly dictating diffusion sharing efficiency and downstream routability. However, identifying optimal topologies remains a persistent bottleneck, as conventional exhaustive search methods become computationally intractable with increasing circuit complexity in advanced nodes. This paper introduces TOPCELL, a novel and scalable framework that reformulates high-dimensional topology exploration as a generative task using Large Language Models (LLMs). We employ Group Relative Policy Optimization (GRPO) to fine-tune the model, aligning its topology optimization strategy with logical (circuit) and spatial (layout) constraints. Experimental results within an industrial flow targeting an advanced 2nm technology node demonstrate that TOPCELL significantly outperforms foundation models in discovering routable, physically-aware topologies. When integrated into a state-of-the-art (SOTA) automation flow for a 7nm library generation task, TOPCELL exhibits robust zero-shot generalization and matches the layout quality of exhaustive solvers while achieving an 85.91x speedup. --- ### One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding Authors: Zheyu Zhang, Ziqi Pang, Shixing Chen, Xiang Hao, Vimal Bhat, Yu-Xiong Wang Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14149v2 Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large language models (LLMs) forces the VLMs to perceive the frames sparsely and lose temporal information. To address this, we explore extreme video token compression towards one token per frame at the final LLM layer. Our key insight is that heuristic-based compression, widely adopted by previous methods, is prone to information loss, and this necessitates supervising LLM layers into learnable and progressive modules for token-level compression (LP-Comp). Such compression enables our VLM to digest 2x-4x more frames with improved performance. To further increase the token efficiency, we investigate frame-level compression, which selects the frames most relevant to the queries via the internal attention scores of the LLM layers, named question-conditioned compression (QC-Comp). As a notable distinction from previous studies, we mitigate the position bias of LLM attention in long contexts, i.e., the over-concentration on the beginning and end of a sequence, by splitting long videos into short segments and employing local attention. Collectively, our combined token-level and frame-level leads to an extreme compression model for long video understanding, named XComp, achieving a significantly larger compression ratio and enabling denser frame sampling. Our XComp is finetuned from VideoChat-Flash with a data-efficient supervised compression tuning stage that only requires 2.5% of the supervised fine-tuning data, yet boosts the accuracy from 42.9% to 46.2% on LVBench and enhances multiple other long video benchmarks. --- ### Seedance 2.0: Advancing Video Generation for World Complexity Authors: Team Seedance, De Chen, Liyang Chen, Xin Chen, Ying Chen, Zhuo Chen, Zhuowei Chen, Feng Cheng, Tianheng Cheng, Yufeng Cheng, Mojie Chi, Xuyan Chi et al. Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14148v1 Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users. --- ### ROSE: Retrieval-Oriented Segmentation Enhancement Authors: Song Tang, Guangquan Jie, Henghui Ding, Yu-Gang Jiang Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14147v1 Existing segmentation models based on multimodal large language models (MLLMs), such as LISA, often struggle with novel or emerging entities due to their inability to incorporate up-to-date knowledge. To address this challenge, we introduce the Novel Emerging Segmentation Task (NEST), which focuses on segmenting (i) novel entities that MLLMs fail to recognize due to their absence from training data, and (ii) emerging entities that exist within the model's knowledge but demand up-to-date external information for accurate recognition. To support the study of NEST, we construct a NEST benchmark using an automated pipeline that generates news-related data samples for comprehensive evaluation. Additionally, we propose ROSE: Retrieval-Oriented Segmentation Enhancement, a plug-and-play framework designed to augment any MLLM-based segmentation model. ROSE comprises four key components. First, an Internet Retrieval-Augmented Generation module is introduced to employ user-provided multimodal inputs to retrieve real-time web information. Then, a Textual Prompt Enhancer enriches the model with up-to-date information and rich background knowledge, improving the model's perception ability for emerging entities. Furthermore, a Visual Prompt Enhancer is proposed to compensate for MLLMs' lack of exposure to novel entities by leveraging internet-sourced images. To maintain efficiency, a WebSense module is introduced to intelligently decide when to invoke retrieval mechanisms based on user input. Experimental results demonstrate that ROSE significantly boosts performance on the NEST benchmark, outperforming a strong Gemini-2.0 Flash-based retrieval baseline by 19.2 in gIoU. --- ### SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments Authors: Dinging Li, Yingxiu Zhao, Xinrui Cheng, Kangheng Lin, Hongbo Peng, Hongxing Li, Zixuan Wang, Yuhong Dai, Haodong Li, Jia Wang, Yukang Shi, Liang Zhao et al. Published: 2026-04-15 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.14144v1 Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked by the cost of geometric annotation. The self-evolving paradigm offers a promising path, but its reliance on model consensus to construct pseudo-labels causes training to reinforce rather than correct the model's own geometric errors. We identify a property unique to 3D spatial reasoning that circumvents this limitation: ground truth is a deterministic consequence of the underlying geometry, computable exactly from point clouds and camera poses without any model involvement. Building on this insight, we present SpatialEvo, a self-evolving framework for 3D spatial reasoning, centered on the Deterministic Geometric Environment (DGE). The DGE formalizes 16 spatial reasoning task categories under explicit geometric validation rules and converts unannotated 3D scenes into zero-noise interactive oracles, replacing model consensus with objective physical feedback. A single shared-parameter policy co-evolves across questioner and solver roles under DGE constraints: the questioner generates physically valid spatial questions grounded in scene observations, while the solver derives precise answers against DGE-verified ground truth. A task-adaptive scheduler endogenously concentrates training on the model's weakest categories, producing a dynamic curriculum without manual design. Experiments across nine benchmarks demonstrate that SpatialEvo achieves the highest average score at both 3B and 7B scales, with consistent gains on spatial reasoning benchmarks and no degradation on general visual understanding. --- ### From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space Authors: Yuqiao Tan, Minzheng Wang, Bo Liu, Zichen Liu, Tian Liang, Shizhu He, Jun Zhao, Kang Liu Published: 2026-04-15 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.14142v1 While reinforcement learning with verifiable rewards (RLVR) significantly enhances LLM reasoning by optimizing the conditional distribution P(y|x), its potential is fundamentally bounded by the base model's existing output distribution. Optimizing the marginal distribution P(y) in the Pre-train Space addresses this bottleneck by encoding reasoning ability and preserving broad exploration capacity. Yet, conventional pre-training relies on static corpora for passive learning, leading to a distribution shift that hinders targeted reasoning enhancement. In this paper, we introduce PreRL (Pre-train Space RL), which applies reward-driven online updates directly to P(y). We theoretically and empirically validate the strong gradient alignment between log P(y) and log P(y|x), establishing PreRL as a viable surrogate for standard RL. Furthermore, we uncover a critical mechanism: Negative Sample Reinforcement (NSR) within PreRL serves as an exceptionally effective driver for reasoning. NSR-PreRL rapidly prunes incorrect reasoning spaces while stimulating endogenous reflective behaviors, increasing transition and reflection thoughts by 14.89x and 6.54x, respectively. Leveraging these insights, we propose Dual Space RL (DSRL), a Policy Reincarnation strategy that initializes models with NSR-PreRL to expand the reasoning horizon before transitioning to standard RL for fine-grained optimization. Extensive experiments demonstrate that DSRL consistently outperforms strong baselines, proving that pre-train space pruning effectively steers the policy toward a refined correct reasoning subspace. --- ### LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction Authors: Lin-Zhuo Chen, Jian Gao, Shangzhan Zhang, Yihang Chen, Ka Leong Cheng, Yipengjing Sun, Liangxiao Hu, Nan Xue, Xing Zhu, Yujun Shen, Yao Yao, Yinghao Xu Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14141v3 Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency, and computational efficiency. Motivated by the principles of Simultaneous Localization and Mapping (SLAM), we introduce LingBot-Map, a feed-forward 3D foundation model for reconstructing scenes from streaming data, built upon a geometric context transformer (GCT) architecture. A defining aspect of LingBot-Map lies in its carefully designed attention mechanism, which integrates an anchor context, a pose-reference window, and a trajectory memory to address coordinate grounding, dense geometric cues, and long-range drift correction, respectively. This design keeps the streaming state compact while retaining rich geometric context, enabling stable efficient inference at around 20 FPS on 518 x 378 resolution inputs over long sequences exceeding 10,000 frames. Extensive evaluations across a variety of benchmarks demonstrate that our approach achieves superior performance compared to both existing streaming and iterative optimization-based approaches. --- ### Geometric Context Transformer for Streaming 3D Reconstruction Authors: Lin-Zhuo Chen, Jian Gao, Yihang Chen, Ka Leong Cheng, Yipengjing Sun, Liangxiao Hu, Nan Xue, Xing Zhu, Yujun Shen, Yao Yao, Yinghao Xu Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14141v2 Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency, and computational efficiency. Motivated by the principles of Simultaneous Localization and Mapping (SLAM), we introduce LingBot-Map, a feed-forward 3D foundation model for reconstructing scenes from streaming data, built upon a geometric context transformer (GCT) architecture. A defining aspect of LingBot-Map lies in its carefully designed attention mechanism, which integrates an anchor context, a pose-reference window, and a trajectory memory to address coordinate grounding, dense geometric cues, and long-range drift correction, respectively. This design keeps the streaming state compact while retaining rich geometric context, enabling stable efficient inference at around 20 FPS on 518 x 378 resolution inputs over long sequences exceeding 10,000 frames. Extensive evaluations across a variety of benchmarks demonstrate that our approach achieves superior performance compared to both existing streaming and iterative optimization-based approaches. --- ### LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning Authors: Sumeet Ramesh Motwani, Daniel Nichols, Charles London, Peggy Li, Fabio Pizzati, Acer Blake, Hasan Hammoud, Tavish McDonald, Akshat Naik, Alesia Ivanova, Vignesh Baskaran, Ivan Laptev et al. Published: 2026-04-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14140v1 As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this ability is planning and managing a long, complex chain-of-thought (CoT). We introduce LongCoT, a scalable benchmark of 2,500 expert-designed problems spanning chemistry, mathematics, computer science, chess, and logic to isolate and directly measure the long-horizon CoT reasoning capabilities of frontier models. Problems consist of a short input with a verifiable answer; solving them requires navigating a graph of interdependent steps that span tens to hundreds of thousands of reasoning tokens. Each local step is individually tractable for frontier models, so failures reflect long-horizon reasoning limitations. At release, the best models achieve <10% accuracy (GPT 5.2: 9.8%; Gemini 3 Pro: 6.1%) on LongCoT, revealing a substantial gap in current capabilities. Overall, LongCoT provides a rigorous measure of long-horizon reasoning, tracking the ability of frontier models to reason reliably over extended periods. --- ### From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs Authors: Itay Itzhak, Eliya Habba, Gabriel Stanovsky, Yonatan Belinkov Published: 2026-04-15 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.14137v3 Evaluating LLMs is challenging, as benchmark scores often fail to capture models' real-world usefulness. Instead, users often rely on ``vibe-testing'': informal experience-based evaluation, such as comparing models on coding tasks related to their own workflow. While prevalent, vibe-testing is often too ad hoc and unstructured to analyze or reproduce at scale. In this work, we study how vibe-testing works in practice and then formalize it to support systematic analysis. We first analyze two empirical resources: (1) a survey of user evaluation practices, and (2) a collection of in-the-wild model comparison reports from blogs and social media. Based on these resources, we formalize vibe-testing as a two-part process: users personalize both what they test and how they judge responses. We then introduce a proof-of-concept evaluation pipeline that follows this formulation by generating personalized prompts and comparing model outputs using user-aware subjective criteria. In experiments on coding benchmarks, we find that combining personalized prompts and user-aware evaluation can change which model is preferred, reflecting the role of vibe-testing in practice. These findings suggest that formalized vibe-testing can serve as a useful approach for bridging benchmark scores and real-world experience. --- ### Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models Authors: Ami Baid, Zihui Xue, Kristen Grauman Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14129v2 While Audio-Visual Language Models (AVLMs) have achieved remarkable progress over recent years, their reliability is bottlenecked by cross-modal hallucination. A particularly pervasive manifestation is video-driven audio hallucination: models routinely exploit visual shortcuts to hallucinate expected sounds, discarding true auditory evidence. To counteract this deeply ingrained visual dominance, we propose Audio-Contrastive Preference Optimization (ACPO). This dual-axis preference learning framework introduces an output-contrastive objective to penalize visual descriptions masquerading as audio facts, alongside an input-contrastive objective that swaps audio tracks to explicitly penalize generation invariant to the true auditory signal. Extensive experiments demonstrate that ACPO establishes highly faithful audio grounding and mitigates audio hallucination. --- ### Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models Authors: Ami Baid, Zihui Xue, Kristen Grauman Published: 2026-04-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14129v1 While Audio-Visual Language Models (AVLMs) have achieved remarkable progress over recent years, their reliability is bottlenecked by cross-modal hallucination. A particularly pervasive manifestation is video-driven audio hallucination: models routinely exploit visual shortcuts to hallucinate expected sounds, discarding true auditory evidence. To counteract this deeply ingrained visual dominance, we propose Audio-Contrastive Preference Optimization (ACPO). This dual-axis preference learning framework introduces an output-contrastive objective to penalize visual descriptions masquerading as audio facts, alongside an input-contrastive objective that swaps audio tracks to explicitly penalize generation invariant to the true auditory signal. Extensive experiments demonstrate that ACPO establishes highly faithful audio grounding and mitigates audio hallucination without compromising overarching multimodal capabilities. --- ### Rhetorical Questions in LLM Representations: A Linear Probing Study Authors: Louie Hong Yao, Vishesh Anand, Yuan Zhuang, Tianyu Jiang Published: 2026-04-15 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.14128v2 Rhetorical questions are asked not to seek information but to persuade or signal stance. How large language models internally represent them remains unclear. We analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts, and find that rhetorical signals emerge early and are most stably captured by last-token representations. Rhetorical questions are linearly separable from information-seeking questions within datasets, and remain detectable under cross-dataset transfer, reaching AUROC around 0.7-0.8. However, we demonstrate that transferability does not simply imply a shared representation. Probes trained on different datasets produce different rankings when applied to the same target corpus, with overlap among the top-ranked instances often below 0.2. Qualitative analysis shows that these divergences correspond to distinct rhetorical phenomena: some probes capture discourse-level rhetorical stance embedded in extended argumentation, while others emphasize localized, syntax-driven interrogative acts. Together, these findings suggest that rhetorical questions in LLM representations are encoded by multiple linear directions emphasizing different cues, rather than a single shared direction. --- ### HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System Authors: Tianshuo Yang, Guanyu Chen, Yutian Chen, Zhixuan Liang, Yitian Liu, Zanxin Chen, Chunpu Xu, Haotian Liang, Jiangmiao Pang, Yao Mu, Ping Luo Published: 2026-04-15 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2604.14125v2 While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound reasoning capabilities inherited from their base Vision-Language Models (VLMs). To resolve this fundamental trade-off, we propose HiVLA, a visual-grounded-centric hierarchical framework that explicitly decouples high-level semantic planning from low-level motor control. In high-level part, a VLM planner first performs task decomposition and visual grounding to generate structured plans, comprising a subtask instruction and a precise target bounding box. Then, to translate this plan into physical actions, we introduce a flow-matching Diffusion Transformer (DiT) action expert in low-level part equipped with a novel cascaded cross-attention mechanism. This design sequentially fuses global context, high-resolution object-centric crops and skill semantics, enabling the DiT to focus purely on robust execution. Our decoupled architecture preserves the VLM's zero-shot reasoning while allowing independent improvement of both components. Extensive experiments in simulation and the real world demonstrate that HiVLA significantly outperforms state-of-the-art end-to-end baselines, particularly excelling in long-horizon skill composition and the fine-grained manipulation of small objects in cluttered scenes. --- ### Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis Authors: Zipeng Ling, Shuliang Liu, Seonil Son, Shenghong Fu, Yuehao Tang, Yao Wan, Xuming Hu Published: 2026-04-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14121v4 Large language models (LLMs) have become increasingly used for various tasks, often coupled with Chain-of-Thought (CoT) prompting to boost accuracy. Recent work has shown that high label-prediction accuracy does not guarantee correct intermediate reasoning, and the causes of *reasoning flaws* vary from sample to sample, yet existing remedies either focus on a single domain or assume that one flaw type applies uniformly across samples. A simple mitigation method is to provide the model with the correct answer, but we show that this yields no consistent improvement in reasoning quality. This indicates that the problem cannot be fixed by LLMs' awareness of answers, and must instead be addressed through the *structure* of reasoning. Motivated by this, we propose **CRAFT** (**C**onsensus **R**easoning-knowledge-graph **A**ggregation for **F**law-aware **T**race synthesis), which aggregates the consensus components shared across multiple candidate reasoning traces to synthesize improved ones. **CRAFT** consistently improves label-prediction accuracy on both logical and mathematical reasoning benchmarks, outperforming most baselines, while its post-processed traces achieve higher quality under fine-grained benchmark evaluation. --- ### Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis Authors: Zipeng Ling, Shuliang Liu, Shenghong Fu, Yuehao Tang, Seonil Son, Yao Wan, Xuming Hu Published: 2026-04-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14121v1 LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, underthinking), which vary by sample. A natural approach would be to provide ground-truth labels to guide LLMs' reasoning. Contrary to intuition, we show that this yields no improvement in reasoning ability. We then propose CRAFT, a unified framework that mitigates both types of Step flaws, which builds a Reasoning Knowledge Graph (RKG) based on the consensus parts of multiple candidate traces, and synthesizes a high-quality trace through topological generation. Our approach improves label-prediction accuracy by 10+% on average, and consistently outperforms all baselines across both logical and mathematical reasoning benchmarks. Further, detailed benchmark evaluation proves that our method also improves the quality of LLMs' reasoning traces in multiple dimensions. --- ### Complex Interpolation of Matrices with an application to Multi-Manifold Learning Authors: Adi Arbel, Stefan Steinerberger, Ronen Talmon Published: 2026-04-15 Categories: cs.LG, math.SP arXiv: https://arxiv.org/abs/2604.14118v1 Given two symmetric positive-definite matrices $A, B \in \mathbb{R}^{n \times n}$, we study the spectral properties of the interpolation $A^{1-x} B^x$ for $0 \leq x \leq 1$. The presence of `common structures' in $A$ and $B$, eigenvectors pointing in a similar direction, can be investigated using this interpolation perspective. Generically, exact log-linearity of the operator norm $\|A^{1-x} B^x\|$ is equivalent to the existence of a shared eigenvector in the original matrices; stability bounds show that approximate log-linearity forces principal singular vectors to align with leading eigenvectors of both matrices. These results give rise to and provide theoretical justification for a multi-manifold learning framework that identifies common and distinct latent structures in multiview data. --- ### TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration Authors: Zerun Ma, Guoqiang Wang, Xinchen Xie, Yicheng Chen, He Du, Bowen Li, Yanan Sun, Wenran Liu, Kai Chen, Yining Li Published: 2026-04-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.14116v2 While Large Language Models (LLMs) have empowered AI research agents to perform isolated scientific tasks, automating complex, real-world workflows, such as LLM training, remains a significant challenge. In this paper, we introduce TREX, a multi-agent system that automates the entire LLM training life-cycle. By orchestrating collaboration between two core modules-the Researcher and the Executor-the system seamlessly performs requirement analysis, open-domain literature and data research, formulation of training strategies, preparation of data recipes, and model training and evaluation. The multi-round experimental process is modeled as a search tree, enabling the system to efficiently plan exploration paths, reuse historical results, and distill high-level insights from iterative trials. To evaluate the capability of automated LLM training, we construct FT-Bench, a benchmark comprising 10 tasks derived from real-world scenarios, ranging from optimizing fundamental model capabilities to enhancing performance on domain-specific tasks. Experimental results demonstrate that the TREX agent consistently optimizes model performance on target tasks. --- ### ID and Graph View Contrastive Learning with Multi-View Attention Fusion for Sequential Recommendation Authors: Xiaofan Zhou, Kyumin Lee Published: 2026-04-15 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.14114v1 Sequential recommendation has become increasingly prominent in both academia and industry, particularly in e-commerce. The primary goal is to extract user preferences from historical interaction sequences and predict items a user is likely to engage with next. Recent advances have leveraged contrastive learning and graph neural networks to learn more expressive representations from interaction histories -- graphs capture relational structure between nodes, while ID-based representations encode item-specific information. However, few studies have explored multi-view contrastive learning between ID and graph perspectives to jointly improve user and item representations, especially in settings where only interaction data is available without auxiliary information. To address this gap, we propose Multi-View Contrastive learning for sequential recommendation (MVCrec), a framework that integrates complementary signals from both sequential (ID-based) and graph-based views. MVCrec incorporates three contrastive objectives: within the sequential view, within the graph view, and across views. To effectively fuse the learned representations, we introduce a multi-view attention fusion module that combines global and local attention mechanisms to estimate the likelihood of a target user purchasing a target item. Comprehensive experiments on five real-world benchmark datasets demonstrate that MVCrec consistently outperforms 11 state-of-the-art baselines, achieving improvements of up to 14.44\% in NDCG@10 and 9.22\% in HitRatio@10 over the strongest baseline. Our code and datasets are available at https://github.com/sword-Lz/MMCrec. --- ### UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding Authors: Fei Tang, Bofan Chen, Zhengxi Lu, Tongbo Chen, Songqin Nong, Tao Jiang, Wenhao Xu, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen Published: 2026-04-15 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.14113v1 GUI grounding, which localizes interface elements from screenshots given natural language queries, remains challenging for small icons and dense layouts. Test-time zoom-in methods improve localization by cropping and re-running inference at higher resolution, but apply cropping uniformly across all instances with fixed crop sizes, ignoring whether the model is actually uncertain on each case. We propose \textbf{UI-Zoomer}, a training-free adaptive zoom-in framework that treats both the trigger and scale of zoom-in as a prediction uncertainty quantification problem. A confidence-aware gate fuses spatial consensus among stochastic candidates with token-level generation confidence to selectively trigger zoom-in only when localization is uncertain. When triggered, an uncertainty-driven crop sizing module decomposes prediction variance into inter-sample positional spread and intra-sample box extent, deriving a per-instance crop radius via the law of total variance. Extensive experiments on ScreenSpot-Pro, UI-Vision, and ScreenSpot-v2 demonstrate consistent improvements over strong baselines across multiple model architectures, achieving gains of up to +13.4\%, +10.3\%, and +4.2\% respectively, with no additional training required. --- ### Interpretable Stylistic Variation in Human and LLM Writing Across Genres, Models, and Decoding Strategies Authors: Swati Rallapalli, Shannon Gallagher, Ronald Yurko, Tyler Brooks, Chuck Loughin, Michele Sezgin, Violet Turri Published: 2026-04-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14111v1 Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such as large scale spam, phishing, or academic misuse. While much work has focused on detecting LLM-generated text, only limited work has gone into understanding the stylistic differences between human-written and machine-generated text. In this work, we perform a large scale analysis of stylistic variation across human-written text and outputs from 11 LLMs spanning 8 different genres and 4 decoding strategies using Douglas Biber's set of lexicogrammatical and functional features. Our findings reveal insights that can guide intentional LLM usage. First, key linguistic differentiators of LLM-generated text seem robust to generation conditions (e.g., prompt settings to nudge them to generate human-like text, or availability of human-written text to continue the style); second, genre exerts a stronger influence on stylistic features than the source itself; third, chat variants of the models generally appear to be clustered together in stylistic space, and finally, model has a larger effect on the style than decoding strategy, with some exceptions. These results highlight the relative importance of model and genre over prompting and decoding strategies in shaping the stylistic behavior of machine-generated text. --- ### Momentum Further Constrains Sharpness at the Edge of Stochastic Stability Authors: Arseniy Andreyev, Advikar Ananthkumar, Marc Walden, Tomaso Poggio, Pierfrancesco Beneventano Published: 2026-04-15 Categories: cs.LG, math.DS, math.OC, stat.ML arXiv: https://arxiv.org/abs/2604.14108v1 Recent work suggests that (stochastic) gradient descent self-organizes near an instability boundary, shaping both optimization and the solutions found. Momentum and mini-batch gradients are widely used in practical deep learning optimization, but it remains unclear whether they operate in a comparable regime of instability. We demonstrate that SGD with momentum exhibits an Edge of Stochastic Stability (EoSS)-like regime with batch-size-dependent behavior that cannot be explained by a single momentum-adjusted stability threshold. Batch Sharpness (the expected directional mini-batch curvature) stabilizes in two distinct regimes: at small batch sizes it converges to a lower plateau $2(1-β)/η$, reflecting amplification of stochastic fluctuations by momentum and favoring flatter regions than vanilla SGD; at large batch sizes it converges to a higher plateau $2(1+β)/η$, where momentum recovers its classical stabilizing effect and favors sharper regions consistent with full-batch dynamics. We further show that this aligns with linear stability thresholds and discuss the implications for hyperparameter tuning and coupling. --- ### From Weights to Activations: Is Steering the Next Frontier of Adaptation? Authors: Simon Ostermann, Daniil Gurgurov, Tanja Baeumel, Michael A. Hedderich, Sebastian Lapuschkin, Wojciech Samek, Vera Schmitt Published: 2026-04-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14090v1 Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficient adaptation, and prompting. In parallel, a growing body of work modifies internal activations at inference time to influence model behavior, an approach known as steering. Despite increasing use, steering is rarely analyzed within the same conceptual framework as established adaptation methods. In this work, we argue that steering should be regarded as a form of model adaptation. We introduce a set of functional criteria for adaptation methods and use them to compare steering approaches with classical alternatives. This analysis positions steering as a distinct adaptation paradigm based on targeted interventions in activation space, enabling local and reversible behavioral change without parameter updates. The resulting framing clarifies how steering relates to existing methods, motivating a unified taxonomy for model adaptation. --- ### UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception Authors: Ziming Wang Published: 2026-04-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.14089v1 We present UMI-3D, a multimodal extension of the Universal Manipulation Interface (UMI) for robust and scalable data collection in embodied manipulation. While UMI enables portable, wrist-mounted data acquisition, its reliance on monocular visual SLAM makes it vulnerable to occlusions, dynamic scenes, and tracking failures, limiting its applicability in real-world environments. UMI-3D addresses these limitations by introducing a lightweight and low-cost LiDAR sensor tightly integrated into the wrist-mounted interface, enabling LiDAR-centric SLAM with accurate metric-scale pose estimation under challenging conditions. We further develop a hardware-synchronized multimodal sensing pipeline and a unified spatiotemporal calibration framework that aligns visual observations with LiDAR point clouds, producing consistent 3D representations of demonstrations. Despite maintaining the original 2D visuomotor policy formulation, UMI-3D significantly improves the quality and reliability of collected data, which directly translates into enhanced policy performance. Extensive real-world experiments demonstrate that UMI-3D not only achieves high success rates on standard manipulation tasks, but also enables learning of tasks that are challenging or infeasible for the original vision-only UMI setup, including large deformable object manipulation and articulated object operation. The system supports an end-to-end pipeline for data acquisition, alignment, training, and deployment, while preserving the portability and accessibility of the original UMI. All hardware and software components are open-sourced to facilitate large-scale data collection and accelerate research in embodied intelligence: \href{https://umi-3d.github.io}{https://umi-3d.github.io}. --- ### TIP: Token Importance in On-Policy Distillation Authors: Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang, Alborz Geramifard Published: 2026-04-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14084v4 On-policy knowledge distillation (OPD) trains a student on its own rollouts under token-level supervision from a teacher. Not all token positions matter equally, but existing views of token importance are incomplete. We ask a direct question: which tokens carry the most useful learning signal in OPD? Our answer is that informative tokens come from two regions: positions with high student entropy, and positions with low student entropy plus high teacher--student divergence, where the student is overconfident and wrong. Empirically, student entropy is a strong first-order proxy: retaining $50\%$ of tokens with entropy-based sampling matches or exceeds all-token training while reducing peak memory by up to $47\%$. But entropy alone misses a second important region. When we isolate low-entropy, high-divergence tokens, training on fewer than $10\%$ of all tokens nearly matches full-token baselines, showing that overconfident tokens carry dense corrective signal despite being nearly invisible to entropy-only rules. We organize these findings with TIP (Token Importance in on-Policy distillation), a two-axis taxonomy over student entropy and teacher--student divergence, and give a theoretical explanation for why entropy is useful yet structurally incomplete. This view motivates type-aware token selection rules that combine uncertainty and disagreement. We validate this picture across three teacher--student pairs spanning Qwen3, Llama, and Qwen2.5 on MATH-500 and AIME 2024/2025, and on the DeepPlanning benchmark for long-horizon agentic planning, where Q3-only training on $<$$20\%$ of tokens surpasses full-token OPD. Our experiments are implemented by extending the OPD repository https://github.com/HJSang/OPSD_OnPolicyDistillation, which supports memory-efficient distillation of larger models under limited GPU budgets. --- ### Multistage Conditional Compositional Optimization Authors: Buse Şen, Yifan Hu, Daniel Kuhn Published: 2026-04-15 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.14075v1 We introduce Multistage Conditional Compositional Optimization (MCCO) as a new paradigm for decision-making under uncertainty that combines aspects of multistage stochastic programming and conditional stochastic optimization. MCCO minimizes a nest of conditional expectations and nonlinear cost functions. It has numerous applications and arises, for example, in optimal stopping, linear-quadratic regulator problems, distributionally robust contextual bandits, as well as in problems involving dynamic risk measures. The naïve nested sampling approach for MCCO suffers from the curse of dimensionality familiar from scenario tree-based multistage stochastic programming, that is, its scenario complexity grows exponentially with the number of nests. We develop new multilevel Monte Carlo techniques for MCCO whose scenario complexity grows only polynomially with the desired accuracy. ---