OCR
-
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
2026-05-13 17:52:53Zhaowei Wang, Lishu Luo, Haodong Duan, Weiwei Liu, Sijin Wu, Ji Luo, Shen Yan, Shuai Peng, Sihang Yuan, Chaoyi Huang, Yi Lin, Yangqiu SongAbstract
Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet practical training recipes remain insufficiently explored, particularly for designing and balancing long-context data mixtures. In this work, we present a systematic study of long-context continued pre-training for LVLMs, extending a 7B model from 32K to 128K context with extensive ablations on long-document data. We first show that long-document VQA is substantially more effective than OCR transcription. Building on this observation, our ablations further yield three key findings: i) for sequence-length distribution, balanced data outperforms target-length-focused data (e.g., 128K), suggesting that long-context ability requires generalizable key-information retrieval across various lengths and positions; ii) retrieval remains the primary bottleneck, favoring retrieval-heavy mixtures with modest reasoning data for task diversity; and iii) pure long-document VQA largely preserves short-context capabilities, suggesting that instruction-formatted long data reduces the need for short-data mixing. Based on these findings, we introduce MMProLong, obtained by long-context continued pre-training from Qwen2.5-VL-7B with only a 5B-token budget. MMProLong improves long-document VQA scores by 7.1% and maintains strong performance at 256K and 512K contexts beyond its 128K training window, without additional training. It further generalizes to webpage-based multimodal needle retrieval, long-context vision-text compression, and long-video understanding without task-specific supervision. Overall, our study establishes a practical LongPT recipe and an empirical foundation for advancing long-context vision-language models.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13831
PDF
-
Qwen-Image-VAE-2.0 Technical Report
2026-05-13 14:04:56Zekai Zhang, Deqing Li, Kuan Cao, Yujia Wu, Chenfei Wu, Yu Wu, Liang Peng, Hao Meng, Jiahao Li, Jie Zhang, Kaiyuan Gao, Kun Yan, Lihan Jiang, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiao Xu, Xiaoyue Chen, Yan Shu, Yanran Zhang, Yilei Chen, Yixian Xu, Yuxiang Chen, Zhendong Wang, Zihao Liu, Zikai Zhou, Yiliang Gu, Yi Wang, Xiaoxiao Xu, Lin QuAbstract
We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To address the reconstruction bottlenecks of high compression, we adopt an improved architecture featuring Global Skip Connections (GSC) and expanded latent channels. Moreover, we scale training to billions of images and incorporate a synthetic rendering engine to improve performance in text-rich scenarios. To tackle the convergence challenges of high-dimensional latent space, we implement an enhanced semantic alignment strategy to make the latent space highly amenable to diffusion modeling. To optimize computational efficiency, we leverage an asymmetric and attention-free encoder-decoder backbone to minimize encoding overhead. We present a comprehensive evaluation of Qwen-Image-VAE-2.0 on public reconstruction benchmarks. To evaluate performance in text-rich scenarios, we propose OmniDoc-TokenBench, a new benchmark comprising a diverse collection of real-world documents coupled with specialized OCR-based evaluation metrics. Qwen-Image-VAE-2.0 achieves state-of-the-art reconstruction performance, demonstrating exceptional capabilities in both general domains and text-rich scenarios at high compression ratio. Furthermore, downstream DiT experiments reveal our models possess superior diffusability, significantly accelerating convergence compared to existing high-compression baselines. These establish Qwen-Image-VAE-2.0 as a leading model with high compression, superior reconstruction, and exceptional diffusability.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13565
PDF
-
Constitutional Governance in Metric Spaces
Abstract
Computational social choice and algorithmic decision theory offer rich aggregation theory but no end-to-end, polynomial-time process for egalitarian self-governance: prior work treats aggregation, deliberation, amendment, and consensus in isolation, and key metric-space aggregators are NP-hard. We propose constitutional governance in metric spaces, integrating these stages into one polynomial-time process. The constitution assigns, per amendable component, a metric space, aggregation rule, and supermajority threshold. Each member submits an ideal element -- both vote and personal proposal. Any member may then submit a public proposal carrying supermajority public support under the revealed votes -- sourced from coalition deliberation, optimization, or AI mediation. The constitutional rule scores proposals against the status quo, adopting the supported proposal of positive maximal score (else retaining the status quo); the same rule, possibly with a higher threshold, amends the constitution itself. We develop the generalised median as the worked rule, establish framework-level guarantees, prove no misreport weakly dominates sincere voting, and study the compromise gap between best peak and unconstrained optimum -- zero in one dimension, bounded in general, narrowed in simulation by a simple heuristic. We instantiate the framework on seven canonical settings; the mean appears as a utilitarian alternative in the appendix. By unifying metric-space aggregation, reality-aware social choice, supermajority amendment, constitutional consensus, deliberative coalition formation, and AI mediation, this work delivers a comprehensive solution to the constitutional democratic governance of digital communities and organisations.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13362
PDF
-
A Multi-Agent Orchestration Framework for Venture Capital Due Diligence
2026-05-13 07:20:16Grigorios Alexandrou, Katerina PramatariAbstract
We present a fully automated multi-agent framework for corporate due diligence and market analysis in venture capital. The system runs on an event-driven orchestration architecture, combining Large Language Models (LLMs) with real-time web retrieval to synthesize unstructured data into structured investment intelligence. A central technical contribution is a programmatic extraction pipeline that reverse-engineers the frontend-to-backend communication of the Greek Business Registry ($\Gamma$.this http URL.), querying dynamic endpoints to retrieve official financial filings that are then parsed using a layout-aware OCR extractor. A structural fallback mechanism explicitly flags data absence rather than generating unverified figures, directly targeting hallucination in financial contexts. All workflow artifacts are publicly available to support replication.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13110
PDF
-
Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education
2026-05-13 04:37:45Mragisha Jain, Tirth Bhatt, Griffin Pitts, Aum Pandya, Peter Brusilovsky, Narges Norouzi, Arto Hellas, Juho Leinonen, Bita AkramAbstract
Students learning algorithms often need support as they interpret traces, debug reasoning errors, and apply procedures across unfamiliar problem instances. In this paper, we present KITE (Knowledge-Informed Tutoring Engine), a Retrieval-Augmented Generation (RAG)-based intelligent tutoring system designed to serve as a classroom teaching assistant for algorithmic reasoning and problem-solving tasks. KITE uses an intent-aware Socratic response strategy to tailor support to different student needs, responding with targeted hints, guiding questions, and progressive scaffolding intended to strengthen students' algorithmic problem-solving ability. To keep responses aligned with course content, KITE uses a multimodal RAG pipeline that retrieves relevant information from course materials. We evaluate KITE using three forms of assessment: RAGAs-based metrics for response grounding and quality, expert evaluation of pedagogical quality, and a simulated student pipeline in which a weaker language model interacts with KITE across two-turn dialogues and produces revised answers after receiving feedback. Results indicate that KITE produces contextually grounded and pedagogically appropriate responses. Further, using simulated students, KITE's feedback helped the student models produce more accurate follow-up responses on procedural and tracing questions, suggesting that its scaffolding can support algorithmic problem-solving. This work contributes a tutoring architecture and an evaluation approach for assessing retrieval-grounded explanations and scaffolded problem-solving feedback.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12988
PDF
-
The End Justifies the Mean: A Linear Ranking Rule for Proportional Sequential Decisions
2026-05-12 20:26:37Carmel Baharav, Niclas Boehmer, Bailey Flanigan, Maximilian T. WittmannAbstract
AI alignment and participatory design motivate a new democratic design problem: how to collectively choose a decision rule to use repeatedly. We study this problem for linear ranking rules, which repeatedly rank items $x_j$ within batches $X=(x_1,\dots,x_m)\in(\mathbb{R}^d)^m$, where each item's ranking is dictated by its score $\langle \theta^*,x_j\rangle$ according to a fixed scoring vector $\theta^*$. Given voters' preferred scoring vectors $\theta^{(1)},\dots,\theta^{(n)}$ and their population fractions $\alpha^{(1)},\dots,\alpha^{(n)}$, we ask how to choose a collective vector $\theta^*$ satisfying individual proportionality (IP): every voter type $i$ should agree with the resulting rankings to an $\alpha^{(i)}$-proportional degree, either on average over time (long-run IP) or even within each batch (per-batch IP). The default rule, the arithmetic mean of the $\theta^{(i)}$, has been shown to be severely majoritarian; more generally, it is not clear that any fixed linear rule can balance many voters' disparate opinions. Our main result is that, surprisingly, there is a simple rule that does satisfy long-run IP: the angular mean, the spherical analog of the arithmetic mean. We then show that exact per-batch IP is impossible for fixed linear rules, but that the gap between per-batch and long-run IP shrinks quickly with batch size. Experiments on three real-world preference datasets show that all rules perform similarly when voters' preferences are homogeneous, while the angular mean substantially improves proportionality in high-disagreement regimes.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12717
PDF
-
DocAtlas: Multilingual Document Understanding Across 80+ Languages
2026-05-12 18:09:38Ahmed Heakl, Youssef Mohamed, Abdullah Sohail, Rania Elbadry, Ahmed Nassar, Peter W. J. Staar, Fahad Shahbaz Khan, Imran Razzak, Salman KhanAbstract
Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that perpetuate existing biases. We introduce DocAtlas, a framework that constructs high-fidelity OCR datasets and benchmarks covering 82 languages and 9 evaluation tasks. Our dual pipelines, differential rendering of native DOCX documents and synthetic LaTeX-based generation for right-to-left scripts produce precise structural annotations in a unified DocTag format encoding layout, text, and component types, without learned models for core annotation. Evaluating 16 state-of-the-art models reveals persistent gaps in low-resource scripts. We show that Direct Preference Optimization (DPO) using rendering-derived ground truth as positive signal achieves stable multilingual adaptation, improving both in-domain (+1.9%) and out-of-domain (+1.8%) accuracy without measurable base-language degradation, where supervised fine-tuning degrades out-of-domain performance by up to 21%. Our best variant, DocAtlas-DeepSeek, improves +1.7% over the strongest baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12623
PDF
-
MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering
2026-05-12 16:32:43Rezarta Islamaj, Robert Leaman, Joey Chan, Nicholas Wan, Qiao Jin, Natalie Xie, John Wilbur, Shubo Tian, Lana Yeganova, Po-Ting Lai, Chih-Hsuan Wei, Yifan Yang, Yao Ge, Qingqing Zhu, Zhizheng Wang, Zhiyong LuAbstract
Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain discriminative as model capabilities improve. Existing biomedical question answering (QA) benchmarks are limited in this respect. Multiple-choice formats can allow models to succeed through answer elimination rather than inference, while widely circulated exam-style datasets are increasingly vulnerable to performance saturation and training data contamination. Multi-hop reasoning, defined as the ability to integrate information across multiple sources to derive an answer, is central to clinically meaningful tasks such as diagnostic support, literature-based discovery, and hypothesis generation, yet remains underrepresented in current biomedical QA benchmarks. MedHopQA is a disease-centered multi-hop reasoning benchmark consisting of 1,000 expert-curated question-answer pairs introduced as a shared task at BioCreative IX. Each question requires synthesis of information across two distinct Wikipedia articles, and answers are provided in an open-ended free-text format. Gold annotations are augmented with ontology-grounded synonym sets from MONDO, NCBI Gene, and NCBI Taxonomy to support both lexical and concept-level evaluation. MedHopQA was constructed through a structured process combining human annotation, triage, iterative verification, and LLM-as-a-judge validation. To reduce leaderboard gaming and contamination risk, the 1,000 scored questions are embedded within a publicly downloadable set of 10,000 questions, with answers withheld, on a CodaBench leaderboard. MedHopQA provides both a benchmark and a reusable framework for constructing future biomedical QA datasets that prioritize compositional reasoning, saturation resistance, and contamination resistance as core design constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12361
PDF
-
Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering
2026-05-12 15:59:28Rezarta Islamaj, Joey Chan, Robert Leaman, Jongmyung Jung, Hyeongsoon Hwang, Quoc-An Nguyen, Hoang-Quynh Le, Harikrishnan Gurushankar Saisudha, Ganesh Chandrasekar, Rustam R. Taktashov, Nadezhda Yu. Bizyukova, Sofia I. R. Concei\c{c}\~ao, Paulo R. C. Lopes, Reem Abdel Salam, Mary Adewunmi, Zhiyong LuAbstract
Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple sources to answer complex questions. To address this problem, the BioCreative IX MedHopQA shared task was designed to benchmark in multi-hop reasoning for large language models (LLMs). We developed a novel dataset of 1,000 challenging QA pairs spanning diseases, genes, and chemicals, with particular emphasis on rare diseases. Each question was constructed to require two-hop reasoning through the integration of information from two distinct Wikipedia pages. The challenge attracted 48 submissions from 13 teams. Systems were evaluated using both surface string comparison and conceptual accuracy (MedCPT score). The results showed a substantial performance gap between baseline LLMs and enhanced systems. The top-ranked submission achieved an 89.30% F1 score on the MedCPT metric and an 87.30% exact match (EM) score, compared with 67.40% and 60.20%, respectively, for the zero-shot baseline. A central finding of the challenge was that retrieval-augmented generation (RAG) and related retrieval-based strategies were critical for strong performance. In addition, concept-level evaluation improved answer assessment when correct responses differed in surface form. The MedHopQA dataset is publicly available to support continued progress in this important area. Challenge materials: this https URL and benchmark this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2605.12313
PDF
-
Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters
2026-05-12 11:14:25Gengluo Li, Shangpin Peng, Xingyu Wan, Chengquan Zhang, Hao Feng, Xin Xu, Pian Wu, Bang Li, Zengmao Ding, Yongge Liu, Yipei Ye, Yang Yang, Zhan Shu, Guojun Yan, Zhe Li, Can Ma, Weiping Wang, Yu Zhou, Han HuAbstract
Vision Large Language Models (VLLMs) have achieved remarkable success in modern text-rich visual understanding. However, their perceptual robustness in the face of the continuous morphological evolution of historical writing systems remains largely unexplored. Existing ancient text datasets typically focus on isolated historical periods, failing to capture the systematic visual distribution shifts spanning thousands of years. To bridge this gap and empower Digital Humanities, we introduce Chronicles-OCR, the first comprehensive benchmark specifically designed to evaluate the cross-temporal visual perception capabilities of VLLMs across the complete evolutionary trajectory of Chinese characters, known as the Seven Chinese Scripts. Curated in collaboration with top-tier institutional domain experts, the dataset comprises 2,800 strictly balanced images encompassing highly diverse physical media, ranging from tortoise shells to paper-based calligraphy. To accommodate the drastic morphological and topological variations across different historical stages, we propose a novel Stage-Adaptive Annotation Paradigm. Based on this, Chronicles-OCR formulates four rigorous quantitative tasks: cross-period character spotting, fine-grained archaic character recognition via visual referring, ancient text parsing, and script classification. By isolating visual perception from semantic reasoning, Chronicles-OCR provides an authoritative platform to expose the limitations of current VLLMs, paving the way for robust, evolution-aware historical text perception. Chronicles-OCR is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11960
PDF
-
Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning
2026-05-12 10:18:08Huiyu Yi, Zhiming Xu, Dunwei Tu, Zhicheng Wang, Baile Xu, Furao ShenAbstract
The Nearest Class Mean (NCM) classifier is widely favored in Class-Incremental Learning (CIL) for its superior resistance to catastrophic forgetting compared to Fully Connected layers. While Neural Collapse (NC) theory supports NCM's optimality by assuming features collapse into single points, non-linear feature drift and insufficient training in CIL often prevent this ideal state. Consequently, classes manifest as complex manifolds rather than collapsed points, rendering the single-point NCM suboptimal. To address this, we propose Hierarchical-Cluster SOINN (HC-SOINN), a novel classifier that captures the topological structure of these manifolds via a ``local-to-global'' representation. Furthermore, we introduce Structure-Topology Alignment via Residuals (STAR) method, which employs a fine-grained pointwise trajectory tracking mechanism to actively deform the learned topology, allowing it to adapt precisely to complex non-linear feature drift. Theoretical analysis and Procrustes distance experiments validate our framework's resilience to manifold deformations. We integrated HC-SOINN into seven state-of-the-art methods by replacing their original classifiers, achieving consistent improvements that highlight the effectiveness and robustness of our approach. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11904
PDF
-
LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
2026-05-11 22:42:12Xueqi Cheng, Yushun DongAbstract
Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, cost, and latency. Effective MLLM routing therefore requires more than estimating query difficulty: a router must match the multimodal requirements of the current image-question input with the capabilities of each candidate model. We propose LatentRouter, a router that formulates MLLM routing as counterfactual multimodal utility prediction. Given an image-question query, LatentRouter extracts learned multimodal routing capsules, represents each candidate MLLM with a model capability token, and performs latent communication between these states to estimate how each model would perform if selected. A distributional outcome head predicts model-specific counterfactual quality, while a bounded capsule correction refines close decisions without allowing residual signals to dominate the prediction. The resulting utility-based policy supports performance-oriented and performance-cost routing, and handles changing candidate pools through shared per-model scoring with availability masking. Experiments on MMR-Bench and VL-RouterBench show that LatentRouter outperforms fixed-model, feature-level, and learned-router baselines. Additional analyses show that the gains are strongest on multimodal task groups where model choice depends on visual, layout-sensitive, or reasoning-oriented requirements, and that latent communication is the main contributor to the improvement. The code is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11301
PDF
-
GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction
2026-05-11 07:23:49Ihor Stepanov, Oleksandr Lukashov, Mykhailo Shtopko, Vivek KalyanaranganAbstract
Joint named entity recognition (NER) and relation extraction (RE) is a fundamental task in natural language processing for constructing knowledge graphs from unstructured text. While recent approaches treat NER and RE as separate tasks requiring distinct models, we introduce GLiNER-Relex, a unified architecture that extends the GLiNER framework to perform both entity recognition and relation extraction in a single model. Our approach leverages a shared bidirectional transformer encoder to jointly represent text, entity type labels, and relation type labels, enabling zero-shot extraction of arbitrary entity and relation types specified at inference time. GLiNER-Relex constructs entity pair representations from recognized spans and scores them against relation type embeddings using a dedicated relation scoring module. We evaluate our model on four standard relation extraction benchmarks: CoNLL04, DocRED, FewRel, and CrossRE, and demonstrate competitive performance against both specialized relation extraction models and large language models, while maintaining the computational efficiency characteristic of the GLiNER family. The model is released as an open-source Python package with a simple inference API that allows users to specify arbitrary entity and relation type labels at inference time and obtain both entities and relation triplets in a single call. All models and code are publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2605.10108
PDF
-
TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
2026-05-11 03:32:55Bihui Yu, Caijun Jia, Jing Chi, Xiaohan Liu, Yining Wang, He Bai, Yuchen Liu, Jingxuan Wei, Junnan ZhuAbstract
Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, and multi-step reasoning. Current tool-using agents usually expose the executed tool trajectory and the final answer, but they rarely specify which tool observation supports each generated claim. We call this missing claim-level dependency structure the provenance gap. The gap makes tool use hard to verify and hard to optimize, because useful evidence, redundant exploration, and unsupported reasoning are mixed in the same trajectory. We introduce TRACER, a framework for verifiable generative provenance in multimodal tool-using agents. Instead of adding citations after generation, TRACER generates each answer sentence together with a structured provenance record that identifies the supporting tool turn, evidence unit, and semantic support relation. Its relation space contains Quotation, Compression, and Inference, covering direct reuse, faithful condensation, and grounded derivation. TRACER verifies each record through schema checking, tool-turn alignment, source authenticity, and relation rationality, and then converts verified provenance into traceability constraints and provenance-derived local credit for reinforcement learning. We further construct TRACE-Bench, a benchmark for sentence-level provenance reconstruction from coarse multimodal tool trajectories. On TRACE-Bench, simply adding tools often introduces noise. With Qwen3-VL-8B, TRACER reaches 78.23% answer accuracy and 95.72% summary accuracy, outperforming the strongest closed-source tool-augmented baseline by 23.80 percentage points. Compared with tool-only supervised fine-tuning, it also reduces total test-set tool calls from 4949 to 3486. These results show that reliable multimodal tool reasoning depends on provenance-aware use of observations, not on more tool calls alone.
Abstract (translated)
URL
https://arxiv.org/abs/2605.09934
PDF
-
Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports
2026-05-10 09:29:33Yu Wang, Yingyun Li, Ying Qin, Haiyang QianAbstract
Clinical reports are often fragmented across healthcare institutions because privacy regulations and data silos limit direct information sharing. When patients seek care at a different hospital, they often carry paper or scanned reports from prior visits. This hinders EHR integration and longitudinal review, and downstream applications that depend on more complete patient records, such as patient management, follow-up care, real-world studies, and clinical-trial matching. Although OCR can digitize such reports, reliable extraction remains challenging because clinical documents are heterogeneous, OCR text is noisy, and many healthcare settings require low-cost on-premise deployment. We formulate this problem as canonical key-conditioned extractive question answering over OCR-derived clinical reports. Because the key fields are neither fixed nor known in advance, the key space is open. We maintain a canonical key inventory through iterative key mining, normalization, clustering, and lightweight human verification, and introduce key coverage as a metric to quantify inventory completeness. Using a 0.2B BERT-based model, experiments on real-world reports from more than 20 hospitals show performance improves monotonically with key coverage. The model achieves F1 scores of 0.839 and 0.893 under exact match and boundary-tolerant matching, respectively, once the Top-90 canonical keys are covered. These results show that key coverage is a dominant factor for end-to-end performance. At Top-90 coverage, our model outperforms a fine-tuned Qwen3-0.6B baseline under exact match. Although our annotated corpus is Chinese, the method relies on the language-agnostic key-value organization of semi-structured clinical reports and can be adapted to other settings given an appropriate canonical key inventory and alias mapping.
Abstract (translated)
URL
https://arxiv.org/abs/2605.09440
PDF
-
Monocular Biomechanical Tracking of Fingers with Inverse Kinematics to Foundation Models
2026-05-10 02:06:43R. James Cotton, Pouyan Firouzabadi, Wendy MurrayAbstract
Accurate hand and finger tracking from video has significant clinical applications for monitoring activities of daily living and measuring range of motion, yet monocular video approaches for obtaining hand biomechanics remain under-developed. We present a method that combines the SAM 3D Body foundation model with inverse kinematics optimization in a full-body biomechanical model to extract anatomically-constrained finger joint angles from single-view video. We port SAM 3D Body from PyTorch to JAX for integration with MuJoCo-MJX, enabling GPU-accelerated optimization, and develop a novel mapping between the Momentum Human Rig (MHR) outputs and biomechanical model markers. Validation against 8-camera multiview reconstruction on 4,590 frames from 7 participants performing a variety of hand poses and object manipulation tasks shows finger joint angle errors of approximately 10 degrees and hand position errors of approximately 6 mm, after Procrustes alignment. Results were consistent across camera viewpoints and robust to different methods for producing reference values from multiview video. This work extends monocular biomechanical analysis to detailed finger tracking, expanding access to quantitative characterization of hand movement from readily available video.
Abstract (translated)
URL
https://arxiv.org/abs/2605.09258
PDF
-
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
2026-05-09 15:10:26Kechen Fang, Yihua Qin, Chongyi Wang, Wenshuo Ma, Tianyu Yu, Yuan YaoAbstract
Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post-ViT compression. Global encoding produces massive token sequences, while post-ViT compression incurs the full quadratic attention cost of the ViT before any token reduction takes place. In this work, we revisit this convention along two dimensions: the encoding strategy and visual token compression. First, controlled experiments show that slice-based encoding outperforms global encoding across benchmarks, suggesting that preserving local details through sliced views can be more beneficial than applying global attention for fine-grained perception. Second, we introduce intra-ViT early compression, which reduces tokens in shallow ViT layers and substantially lowers visual-encoding FLOPs while preserving downstream performance. By integrating intra-ViT compression into the slice-based encoding framework, we present LLaVA-UHD v4, an efficient and compute-controllable visual encoding scheme tailored for high-resolution inputs. Across a diverse set of benchmarks covering document understanding, OCR, and general VQA, LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% while matching or even surpassing baseline performance. These results suggest that visual-encoding efficiency can be substantially improved without sacrificing downstream performance, providing a practical design direction for efficient high-resolution MLLMs. All model weights and code will be publicly released to support further research.
Abstract (translated)
URL
https://arxiv.org/abs/2605.08985
PDF
-
simpleposter: a simple baseline for product poster generation
2026-05-09 08:12:55Benlei Cui, Fangao Zeng, Weitao Jiang, Yuwen Zhai, Haiwen Hong, Longtao Huang, Hui Xue, Wenxiang Shang, Pipei HuangAbstract
Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise control over dense, multi-line text layouts. Prior methods typically adopt inpainting frameworks augmented with auxiliary modules such as ControlNet and OCR encoders. However, these approaches introduce architectural complexity and computational overhead while still suffering from text errors and subject extension artifacts. We present SimplePoster, a simple yet effective inpainting-based framework that achieves faithful subject preservation and accurate, position-controllable text rendering without external controllers. Our approach builds on two observations: (1) full-parameter fine-tuning of the base model effectively suppresses subject extension, outperforming ControlNet-based alternatives; and (2) a zero-cost character-level position encoding enables geometry-aware text generation without dedicated layout modules. Experiments show that SimplePoster achieves a $98.7\%$ subject preservation rate, compared to $55.2\%$ for SeedEdit 3.0 and $85.3\%$ for PosterMaker, while also improving text rendering accuracy. Code, models, benchmark and a part of training data will be available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2605.08784
PDF
-
Flow-OPD: On-Policy Distillation for Flow Matching Models
2026-05-08 17:50:15Zhen Fang, Wenxuan Huang, Yu Zeng, Yiming Zhao, Shuang Chen, Kaituo Feng, Yunlong Lin, Lin Chen, Zehui Chen, Shaosheng Cao, Feng ZhaoAbstract
Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing heterogeneous objectives, which together give rise to a 'seesaw effect' of competing metrics and pervasive reward hacking. Inspired by the success of On-Policy Distillation (OPD) in the large language model community, we propose Flow-OPD, the first unified post-training framework that integrates on-policy distillation into Flow Matching models. Flow-OPD adopts a two-stage alignment strategy: it first cultivates domain-specialized teacher models via single-reward GRPO fine-tuning, allowing each expert to reach its performance ceiling in isolation; it then establishes a robust initial policy through a Flow-based Cold-Start scheme and seamlessly consolidates heterogeneous expertise into a single student via a three-step orchestration of on-policy sampling, task-routing labeling, and dense trajectory-level supervision. We further introduce Manifold Anchor Regularization (MAR), which leverages a task-agnostic teacher to provide full-data supervision that anchors generation to a high-quality manifold, effectively mitigating the aesthetic degradation commonly observed in purely RL-driven alignment. Built upon Stable Diffusion 3.5 Medium, Flow-OPD raises the GenEval score from 63 to 92 and the OCR accuracy from 59 to 94, yielding an overall improvement of roughly 10 points over vanilla GRPO, while preserving image fidelity and human-preference alignment and exhibiting an emergent 'teacher-surpassing' effect. These results establish Flow-OPD as a scalable alignment paradigm for building generalist text-to-image models.
Abstract (translated)
URL
https://arxiv.org/abs/2605.08063
PDF
-
Towards multi-modal forgery representation learning for AI-generated video detection and localization
2026-05-08 04:35:50Dat Le, Khoa Nguyen, Xin Wang, Shu HuAbstract
Recent advances in generative AI have democratized video creation at scale. AI-generated videos, including partially manipulated clips across visual and audio channels, pose escalating risks of semantic distortion and misuse, which motivates the need for reliable detection tools. Most existing AI-generated video detectors remain limited by single- or partial-modality of data modeling and the lack of fine-grained temporal forgery localization. To address these challenges, our primary novelty introduces a core architecture that jointly integrates an LMM semantic branch with a spatio-temporal (ST) visual branch and a multi-scale partial-spoof (PS) audio branch. This multi-modal approach enables simultaneous detection and fine-grained temporal localization of partially manipulated AI-generated video forgeries. Extensive experiments show that this approach outperforms existing state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2605.07232
PDF
