# Research Papers — 2026-05 · bundle page 161 of 326 > Full-text markdown of papers #8001–8050 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/161 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/160.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/162.md) ### The IsalProgram Programming Language Authors: Ezequiel López-Rubio Published: 2026-05-16 Categories: cs.PL, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.17008v1 We introduce IsalProgram (Instruction Set and Language for Programming), a novel assembly-like programming language with three distinctive theoretical properties: (1) it is a regular language in the sense of formal language theory, meaning its programs are accepted by a finite automaton; (2) every finite string over the instruction alphabet is a syntactically valid program; and (3) it makes no explicit use of memory addresses or variable names, absolute or relative. Programs are finite sequences of tokens drawn from a fixed instruction set, and are executed on a virtual machine whose sole data structure is a circular doubly linked list (CDLL) navigated by three data pointers, with control flow governed by two code pointers. We give a complete formal definition of the language and its virtual machine, prove its regularity, and demonstrate its expressive power. We further discuss IsalProgram's potential advantages as a target language for neural program synthesis, the amenability of its program space to metric-based exploration via the Levenshtein edit distance, and directions for analyzing computability and complexity within this framework. --- ### HalluScore: Large Language Model Hallucination Question Answering Benchmark Authors: Aisha Alansari, Hamzah Luqman Published: 2026-05-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.17007v1 Large language models (LLMs) have achieved remarkable progress in natural language generation, but remain susceptible to hallucination. In response to growing concerns about hallucinations, several benchmarks have been developed, primarily in English and Chinese. However, Arabic remains underrepresented, with limited benchmarks for LLMs hallucination due to scarce annotated resources and the language's morphological complexity. Consequently, existing benchmarks do not adequately reflect the linguistic, cultural, and reasoning characteristics of Arabic. To address this gap, we introduce HalluScore, a structured Arabic question answering benchmark designed to evaluate hallucination behavior in LLMs across different levels of reasoning difficulty, various knowledge domains, historical timelines, and culturally grounded Arabic scenarios. It contains 827 carefully curated questions for evaluating, detecting, and mitigating hallucination in LLMs. The dataset was constructed through a structured pipeline involving quality assurance, filtering for clarity and factual validity, and model-driven selection to retain questions that consistently trigger hallucinations. Each question is linked to verified ground-truth evidence, answer explanations, and multi-label annotations. Using the HalluScore benchmark, we conduct a comprehensive empirical analysis of hallucination patterns across 17 Arabic, multilingual, and reasoning LLMs. Moreover, we provide high-quality human annotations identifying hallucinated, non-hallucinated, and partially hallucinated responses of all evaluated LLMs. These results suggest that hallucination in Arabic LLMs extends beyond factual inaccuracies, encompassing challenges related to cultural understanding, linguistic reasoning, and logical consistency. We release HalluScore to support future research on improving the reliability and cultural competence of LLMs in Arabic. --- ### Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training Authors: Peng Cui, Boyao Yang, Jun Zhu Published: 2026-05-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.17003v2 Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets nearly uniformly across prompts, squandering compute on samples that are already mastered or remain far beyond the model's current capability. To address this fundamental inefficiency, we propose Learning-Zone Energy (LZE), a theoretically grounded, fully online data selection framework that concentrates computation on the model's active learning frontier. At its core, we define a closed-form Learning-Zone Energy Score that fuses three complementary signals, an initial-difficulty anchor, a normalized outcome-uncertainty term, and a pass-rate momentum, into a single scalar that is provably aligned with the expected magnitude of group-relative policy gradient updates. A forward pruner with replay further reduces wall-clock time cost by skipping rollout generation for persistently solved prompts while periodically checking for forgetting. Evaluated on Qwen-family models (1.5B-8B) across GSM8K, MATH and DAPO-MATH, our method retains only 40% of the training data per step yet matches or surpasses full-data baselines, with especially pronounced out-of-distribution gains on AIME25 (+45.9%) and AMC23 (+18.2%), alongside an estimated 36% reduction in training FLOPs. Our code is available at https://github.com/Stellaris167/LZE. --- ### BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks Authors: Ruth Wan Theng Chew, Zhiliang Chen, Apivich Hemachandra, Bryan Kian Hsiang Low Published: 2026-05-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.17000v1 Optimization of LLM training and inference configurations, such as hyperparameters, data mixtures, and prompts, is critical to performance, but it is often approached heuristically in practice, leading to potentially suboptimal outcomes. By framing them as noisy, expensive, and derivative-free optimization problems, Bayesian optimization (BO) and other black-box optimization (BBO) methods offer a promising yet underexplored direction for principled, sample-efficient methods. However, LLM training and inference costs are prohibitively high for most of the BBO research community, and new methods are often only evaluated on synthetic test functions and small-scale datasets that fail to capture the challenges of modern LLM optimization problems. This impedes the development of BBO methods and makes it difficult to assess their effectiveness on modern LLM tasks. We introduce BoLT, the first LLM-centric benchmark that democratizes LLM research for the BBO community. BoLT is released at https://github.com/chewwt/bolt. BoLT covers broad and well-motivated LLM optimization problems, involving multi-fidelity, multi-objective, heteroscedastic noise, and high-dimensional search spaces. Each problem in BoLT is grounded in real experimental data and made fully reproducible and accessible through lightweight surrogate models fitted to the results of thousands of real LLM experiments. We benchmark BoLT against an extensive range of BO and BBO methods, showing that selected BO methods consistently outperform others across tasks and highlighting gaps in existing BBO methods on LLM tasks, underscoring the need to modernize benchmarks for the BBO community. --- ### Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning Authors: Peng Cui, Boyao Yang, Jun Zhu Published: 2026-05-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16999v1 Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident errors more than uncertain ones and no signal that ties confidence to the quality of visual evidence, a gap that becomes especially severe under corrupted or ambiguous inputs where models continue to report high confidence on incorrect answers. We introduce Ranking-Aware Calibration (RAC), a training-time framework that supervises confidence using two comparison signals that group-based RL already produces at no additional labeling cost. The ranking-aware group loss enforces that a better rollout receives higher confidence than a worse one within the same prompt. The clean--corrupted pairwise loss enforces that confidence attenuates as visual evidence degrades. Because the ranking signal forces the policy to distinguish between correct and incorrect reasoning paths, it also reinforces task accuracy beyond what correctness rewards alone produce. Both losses require no external confidence annotations and integrate naturally with group-based RL post-training. We instantiate RAC on Qwen2.5-VL and InternVL-3.5 backbones and evaluate on six multimodal reasoning benchmarks under clean and corrupted inputs. Empirical results show that the ranking-aware loss substantially improves task accuracy by teaching the policy to discriminate between better and worse reasoning, while the pairwise corruption loss reduces calibration error under degraded inputs. Their combination achieves the best calibration across all tested backbones while improving accuracy in the majority of settings. --- ### $\mathcal{O}(n)$ alternative to Quantum Fourier Transform with efficient neural net classical post-processing Authors: Kaiming Bian, Zujin Wen, Oscar Dahlsten Published: 2026-05-16 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2605.16998v2 The Quantum Fourier Transform (QFT) is employed by hidden subgroup problem (HSP) algorithms, including Shor's algorithm for factoring. The circuit depth of the QFT remains challenging for near-term hardware. To find shallower alternatives we identify two properties that are exploited by the QFT to enable HSP. Firstly, the shift invariance of the QFT allows for the removal of a random overall shift. Secondly, the QFT retains information about the hidden subgroup generator accessible in the measurement outcomes. We quantify that information via the discrete Fisher information. We construct a family of shallow circuits using Hadamards and controlled-Phase gates, HP-$L$ circuits, that we prove preserve shift invariance. Numerical analysis shows these circuits retain exponentially growing Fisher information. The $\mathcal{O}(n)$ HP-$1$ is employed in place of the $\mathcal{O}(n^2)$ QFT in our numerical implementation of Shor's algorithm. An efficient neural network is used for the corresponding classical post-processing. --- ### $\mathcal{O}(n)$ alternative to Quantum Fourier Transform with efficient neural net classical post-processing Authors: Kaiming Bian, Zujin Wen, Oscar Dahlsten Published: 2026-05-16 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2605.16998v1 The Quantum Fourier Transform (QFT) is required by hidden subgroup problem (HSP) algorithms, including Shor's algorithm for factoring. The circuit depth of the QFT remains challenging for near-term hardware. To find shallower alternatives we identify two properties that are exploited by the QFT to enable HSP. Firstly, the shift invariance of the QFT allows for the removal of a random overall shift. Secondly, the QFT retains information about the hidden subgroup generator accessible in the measurement outcomes. We quantify that information via the discrete Fisher information. We construct a family of shallow circuits using Hadamards and controlled-Phase gates, HP-$L$ circuits, that we prove preserve shift invariance. Numerical analysis shows these circuits retain exponentially growing Fisher information. The $\mathcal{O}(n)$ HP-$1$ can replace the $\mathcal{O}(n^2)$ QFT in Shor's algorithm, as demonstrated numerically, with an efficient neural network implementing classical post-processing. --- ### Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost? Authors: Prateek Rajput, Yewei Song, Iyiola E. Olatunji, Jacques Klein, Tegawendé F. Bissyandé Published: 2026-05-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.16996v1 Can large language models reliably express a human-like personality, or are they merely mimicking surface cues without a stable underlying profile? To investigate this, we induce personality in LLMs by fine-tuning them on the long-form essays, where each essay is associated with a target Big Five personality profile. We then evaluate the stability and fidelity of the induced personality using the IPIP-NEO questionnaire. Specifically, we ask: (i) does post-training (SFT, DPO, ORPO) stabilize questionnaire scores under prompt rephrasings, and (ii) can it induce target Big Five profiles from unguided essays? Our results demonstrate that fine-tuning consistently reduces variance in questionnaire responses across five models, directly mitigating the evaluation fragility reported in pre-trained models. However, this newfound stability reveals a more fundamental limitation: accuracy on the full five-dimensional profile remains near chance, even when single-trait scores improve. This indicates that unguided essays lack the cues needed for faithful personality expression. We therefore argue for scenario-grounded datasets or interactive elicitation that accumulates test-aligned evidence over time. --- ### Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings Authors: Anthonio Oladimeji Gabriel, Ahmad Rufai Yusuf Published: 2026-05-16 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.16993v1 Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, standardised, English-language inputs, conditions that do not reflect the realities of healthcare delivery in low-resource settings. This study presents the first systematic dual audit of two orthogonal safety vulnerabilities in clinical AI: adversarial image fragility and cross-lingual diagnostic drift. Using DenseNet121, the architecture underlying CheXNet, fine-tuned on the COVID-QU-Ex chest X-ray dataset (85,318 images; COVID-19, Non-COVID Pneumonia, Normal), we demonstrate that diagnostic accuracy collapses from 89.3% to 62.0% under a Fast Gradient Method (FGM) perturbation of epsilon=0.021, a magnitude imperceptible to the human eye. Standard defensive strategies including Gaussian smoothing and ensemble voting failed to restore clinical safety. In a parallel language fragility experiment, we tested Llama3.1:8b and NatLAS (N-ATLAS) on 20 COVID-19 clinical cases presented in Standard English, Nigerian Pidgin (Naija), and Yoruba-inflected English. Both models exhibited significant accuracy degradation: Llama3.1:8b dropped from 80.0% to 65.0% on Pidgin; NatLAS, an African-context model, collapsed from 85.0% to 55.0%, with diagnosis consistency falling to 50%. These findings establish a quantitative failure envelope for clinical AI under conditions representative of Primary Health Centre (PHC) deployment in Nigeria, and motivate urgent calls for adversarially hardened, linguistically inclusive clinical AI architectures. --- ### Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning Authors: Jan Netík, Patrícia Martinková Published: 2026-05-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.16991v2 Item difficulty must often be estimated before test administration, when no responses are yet available for calibration. While most response-free difficulty modelling approaches derive item-text features by hand for a separate statistical model, we fine-tune a transformer end-to-end on the wording, avoiding the theory-based feature design and the preprocessing that discards information. We address reading-comprehension multiple-choice items, whose difficulty depends on inferential demands spanning passage, question, and options, yet the simplest model sees one undifferentiated sequence and is trained on difficulty alone. We introduce and investigate two extensions to the joint-encoding baseline: a component-wise variant, which encodes the wording parts separately, and a multi-task variant, which adds an auxiliary task of question answering. We compare the methods across three training-set sizes sampled from a corpus of nearly 30,000 items whose labels approximate response-based Rasch difficulty. At the smallest training size, both extensions improve on the baseline, the multi-task variant across every metric, and component-wise encoding in rank ordering. Further research may ground the auxiliary supervision in observed responses and extend the approach to other item types. --- ### Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning Authors: Jan Netík, Patrícia Martinková Published: 2026-05-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.16991v1 Response-free item difficulty modelling promises to reduce reliance on response-based calibration but is intrinsically difficult on reading-comprehension multiple-choice items, where difficulty depends on inferential demands across wording components. Whereas most existing approaches extract item-text features and pass them to a separate statistical or machine-learning model, we fine-tune transformer encoders end-to-end on the item wording, eliminating the manual feature engineering and preprocessing that discards information. Moreover, two extensions to this joint-encoding approach are proposed: a component-wise variant that encodes wording components separately through a shared encoder, and a multi-task variant that retains joint encoding and adds an auxiliary multiple-choice question answering objective on the shared encoder. Each method is evaluated under a Monte Carlo subsampling design at three training-set sizes on a held-out test set. We find that joint encoding is a viable end-to-end alternative to feature-engineering pipelines; while the component-wise variant shows no detectable benefit, consistent with self-attention already harvesting the cross-component signal, the multi-task variant delivers significant paired improvements in the smallest-sample regime. Transformer fine-tuning, especially if regularised by a suitable auxiliary task, recovers a substantial share of the wording-derivable signal at training-set sizes typical of applied measurement. The framework provides a customisable interface for psychometrically motivated extensions. --- ### DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing Authors: Jinxin Ai, Matthias Nießner, Ziya Erkoç Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16990v1 While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a significant challenge due to the complexities of multi-view consistency and spatial control. Inspired by these 2D advancements, we present a novel personalization method for text-guided 3D editing that enables compositional, object-level control through natural language. Given a 3D input, we render orthogonal views and extract object-level segmentation masks to isolate semantic components. We then learn distinct token embeddings for each component through a tailored two-phase optimization strategy: multi-view textual inversion with attention alignment, followed by full fine-tuning of multi-view diffusion model. During inference, these disentangled tokens seamlessly compose with editing prompts to generate multi-view consistent images, which are subsequently lifted into high-fidelity textured 3D meshes. Extensive evaluations across diverse editing scenarios demonstrate that our method successfully transfers the flexibility of 2D personalization to 3D, achieving state-of-the-art edit faithfulness and identity preservation compared to existing baselines. --- ### Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection Authors: Tomàs Garriga, Alejandro Almodóvar, Axel Brando, Gerard Sanz, Eduard Serrahima de Cambra, Juan Parras Published: 2026-05-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16989v1 Individualized treatment selection with continuous actions requires accurate causal response estimation in decision-relevant regions, rather than uniformly over the entire action space. Estimating a global causal response surface and then choosing the treatment that maximizes it can therefore be suboptimal, since standard estimation objectives allocate modeling effort according to the observed treatment distribution rather than the regions that determine the optimal decision. While decision-aware approaches have been studied in unconfounded settings, this problem remains underexplored in proximal causal inference, where proxy variables and bridge functions enable identification under suitable assumptions even in the presence of hidden confounding. Despite recent progress, proximal methods have primarily focused on treatment-effect and potential-outcome estimation rather than treatment selection and optimal decision-making. To bridge this gap, we introduce a policy-targeted weighted bridge loss that emphasizes decision-relevant treatment regions while retaining global stabilization. We prove a regret bound showing that the proposed weighted bridge loss controls treatment-selection regret through a weighted ill-posedness constant. We instantiate the framework in decision-aware variants of several proximal bridge solvers, yielding practical algorithms that alternate between weighted bridge estimation, response-surface projection, policy update, and weight refinement. Empirically, we find that decision-aware weighting reduces regret across several bridge solvers, suggesting improved treatment selection in proximal settings. --- ### Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents Authors: Jingxing Wang, Chenyu Zhou, Zhihui Fu, Jun Wang, Weiwen Liu, Weinan Zhang, Jianghao Lin Published: 2026-05-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.16986v2 Additional test-time compute can give LLM agents access to more past experience, yet expanding the context or adding rollouts does not necessarily yield greater agent capability. We call this challenge test-time compute-to-capability conversion and propose SkillTTA, which retrieves task-relevant training trajectories and synthesizes a temporary skill conditioned on the visible target context for a solver with fixed parameters. To pursue a higher performance ceiling, SkillTTA further uses meta prompt optimization (MPO) to adapt the policy that writes these skills. MPO evaluates candidate prompts on paired tasks and emphasizes informative transitions. It also confines updates to benchmark-specific atomic slots, reducing the variance caused by observing each edit only indirectly through skill synthesis and solver rollout. Across ALFWorld, SpreadsheetBench, BigCodeBench, and WebShop, SkillTTA outperforms state-of-the-art reuse and optimization baselines. It attains a higher performance ceiling at lower compute cost than baseline reuse and sampling strategies. --- ### Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution Authors: Antoine Bourgois, Olga Seminck, Thierry Poibeau Published: 2026-05-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.16984v2 We present our submission to the LLM track of the 2026 Computational Models of Reference, Anaphora and Coreference (CRAC 2026) shared task. With an average CoNLL F1 score of 74.32 on the official test set, our system ranked first in the LLM track, and third overall. Our system is based on the Gemma-3-27b model, fine-tuned using a two-stage strategy with a multilingual base adapter followed by dataset-specific adapters. We represent mention spans by their headword using an XML-inspired format with local reindexing and annotate documents iteratively. These design choices proved effective across languages, document lengths, and annotation guidelines. --- ### Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction Authors: Kejun Ren, Lei Jin, Tianxin Huang, Lianming Xu, Li Wang Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16981v2 Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TTT3R-style per-token gates across five benchmarks and discover a structural bottleneck: the gate is intrinsically bounded in magnitude (median $0.31$; never exceeding $0.6$) and nearly frame-invariant, yielding an effective memory horizon of only $\sim$3 frames per state token, which serves as the structural origin of long-sequence drift. We trace this to a missing axis: existing inference-time methods modulate updates only at the per-token, intra-frame level, while the orthogonal frame-level question of \emph{how strongly each frame should contribute to the state} has been treated as content-independent. We close this gap with a scalar frame-level gate $α_t \in (0, 1)$ derived in closed form from frame-to-frame changes of internal features---a graded write weight, inspired by classical Simultaneous Localization and Mapping (SLAM) keyframe selection, that never discards a frame and requires no parameters, no training, and no extra forward pass. Across six benchmarks spanning camera pose, video depth, and 3D reconstruction at sequence lengths up to $4,661$ frames, our gate cuts ATE by $51\%$ on long TUM-RGBD pose sequences, reduces AbsRel by $13.0\%$ on Bonn video depth, and on KITTI long-sequence pose estimation surpasses both LongStream and Keyframe-VO in average ATE, while retaining strictly constant memory at zero training cost. --- ### Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction Authors: Kejun Ren, Lei Jin, Tianxin Huang, Lianming Xu, Li Wang Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16981v1 Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TTT3R-style per-token gates across five benchmarks and discover a structural bottleneck: the gate is intrinsically bounded in magnitude (median $0.31$; never exceeding $0.6$) and nearly frame-invariant, yielding an effective memory horizon of only $\sim$3 frames per state token, which serves as the structural origin of long-sequence drift. We trace this to a missing axis: existing inference-time methods modulate updates only at the per-token, intra-frame level, while the orthogonal frame-level question of \emph{how strongly each frame should contribute to the state} has been treated as content-independent. We close this gap with a scalar frame-level gate $α_t \in (0, 1)$ derived in closed form from frame-to-frame changes of internal features -- a continuous relaxation of classical Simultaneous Localization and Mapping (SLAM) keyframe selection that requires no parameters, no training, and no extra forward pass. Across six benchmarks spanning camera pose, video depth, and 3D reconstruction at sequence lengths up to $4,541$ frames, our gate cuts ATE by $51\%$ on long TUM-RGBD pose sequences, reduces AbsRel by $12.8\%$ on Bonn video depth, and on KITTI long-sequence pose estimation surpasses both LongStream and Keyframe-VO, while retaining strictly constant memory at zero training cost. --- ### Statistical Hand Shape Modeling from Clinical CT Scans Using Deep Learning and Implicit Skinning Authors: Gokce Guven, Hasan Fehmi Ates, Deniz Karasahin, Kaan Erdogan Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16980v1 Accurate segmentation and statistical shape modeling of hand anatomy have significant implications for medical diagnostics, ergonomics, and biomechanics. This study proposes an AI-assisted reconstruction pipeline for segmenting and analyzing hand anatomy from 1,271 elbow-to-hand (e2h-CT) computed tomography scans. A Pix2Pix-based conditional generative adversarial network is first employed to remove plaster cast and background artifacts from CT volumes. The cleaned scans are then processed in 3D Slicer to extract skin and bone masks, which are converted into closed-surface mesh models. Segmented bone meshes are used to construct skeletal representations, enabling implicit skinning to align all hand models into a standardized anatomical configuration. Subsequently, non-rigid registration is performed on the hand skin surfaces using the Geodesic Based Coherent Point Drift++ (GBCPD++) algorithm to establish point-wise correspondence across subjects. Principal Component Analysis (PCA) is then applied to the registered models to quantify anatomical shape variability. The Pix2Pix preprocessing stage achieved a Dice coefficient of 0.9856 and an IoU of 0.9720 on the held-out test set. Statistical modeling was performed on a subset of 90 scans in which the fingers were fully visible and anatomically separated. The resulting statistical shape distributions demonstrate strong agreement with the U.S. Army Anthropometric Survey (ANSUR II), supporting the anatomical validity of the reconstructed models. The proposed methodology demonstrates significant potential for advancing biomechanical modeling, ergonomic optimization, prosthetic design, and precision medical diagnostics. --- ### Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons Authors: Wei Tang, Jinpei Han, Kangning Cui, Mattia Carletti, Fredrik K. Gustafsson, Shreyank N Gowda, Patitapaban Palo, Anshul Thakur, Lei Clifton, Jean-michel Morel, Raymond H. Chan, David A. Clifton et al. Published: 2026-05-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16975v1 Electrocardiogram (ECG) foundation models pretrained on typical diagnostic 10-second ECG segments, have demonstrated strong transferability across a range of clinical applications. However, many real-world applications produce recordings that are typically longer, and are varied in duration during inference time. These 10-second models have no built-in way to combine information across time. Extending them to longer horizons introduces two challenges: structural incompatibilities arising from input-length disparities, and semantic challenges that limit meaningful temporal aggregation. We propose a parameter-efficient framework that extends pretrained ECG foundation models to longer and variable-length ECGs without retraining the backbone. Guided by a frozen pretrained 10-second model, we introduce a lightweight plug-in module that extends the model in two complementary ways: (i) structurally compatible long-sequence processing and (ii) semantically informed temporal modeling. Experiments on multiple long-horizon ECG tasks, datasets, and foundation model backbones demonstrate that our method enables robust long-horizon extension from pretrained snapshot models, consistently outperforming sliding-window and pooling-based baselines with strong parameter efficiency. --- ### SHED: Style-Homogenized Embedding Alignment for Domain Generalization Authors: Kai Gan, Tong Wei Published: 2026-05-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.16973v1 Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong generalization, their direct image-text embedding alignment suffers from inherent information asymmetry: images encode both class semantics and domain-specific styles, whereas text prompts primarily convey basic class cues. This asymmetry hinders generalization to novel domains in realistic scenarios. To address this, we propose Style-Homogenized Embedding alignment for Domain-generalization (SHED), a novel CLIP-based method that aligns style-homogenized embeddings instead of raw representations from encoders in CLIP. During training, SHED removes domain-specific style centroids from both image embeddings computed per source domains and text embeddings which are averaged across diverse prompt templates and stripped of a global centroid. For inference, considering the lack of target domain information, SHED projects diverse textual domain centroids into the visual space and aggregates predictions via membership weighting. Extensive experiments on five benchmarks show SHED achieves state-of-the-art performance, outperforming prior methods significantly (e.g., +4.0\% on DomainNet vs. standard fine-tuning). --- ### WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI Authors: Jingjing Li, Zhi Liu, Xiyao Jin, Tatsuki Fushimi, Yoichi Ochiai Published: 2026-05-16 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.16972v2 Cultural heritage exhibitions often struggle to sustain attention and support reflective engagement. Physical exhibitions rely on fixed interpretive aids that lack adaptability to individual backgrounds or curiosity, and their effectiveness depends heavily on a visitor's Personal Context, prior knowledge, and cultural literacy. Meanwhile, digital exhibitions prioritize convenience and accessibility but risk weakening the Physical and Social Contexts that define embodied cultural experience. WhiteTesseract addresses this gap by enabling in-situ interpretation through high-resolution XR and conversational AI. The system integrates spatial intelligence via artwork recognition to allow visitors to selectively reduce environmental distractions (via diminished reality) and engage in context-aware dialogue (via large language models). The goal is to preserve the richness of the physical and social environment while providing a flexible space for personal reflection, enhancing Personal Context without compromising physical authenticity. We deployed the system in a Claude Monet exhibition and conducted a controlled user study with 26 participants. Quantitative results showed that WhiteTesseract modulation significantly increased average viewing duration from 35.3 to 98.3 seconds (p < 0.001). Analysis of 529 visitor-AI interactions revealed that 60% extended beyond factual queries to include analytical, emotional, and comparative inquiries. These findings demonstrate how XR and AI can enrich the physical exhibition experience by supporting deeper, more personalized engagement without displacing the embodied value of cultural heritage. We discuss technical and social constraints for real-world deployment and limitations of our controlled setting. --- ### Brain Vascular Age Prediction Using Cerebral Blood Flow Velocity and Machine Learning Algorithms Authors: Anni Zhao, Alex Bateh, Tyler Baldridge, Sandra Billinger, Xiao Hu Published: 2026-05-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.16969v2 Defining vascular age in terms of physiological function has become one focal point of the extensive studies to categorize and track chronological age. Transcranial Doppler (TCD) is a method by which cerebral blood flow velocity is measured along the major arteries feeding the human brain. This study aims to use features extracted from TCD to estimate chronological age and assess accelerated aging in subjects with various brain diseases. We predict subjects with various brain diseases to present with accelerated cerebrovascular aging when tested on various regression models trained by healthy subjects. 168 healthy subjects and 277 diseased subjects with bilateral TCD recordings of the middle cerebral artery were analyzed using the Morphological Analysis and Clustering of Intracranial Pressure (MOCAIP) algorithm. MOCAIP-generated features and heart rate variability features were used as input features for regression models to predict the brain vascular age. 66 subjects with acute stroke, 27 subjects with post stroke, 26 subjects with Alzheimer's disease, 23 subjects with mild cognitive impairment, and 135 established subjects were tested against the machine learning model to assess for accelerated cerebrovascular age. The trained model, on average, predicted healthy subjects' cerebrovascular age to be 3.69 years above their chronological age. Subjects with different disease conditions exhibited varying levels of age acceleration. The differences in healthy and diseased subjects' performances suggest that features generated using TCD may be relevant when evaluating accelerated cerebrovascular aging. Moreover, imbalanced datasets have been observed to affect the performance of machine-learning-based brain age prediction models. --- ### Expandable, Compressible, Mineable: Open-World Thermal Image Restoration Authors: Pu Li, Huafeng Li, Yafei Zhang, Wen Wang, Neng Dong, Jie Wen Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16967v1 In open-world settings, thermal infrared (TIR) image degradations continuously emerge and evolve, while most existing all-in-one restoration methods are built on a closed-set assumption and struggle to continually adapt to novel degradations. To address this, we propose ECMRNet, an Expandable, Compressible, and Mineable Restoration Network for open-world TIR restoration from a continual learning perspective. Conceptually, ECMRNet unifies continual degradation learning as an "expand-compress-mine" closed-loop process, enabling sustained adaptation to new degradations with controllable evolution. Structurally, ECMRNet decomposes intermediate representations into group-isolated subspaces, and achieves strict parameter isolation and fast adaptation to new degradations by freezing historical groups and isomorphically expanding new ones. To curb model growth as tasks accumulate, we present Structural Entropy Pruning, which identifies and removes redundant channel groups via two-dimensional structural entropy minimization, achieving information contribution-driven adaptive compression. Moreover, we design a Sub-degradation Knowledge Mining Module that dynamically retrieves and recombines transferable components from historical representations to improve restoration under compound degradations. Experimental results demonstrate that ECMRNet achieves superior overall performance across diverse single and compound degradations while using fewer parameters and lower computational cost. The source code is available at https://github.com/Kust-lp/ECMRNet. --- ### Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects Authors: Zhentao Tan, Yuze Hao, Boyi Zou, Mingsheng Long, Yi Yang, Gang Bao Published: 2026-05-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.16966v1 Solving inverse partial differential equation (PDE) problems is a fundamental topic in scientific research due to its broad significance across a wide range of real-world applications. Inverse PDE problems arise across medical imaging, geophysics, materials science, and aerodynamics, where the goal is to infer hidden causes, design structures, or control physical states. In this paper, we provide a comprehensive review of recent advances in solving inverse PDE problems using artificial intelligence (AI). We first introduce the basic formulation, key challenges, and traditional numerical foundations of inverse PDE problems, and then organize it into three major categories: inverse problems, inverse design, and control problems. For each category, we further present a methodological paradigms, and review representative state-of-the-art approaches from recent years. We then summarize representative applications across scientific and industrial domains, including mechanical systems, aerodynamic problems, thermal systems, full-waveform inversion, system identification, and medical imaging. Finally, we discuss open challenges and future prospects, such as physics-informed architectures, limited real-world data, uncertainty quantification, and inverse foundation models. This survey aims to provide the first unified and systematic perspective on AI for inverse PDE problems, demonstrating how modern learning-based methods are reshaping inverse problems, inverse design, and control problems in PDE-governed systems. --- ### OmniVL-Guard Pro: A Tool-Augmented Agent for Omnibus Vision-Language Forensics Authors: Jinjie Shen, Zheng Huang, Yuchen Zhang, Yujiao Wu, Yaxiong Wang, Lechao Cheng, Shengeng Tang, Tianrui Hui, Nan Pu, Zhun Zhong Published: 2026-05-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16962v2 Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the model alone. However, self-contained MLLMs are constrained by finite parametric knowledge, static training corpora, and limited perceptual resolution, creating a practical ceiling in dynamic open-world forensics -- particularly for real-time event verification requiring external clues and forgery segmentation demanding fine-grained scrutiny of local manipulations. To address these limitations, we shift from scaling up the self-contained model toward reaching beyond it. We propose \textbf{OmniVL-Guard Pro}, a tool-augmented agent that extends unified forensics from closed-world prediction to open-world clues-driven reasoning. OmniVL-Guard Pro integrates a tool environment spanning real-time event search, local cropping and zooming, edge-anomaly screening, face detection, video frame extraction, and SAM3-based segmentation. To generate high-quality tool-reasoning trajectories, we introduce \textbf{Tree-Structured Self-Evolving Tool Trajectory Generation}, which produces diverse trajectories through seed guidance, guider-free self-evolution, and weakly-hinted hard sample synthesis, yielding the Full-Spectrum Tool Reasoning (FSTR) dataset for training. We further propose \textbf{Checker-Guided Agentic Reinforcement Learning} (CGARL), which provides process-level supervision to penalize cases where the answer is correct but the reasoning is distorted. Extensive experiments demonstrate that OmniVL-Guard Pro achieves state-of-the-art performance across various tasks, and exhibits strong zero-shot generalization. The FSTR dataset and code for OmniVL-Guard Pro will be publicly released at https://github.com/shen8424/OmniVL-Guard-Pro. --- ### Latent Action Control for Reasoning-Guided Unified Image Generation Authors: Fuxiang Zhai, Sixiang Chen, Yingjin Li, Shuaibo Li, Jianyu Lai, Tengjun Huang, Lei Zhu Published: 2026-05-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16961v1 Unified multimodal models can encode visual understanding and image generation within a shared backbone, yet understanding does not automatically translate into control: models may infer objects, relations, or knowledge cues but fail to instantiate them in the generated image. We propose Latent Action Control (LAC), which makes reasoning actionable by representing it as hidden continuous actions inside a unified generator. Given a prompt, LAC rolls out a role-structured latent trajectory for planning, internal visual drafting, diagnosis, and refinement, and injects these actions into the hidden stream that conditions flow-based generation, without producing reasoning tokens or intermediate images. Since such action trajectories are unobserved, LAC learns them through prior-guided variational latent action alignment from training-only rendered semantic priors, draft image features, and supervised halting signals, followed by Latent-Flow GRPO to align the latent-to-image rollout with terminal visual feedback. This provides a control path from inferred relations, bindings, and knowledge cues to the generation process. Instantiated on BAGEL-7B-MoT, LAC consistently improves compositional and knowledge-grounded generation across GenEval, WISE, and T2I-CompBench, with the largest gains on spatial relations, attribute binding, and world-knowledge-sensitive prompts. Ablations and latent interventions show that the learned action trajectory is consumed by the generator, suggesting that unified generation benefits when understanding is not only encoded, but made actionable during generation. --- ### How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study Authors: Shuqi Zhu, Yi Zhong, Ziyi Ye, Bangde Du, Yujia Zhou, Qingyao Ai, Yiqun Liu Published: 2026-05-16 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.16953v2 While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remain unclear. To address this problem, this paper explores humans' neural dynamics to characterize how the brain processes hallucinated content. We record EEG signals from 27 participants while they are performing a verification task to judge the correctness of image descriptions generated by a multi-modal large language model (MLLM). Based on an averaged event-related potential (ERP) study, we reveal that multiple cognitive processes, e.g., semantic integration, inferential processing, memory retrieval, and cognitive load, exhibit distinct patterns when humans process hallucinated versus non-hallucinated content. Notably, neural responses to hallucinations that were misjudged versus correctly judged by human participants showed significant differences. This indicates that misjudged AI-generated hallucinations failed to trigger the standard neurocognitive fact verification pathway. --- ### Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing Authors: Shaodong Xu, Zexian Li, Zhendong Wang, Litong Gong, Tiezheng Ge, Wengang Zhou, Bo Zheng, Houqiang Li Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16951v1 A fundamental challenge in image editing lies in preserving spatial locality: edits should improve targeted content without inadvertently altering surrounding regions. However, most optimization-based editing approaches treat images as holistic entities, causing global policy updates that undermine locality and introduce undesired context changes. We observe that this issue stems from a mismatch between localized editing intent and globally applied optimization signals. Motivated by this insight, we propose Edit-GRPO, preserving Locality while optimizing image editing, a locality-preserving policy optimization framework that explicitly decouples editing and preservation objectives. By assigning region-specific optimization signals to edit and non-edit areas, Edit-GRPO aligns policy updates with the spatial structure of editing tasks, enabling localized improvements while maintaining global visual coherence. This design effectively suppresses common artifacts such as context distortion and boundary inconsistency. Extensive experiments across diverse image editing scenarios demonstrate that Edit-GRPO significantly improves locality preservation while maintaining strong editing performance compared to existing optimization-based methods, validating the generality and effectiveness of the proposed framework. --- ### Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers Authors: Shaodong Xu, Zhendong Wang, Litong Gong, Zexian Li, Wengang Zhou, Tiezheng Ge, Houqiang Li Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16949v1 Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Representation Alignment (REPA)-can substantially accelerate training and improve generation fidelity. Subsequent analysis(e.g., iREPA) suggests that these gains arise primarily from transferring spatial structure contained in pre-trained vision representations. However, mostly existing alignment methods employ point-wise matching objectives or rely on implicit architectural tweaks, which fail to explicitly model the spatial relational geometry inherent in vision foundation models. We argue that such element-wise supervision is insufficient to capture the rich spatial topology of visual representations, and that effective alignment for generation should instead be formulated as an explicit structural constraint. To this end, we propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps, rather than merely matching individual feature points. By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence, along with improved sample quality, compared to state-of-the-art alignment strategies. Our code and models will be released. --- ### Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers Authors: Fanqin Zeng, Feng Hong, Geng Yu, Huangjie Zheng, Xiaofeng Cao, Ya Zhang, Bo Han, Yanfeng Wang, Jiangchao Yao Published: 2026-05-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.16941v1 Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We attribute this dilemma to a train-inference mismatch amplified by irreversible decoding. While training reconstructs tokens from randomly corrupted states, efficient inference requires an adaptive denoising order, where easier tokens are revealed earlier and context-dependent ones are deferred. This view motivates two complementary methods: an inference-time method that makes parallel decoding revokable, and a training-time extension that distills the reliable order exposed by this revokable process. Accordingly, we first propose Wide-In, Narrow-Out (WINO), a training-free decoding algorithm that enables revokable parallel generation. WINO aggressively drafts multiple tokens, verifies generated tokens with enriched global context, and re-masks unreliable ones for later refinement. Building on this discovered order, we further introduce WINO+, which injects the verified denoising trajectories produced by WINO into model parameters, aligning training with efficient inference. Experiments on LLaDA and MMaDA show that WINO improves both quality and efficiency, while WINO+ further strengthens this progression. On GSM8K, WINO improves accuracy from 73.24% to 75.82% with a 6.10x step reduction, and WINO+ further achieves 76.58% with a 6.83x reduction. On Flickr30K, WINO+ reaches a 16.22x step reduction with improved CIDEr. These results demonstrate that DLLMs can serve as their own efficiency teachers by first discovering reliable denoising orders through revokable decoding and then learning to follow them for faster generation. Code is available at https://github.com/Feng-Hong/WINO-DLLM/tree/WINO-plus. --- ### Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models Authors: Yueqing Hu, Tianhong Wang Published: 2026-05-16 Categories: cs.CL, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2605.16938v1 Large Reasoning Models (LRMs) generate chain-of-thought traces whose length tracks human reaction times across cognitive tasks, but recent debate questions whether this alignment reflects genuine computational structure or surface verbosity. We test whether the alignment varies with inference-time reasoning effort. Across GPT-OSS-20B and GPT-OSS-120B, three effort levels, and six reasoning tasks, within-task and cross-task alignment remain invariant: Bayes Factors lean toward the null, and mean alignment is numerically near-identical across conditions. A manipulation check reveals that the effort parameter sets an upper budget on generation rather than driving real-time allocation, suggesting that the allocation policy is crystallized at training time. Arithmetic complexity contrasts further show that token allocation tracks fine-grained, format-dependent human difficulty patterns, with model scale improving the match. Cognitive cost alignment between LRMs and humans appears to be a training-time achievement, robust to inference-time perturbations, supporting a compiled rather than online account of LRM problem-solving. --- ### DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis Authors: Yi Zuo, Huimin Wu, Lingling Li, Fang Liu, Licheng Jiao, Qing Li Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16937v1 Trajectory-controlled video generation has become essential for controllable video generation. While current methods perform well under small-view camera motions, they degrade significantly with large-view motions. Existing solutions for extreme-view synthesis typically require dedicated video pairs, demanding substantial annotation effort. To address these limitations, we propose Dynamic Extreme VIew Synthesis-GRPO (DEVIS-GRPO), a GRPO-based framework for trajectory-controlled video generation, the first online policy gradient method for extreme view video generation. Central to our approach is a novel sampling strategy: Accumulative Dynamic Extreme VIew Synthesis (ADEVIS), which achieves large-view camera motions by progressively accumulating small-view increments. This method delivers two key advantages: 1) enhanced training efficiency, as it eliminates the need to warm-start the policy model by collecting expensive paired large-view videos, and 2) increased sampling diversity, achieved by flexibly varying trajectory configurations. Finally, we designed a multi-level consistency-quality reward function to select high-quality samples for model optimization. Experiments on the Kubric-4D, iPhone, and DL3DV datasets demonstrate our method's superiority. On Kubric-4D, we achieve relative improvements of 21.57% in PSNR and 7.31% in SSIM over the second-best method in non-occlusion areas. On iPhone, LPIPS is reduced by 18.56%. --- ### Emulating the Forced Response of Climate Models with Generative Machine Learning Authors: Graham Clyne, Julia Kaltenborn, Peer Nowack, Claire Monteleoni, Anastase Charantonis Published: 2026-05-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16929v2 Global climate models are essential tools to simulate past and potential future pathways of climate change, as well as associated climate impacts. Shared Socioeconomic Pathways (SSPs) describe a range of future scenarios of global economic and demographic development. These SSPs are intrinsically linked to changes in climate forcings -- the external drivers, such as greenhouse gas and aerosol emissions, which change Earth's energy balance over time. These forcings act as boundary conditions in Earth System Models (ESM), providing insight into the potential climatic impacts of each SSP. Running an ESM, however, is extremely computationally expensive, conflicting with the need for large ensemble runs to provide robust estimates in the presence of internal variability and scenario uncertainty. Machine Learning emulators provide a promising avenue towards fast and cheap scenario generation, but until recently lacked uncertainty quantification and the ability to condition on external forcings. Here, we build upon recent work and extend it by training on multiple SSPs. We successfully generate scenarios of IPSL -- CM6A -- LR unseen during training and remain physically consistent with the underlying climate model, even under strong extrapolation scenarios. Our emulator is validated against MESMER -- M, a statistical emulator of land surface temperature. Our research demonstrates that our model, ArchesClimate -- SSP, does not simply imitate scenarios seen during training, but is actually capable of modeling the response of a climate state to diverse forcings. This is an important step towards reliable and rapid climate model scenario generation. --- ### Emulating the Forced Response of Climate Models with Flow Matching Authors: Graham Clyne, Julia Kaltenborn, Peer Nowack, Claire Monteleoni, Anasatase Charantonis Published: 2026-05-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16929v1 Global climate models are essential tools to simulate past and potential future pathways of climate change, as well as associated climate impacts. Shared Socioeconomic Pathways (SSPs) describe a range of future scenarios of global economic and demographic development. These SSPs are intrinsically linked to changes in climate forcings, the external drivers, such as greenhouse gas and aerosol emissions, which in turn lead to the human impact on the energy balance of the Earth over time. These forcings are fundamental boundary conditions in climate models in order to gain insight into the potential climatic impacts of these changes described by each SSP. Running a climate model, however, is extremely computationally expensive, conflicting with the need for large ensembles of simulations for each model to give, e.g., more robust estimates in the presence of internal variability (the inherent, chaotic fluctuations within the climate system) and scenario uncertainty. Recent research has demonstrated the ability to capture climate model dynamics using machine learning when conditioned on forcings from different climatic scenarios. We here train a Deep Learning (DL) model on multiple SSPs and successfully generate scenarios unseen during training. Our emulator is validated against MESMER-M, a statistical emulator of land surface temperature. Our research demonstrates the capacity to generate such changing climate states in response to a variety of simultaneous climate forcings (e.g., carbon dioxide, methane, nitrous oxide, sulphate aerosols, and ozone). In particular, our ablation studies underline a need to include a range of different forcings to represent long-term atmospheric trends with a DL emulator. --- ### Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps Authors: Yanke Zhou, Yiduo Li, Hanlin Tang, Maohua Li, Kan Liu, Tao Lan, Lin Qu, Yuan Yao, Xiaoxing Ma Published: 2026-05-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.16928v2 Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training or on heuristic token eviction, creating an undesirable trade-off among efficiency, training cost, and accuracy. In this work, we show that full-attention LLMs are already intrinsically sparse and can be transformed into highly sparse models with only minimal adaptation. Our approach is built on three observations: (1) only a small subset of attention heads truly requires full long-context processing; (2) long-range retrieval is governed primarily by a low-dimensional subspace, allowing relevant tokens to be retrieved efficiently with a 16-dimensional indexer; and (3) the useful token budget is strongly query-dependent, making dynamic top-$p$ selection more suitable than fixed top-$k$ sparsification. Based on these insights, we propose RTPurbo, which retains the full KV cache only for retrieval heads and introduces a lightweight token indexer for sparse attention. By exploiting the model's intrinsic sparsity, RTPurbo achieves sparsification with only a few hundred training steps. Experiments on long-context benchmarks and reasoning tasks show that RTPurbo preserves near-lossless accuracy while delivering substantial efficiency gains, including up to a 9.36$\times$ prefill speedup at 1M context and about a 2.01$\times$ decode speedup. These results suggest that strong sparse inference can be obtained from standard full-attention training without expensive native sparse pretraining. --- ### From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction Authors: Pujun Feng, Xiaoyu Guo, Seyed Ehsan Saffari, Min Hun Lee, Siew-Kei Lam, Erik Cambria, Xibin Sun, Yangtao Zhou, Tong Yang, Xiaoyu Zhang, Tao Tan, Yue Sun et al. Published: 2026-05-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.16927v1 Clinical decision-making is a feedback system where risk estimates influence treatment, which in turn changes disease trajectories, and both shape clinicians' measurement practices. Static prediction often fails clinically: models trained on observational care logs conflate disease biology with clinician behavior, particularly under treatment confounder feedback and irregular or informative observation. This Review focuses on intervention-aware disease trajectory modeling in clinical AI--methods estimating patient-specific longitudinal disease evolution and assessing trajectory changes under alternative treatments. We organize the field around six linked components: three decision tasks (factual forecasting, counterfactual estimation, policy evaluation) and three data-generating mechanisms (disease evolution, treatment assignment, observation process) that determine identifiability. We present the first unified framework bridging forecasting, counterfactual trajectories, and policy evaluation across discrete/continuous time, explicitly addressing treatment assignment, time-varying confounding, and observation bias. We synthesize key method families (multistate/joint models, temporal point-process, deep sequence architectures, longitudinal causal inference), map them to relevant components, and align evaluation with claim strength via overlap diagnostics, uncertainty quantification, off-policy robustness, and target-trial validation. This synthesis advances benchmark prediction to decision-grade clinical evidence, enabling treatment-sensitive individualized futures, pre-deployment policy stress-testing, and safer closed-loop learning health systems that adapt/abstain when evidence is insufficient. --- ### P2GS: Physical Prior-guided Gaussian Splatting for Photometrically Consistent Urban Reconstruction Authors: Kota Shimomura, Hidehisa Arai, Tsubasa Takahashi, Takayoshi Yamashita, Hironobu Fujiyoshi Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16925v1 3D Gaussian Splatting (3DGS) has recently emerged as a powerful explicit representation enabling fast, high-fidelity rendering, making it a promising foundation for closed-loop simulators and perception models in autonomous driving. However, conventional 3DGS implicitly assumes consistent exposure and tone mapping across views. Real driving data violates this assumption due to heterogeneous camera pipelines and dynamic outdoor illumination, baking exposure discrepancies and sensor noise into the radiance field and producing artifacts and inconsistent illumination especially in static backgrounds crucial for realistic simulation. These issues are amplified in autonomous driving, where sparse viewpoints, varying exposures, and outdoor lighting interact, while prior work mainly targets dynamic-object reconstruction and overlooks cross-view photometric consistency. To address this limitation, we introduce P2GS, a physically consistent Gaussian Splatting framework that jointly decomposes a view-invariant linear HDR radiance field, per-view exposure scales, and tone-mapping functions from only LDR images without HDR supervision. P2GS employs a unified optimization strategy grounded in the physical image-formation process, enforcing relative-exposure consistency and HDR-domain radiance regularization. This yields a radiance field robust to inter-camera illumination differences while preserving the real-time efficiency of standard 3DGS. Experiments across real and simulated driving environments show that P2GS matches or surpasses prior methods in LDR reconstruction while providing substantially improved photometric consistency, reliable exposure normalization, and physically coherent illumination across diverse scenes. --- ### Neuroscience-inspired Staged Representation Learning with Disentangled Coarse- and Fine-Grained Semantics for EEG Visual Decoding Authors: Xiang Gao, Hui Tian, Yanming Zhu, Xuefei Yin, Alan Wee-Chung Liew Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16923v3 Decoding visual information from electroencephalography (EEG) signals remains a fundamental challenge in brain-computer interfaces and medical rehabilitation. Existing EEG visual decoding methods mainly focus on learning a single global EEG embedding for cross-modal alignment, but they largely overlook the staged and hierarchical characteristics of human visual processing. To address this limitation, we propose a neuroscience-inspired staged representation learning framework that reformulates EEG visual decoding as a stage-specific representation decomposition problem. The proposed framework organizes EEG representation learning into three complementary phases: low-level visual representation learning, high-level semantic representation learning, and integrative information fusion. To strengthen semantic modeling, we further introduce a multimodal dual-level semantic learning mechanism that separates coarse label-level semantics from fine image-level visual-semantic information. In addition, semantic latent channels are introduced as computational representation channels generated from observed visual EEG signals, expanding the channel-level semantic representation space for structured semantic abstraction and cross-modal alignment. Extensive experiments on the THINGS-EEG benchmark demonstrate that the proposed method achieves superior performance under subject-dependent zero-shot evaluation and improved exact retrieval under subject-independent zero-shot evaluation. Additional analyses, including layer-wise retrieval, temporal accumulation, expanded multi-image retrieval, and ablation studies, further support the effectiveness of staged decomposition and structured semantic modeling. These results suggest that explicitly modeling staged perceptual, semantic, and integrative representations provides an effective neuroscience-inspired framework for EEG-based visual decoding. --- ### Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation Authors: Youngdong Jang, Gyeongrok Oh, Jong Wook Kim, Hyunju Ryu, Hyung-gun Chi, SeungHyeon Kim, Seungryong Kim, Jonghyun Choi, Sangpil Kim Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16922v1 LiDAR scene flow estimation is essential for autonomous driving, as it provides 3D motion for each point. Self-supervised approaches use static-dynamic classification to mitigate the imbalance between static and dynamic points, deriving targeted supervision. However, existing methods rely on sparse geometric observations for this classification, making them vulnerable to data sparsity and occlusions. The resulting noisy labels provide incorrect motion guidance and degrade scene flow learning. To address this, we introduce TrackCue, a tracking-guided framework for improving dynamic object representation in LiDAR scene flow estimation. In particular, TrackCue repurposes point tracking to obtain dense image-space trajectories anchored to LiDAR points, providing motion cues beyond sparse geometric observations. Furthermore, we present a visually consistent motion compensation strategy that compares the tracked trajectories with ego-induced rigid trajectories in the image plane, effectively isolating true object motion from ego-induced apparent motion. To transfer these isolated motion cues back to the LiDAR domain, we perform visual motion cue lifting, which associates ego-compensated image trajectories with LiDAR points for static-dynamic label refinement. As a result, TrackCue produces more accurate static-dynamic classification and provides more reliable supervision for scene flow learning. Experimental results show that TrackCue significantly improves the precision and F1 score of dynamic labels, leading to performance gains in self-supervised scene flow estimation. --- ### CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series Authors: Jiecheng Lu, Jieqi Di, Runhua Wu, Yuwei Zhou Published: 2026-05-16 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.16919v1 Many decision-facing stochastic systems are observed through aggregate distributions rather than scalar trajectories: queue occupancies, mobility shares, public-health mixtures, generation-source shares, ecological compositions, and air-quality severity profiles all live on the probability simplex and evolve over time. We study causal (online) forecasting for these distribution-valued time series and argue that the transition operator itself should be structured around the simplex. We introduce CAST (Causal Anchored Simplex Transport), a successor-local operator that (i) retrieves empirical successors from causal context, (ii) stabilizes them with a persistence anchor, and (iii) applies a bounded local stochastic transport on ordered supports; every stage preserves the simplex by construction. We identify a structural failure mode, latent transition-kernel aliasing, where similar observed distributions evolve differently under different contextual regimes, and prove that any forecaster depending only on an aliased summary incurs an irreducible weighted Jensen-Shannon excess-risk lower bound, while the CAST hypothesis class contains the regime-aware Bayes successor; for ordered supports an additional Pinsker separation holds whenever the transported successor lies outside the no-transport anchor hull. On eleven public and simulated benchmarks spanning ecology, energy, diet, mortality, employment, air quality, severe weather, mobility, and G/G/1, G_t/G/1 queue occupancy, CAST attains the best average rank on both one-step KL (1.27) and autoregressive rollout JSD (1.91), winning 8/11 sections on each metric against a broad statistical, compositional, recurrent, convolutional, and Transformer baseline set, and top-2 on all 11 sections for offline KL. Component ablations and a controlled synthetic aliasing experiment corroborate the theory. --- ### HighSync: High-Quality Lip Synchronization via Latent Diffusion Models Authors: Saeid Firouzi Daghigh, Majid Iranpour Mobarakeh, Mostafa Alavi, Mahdi Bagheri Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16918v2 We present HighSync, an end-to-end diffusion-based framework for high-fidelity lip synchronization that generates photorealistic talking-face videos aligned with arbitrary input audio. Existing approaches consistently struggle to reconcile image quality with synchronization accuracy, producing either visually degraded outputs or temporally inconsistent lip movements. HighSync addresses both challenges simultaneously and, to our knowledge, is the first lip sync model to operate natively at 512*512 resolution, positioning it as a viable solution for professional production environments such as the film and broadcast industries. Central to our approach is the identification and systematic elimination of a data leakage phenomenon that has silently undermined temporal modeling in prior work, preventing models from developing a genuine dependence on the audio signal. Comprehensive evaluations across both perceptual quality and synchronization accuracy metrics confirm that HighSync achieves state-of-the-art performance on both fronts. Source code, pre-trained models, and supplementary video results are publicly available at: https://github.com/saeed5959/high_sync --- ### HighSync: High-Quality Lip Synchronization via Latent Diffusion Models Authors: Saeed Firouzi Daghigh, Majid Iranpour Mobarekeh, Mostafa Alavi, Mehdi Bagheri Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16918v1 We present HighSync, an end-to-end diffusion-based framework for high-fidelity lip synchronization that generates photorealistic talking-face videos aligned with arbitrary input audio. Existing approaches consistently struggle to reconcile image quality with synchronization accuracy, producing either visually degraded outputs or temporally inconsistent lip movements. HighSync addresses both challenges simultaneously and, to our knowledge, is the first lip sync model to operate natively at 512*512 resolution, positioning it as a viable solution for professional production environments such as the film and broadcast industries. Central to our approach is the identification and systematic elimination of a data leakage phenomenon that has silently undermined temporal modeling in prior work, preventing models from developing a genuine dependence on the audio signal. Comprehensive evaluations across both perceptual quality and synchronization accuracy metrics confirm that HighSync achieves state-of-the-art performance on both fronts. Source code, pre-trained models, and supplementary video results are publicly available at: https://github.com/saeed5959/high_sync --- ### A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights Authors: Fabiola Ricci, Claudia Merger, Sebastian Goldt Published: 2026-05-16 Categories: stat.ML, cond-mat.dis-nn, cond-mat.stat-mech, cs.LG, math.PR arXiv: https://arxiv.org/abs/2605.16913v1 Neural networks trained with gradient-based methods exhibit a strong simplicity bias: they learn simpler statistical features of their data before moving to more complex features. Previous analyses of this phenomenon have largely focused on settings with (quasi-)isotropic inputs. In this work, we study the simplicity bias from a Fourier perspective, which allows us to include two key features of natural images in the analysis: approximate translation-invariance and power-law spectra. We first show experimentally that simple neural networks trained on image classification tasks first rely on amplitude information -- related to pair-wise correlations between pixels -- before exploiting phase information, which encodes edges and higher-order correlations. In view of this, we introduce a synthetic data model for translation-invariant inputs that allows precise control over amplitudes and phases while remaining tractable. We rigorously establish that for isotropic and high-dimensional inputs, classification based on phase information alone is a genuinely hard task: online stochastic gradient descent (SGD) cannot distinguish the structured inputs from noise within $n \ll N^3$ steps, but needs at least $n \gg N^3 \log^2{N}$ steps. In contrast, we show both experimentally and theoretically that power-law spectra can dramatically accelerate the speed of learning phase information, even if the spectra do not help with classification. Simulations with two-layer networks trained on textures and with deep convolutional networks on ImageNet and CIFAR100 confirm this non-trivial interaction between amplitudes and phases, providing mechanistic insights into how deep neural networks can learn natural image distributions efficiently. --- ### VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction Authors: Xun Chen, Tianchen Deng, Rui Wang, Fangjinhua Wang, Junyi Ma, Hongming Shen, Hesheng Wang, Danwei Wang Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16911v1 3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subsequent operations like offset learning, attention weighting, and cross-camera aggregation remain geometry-agnostic, ignoring essential physical constraints. We propose VGGT-Occ, a framework that embeds geometric tokens throughout the entire pipeline. We introduce Projection-Aware Deformable Attention (PA-DA) to inject geometry into all attention stages. PA-DA projects 3D offsets back to image planes and leverages the projection Jacobian as an additive bias to suppress unreliable observations. Features are then integrated through a view-quality semantic gate for cross-view consistency. To optimize both efficiency and performance, we employ a sequential coarse-to-fine decoder with gated fusion, where low-resolution features are refined into higher resolutions, allocating computation by information density while substantially reducing decoder cost. Extensive evaluations demonstrate the effectiveness and accuracy of our approach. On SurroundOcc-nuScenes, VGGT-Occ achieves 33.00\% IoU and 21.08\% mIoU ($T{=}1$), and 33.64\% IoU and 21.43\% mIoU with $T{=}2$ inference, outperforming existing methods, with only ${\sim}41$M trainable parameters in the occupancy head. Code will be released publicly. --- ### TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents Authors: Zhiqiang Liu, Wenhui Dong, Yilang Tan, Yuwen Qu, Haochen Yin, Chenyang Si Published: 2026-05-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.16909v1 Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before producing a final result. Existing benchmarks, however, often evaluate tool use, computer use, and multimodal reasoning in isolation, leaving a gap between benchmark settings and end-to-end omni-modal tool use in the real world. To address this gap, we introduce MM-ToolBench, a benchmark and evaluation harness for task-oriented omni-modal tool use. MM-ToolBench contains 100 executable tasks from two macro task families, Customer Service and Intelligent Creation, covering 20 subcategory slices and supported by 27 MCP servers with 324 tools. The central design of MM-ToolBench is closed-loop multimodal verification: agents must execute tools, inspect rendered or transformed artifacts, and self-correct when outputs fail task-specific requirements. To make such evaluation scalable and verifiable, MM-ToolBench couples MCP-based execution with task-specific grounded evaluators and a semi-automated construction pipeline for scenario discovery, task instantiation, evaluator synthesis, and human audit. Experiments on 15 contemporary agentic models show that MM-ToolBench remains highly challenging: Claude Opus 4.6, commonly regarded as one of the strongest coding-agent models, achieves only 32.0% task success, far below the 94.0% human benchmark. We envision MM-ToolBench as a practical foundation for evaluating and advancing next-generation omni-modal tool-using agents through closed-loop multimodal verification. --- ### BIDO: A Biometric Identity Online Authentication Framework Authors: Aditya Mithra, Sibi Chakkaravarthy S, Srinivas Kankanala Published: 2026-05-16 Categories: cs.ET, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2605.16908v1 Security systems demand continuous, cryptograph- ically robust identity verification without requiring subjects to carry physical tokens, smart cards, or dedicated hardware authenticators. This paper presents BIDO (Biometric Identity Online), a device-free authentication standard that achieves Au- thenticator Assurance Level 2 (AAL2) per NIST SP 800-63B with- out storing long-lived biometric templates, facial images, or any other form of Personally Identifiable Information (PII). BIDO derives Elliptic Curve Digital Signature Algorithm (ECDSA) key material deterministically from a live biometric measurement salted with a user-defined memorized secret at every authen- tication event, eliminating persistent private-key storage while enabling verification from any commodity sensor terminal. The generated credentials are non-discoverable (non-resident) Web Authentication (WebAuthn) credentials, fully compatible with all FIDO2-enabled websites and services without modification on the server side. A multi-stage pipeline, comprising capture of 200 valid biometric samples, feature extraction using the Dlib 68- point facial landmark predictor, affine face alignment, frontality gating, Euclidean distance computation from the inter-eye mid- point, floor-division quantization with divisor q = 8, inter-session drift stabilization, and majority-voting SHA-256 hash binding, produces a Verification Seed (Vseed) from which the WebAuthn credential is transiently derived and immediately zeroized after signing. Evaluated against three prominent face benchmarks (VGGFace2, LFW, and MegaFace), achieving 99.51% verification accuracy on LFW and 92.14% Rank-1 identification accuracy on MegaFace Challenge 1 at 10^6 distractors, with a cryptographic False Accept Rate (FAR) of 0.03%, a False Reject Rate (FRR) of 0.90%. --- ### AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps Authors: Chia-Ying Hsieh, Hsin-Yuan Fang, Chun-Shu Wei Published: 2026-05-16 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2605.16905v1 Post-hoc saliency methods are widely used to interpret deep neural networks, but their faithfulness is difficult to evaluate reliably. Existing evaluations mask features according to saliency-induced feature ordering and measure performance degradation, but this degradation can be confounded by the masking operator: zero masking may create out-of-distribution artifacts, while interpolation-based masking may preserve residual predictive information. We propose Adversarial Information Masking (AIM), a saliency-guided adversarial feature replacement framework for evaluating both saliency-map faithfulness and masking-operator reliability. AIM replaces selected features with values from an adversarial counterpart of the input and compares degradation under complementary masking orders. We assess reliability using random-attribution bias and stability of explanation-method faithfulness rankings. Experiments on image, audio, and EEG tasks suggest that AIM reduces masking-induced bias compared with zero and interpolation-based masking, while revealing modality-dependent differences between signed and unsigned attributions. --- ### WOW-Seg: A Word-free Open World Segmentation Model Authors: Danyang Li, Tianhao Wu, Bin Li, Zhenyuan Chen, Yang Zhang, Yuxuan Li, Ming-Ming Cheng, Xiang Li Published: 2026-05-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.16903v1 Open world image segmentation aims to achieve precise segmentation and semantic understanding of targets within images by addressing the infinitely open set of object categories encountered in the real world. However, traditional closed-set segmentation approaches struggle to adapt to complex open world scenarios, while foundation segmentation models such as SAM exhibit notable discrepancies between their strong segmentation capabilities and relatively weaker semantic understanding. To bridge these discrepancies, we propose WOW-Seg, a Word-free Open World Segmentation model for segmenting and recognizing objects from open-set categories. Specifically, WOW-Seg introduces a novel visual prompt module, Mask2Token, which transforms image masks into visual tokens and ensures their alignment with the VLLM feature space. Moreover, we introduce the Cascade Attention Mask to decouple information across different instances. This approach mitigates inter-instance interference, leading to a significant improvement in model performance. We further construct an open world region recognition test benchmark: the Region Recognition Dataset (RR-7K). With 7,662 classes, it represents the most extensive category-rich region recognition dataset to date. WOW-Seg attains strong results on the LVIS dataset, achieving a semantic similarity of 89.7 and a semantic IoU of 82.4. This performance surpasses the previous SOTA while using only one-eighth the parameter count. These results underscore the strong open world generalization capabilities of WOW-Seg. The code and related resources are available at https://github.com/AAwcAA/WOW-Seg-Meta. --- ### ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery Authors: Haofei Yu, Jiaxuan You, Peter Clark, Bodhisattwa Prasad Majumder, Kyle Richardson Published: 2026-05-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16902v2 Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have access to a large number of artifacts. Yet, a key challenge remains: how can we automatically discover the state-of-the-art (SOTA) model for a given dataset by fully leveraging existing artifacts? We formalize this task as automatic SOTA discovery by modeling HuggingFace as an artifact graph, where nodes are models/datasets and edges represent evaluations. We propose ArtifactLinker, a two-stage framework: (1) ranking promising unobserved model--dataset links using Graph Neural Networks (GNNs) or graph-augmented Large Language Models (LLMs), and (2) verifying top-ranked links via coding experiments with LLM-based agents. We further introduce a benchmark named ArtifactBench with 14,053 artifacts and 51,337 relations to evaluate the performance of both stages. Results show that (1) graph structures between existing artifacts are effective for missing link prediction; (2) end-to-end ranking and verification with ArtifactLinker help discover potential SOTA results and research insights. --- ### ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery Authors: Haofei Yu, Jiaxuan You, Peter Clark, Bodhisattwa Prasad Majumder, Kyle Richardson Published: 2026-05-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16902v1 Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have access to a large number of artifacts. Yet, a key challenge remains: how can we automatically discover the state-of-the-art (SOTA) model for a given dataset by fully leveraging existing artifacts? We formalize this task as automatic SOTA discovery by modeling HuggingFace as an artifact graph, where nodes are models/datasets and edges represent evaluations. We propose ArtifactLinker, a two-stage framework: (1) ranking promising unobserved model--dataset links using Graph Neural Networks (GNNs) or graph-augmented Large Language Models (LLMs), and (2) verifying top-ranked links via coding experiments with LLM-based agents. We further introduce a benchmark named ArtifactBench with 14,053 artifacts and 51,337 relations to evaluate the performance of both stages. Results show that (1) graph structures between existing artifacts are effective for missing link prediction; (2) end-to-end ranking and verification with ArtifactLinker help discover potential SOTA results and research insights. ---