arXiv subjects

Zhibo Yang

Publications and source records attributed to Zhibo Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models

Visually-situated text parsing (VsTP) has recently seen notable advancements, driven by the growing demand for automated document understanding and the emergence of large language models capable of processing document-based questions. While various methods have been proposed to tackle the complexities of VsTP, existing solutions often rely on task-specific architectures and objectives for individual tasks. This leads to modal isolation and complex workflows due to the diversified targets and heterogeneous schemas. In this paper, we introduce OmniParser V2, a universal model that unifies VsTP typical tasks, including text spotting, key information extraction, table recognition, and layout analysis, into a unified framework. Central to our approach is the proposed Structured-Points-of-Thought (SPOT) prompting schemas, which improves model performance across diverse scenarios by leveraging a unified encoder-decoder architecture, objective, and input\&output representation. SPOT eliminates the need for task-specific architectures and loss functions, significantly simplifying the processing pipeline. Our extensive evaluations across four tasks on eight different datasets show that OmniParser V2 achieves state-of-the-art or competitive results in VsTP. Additionally, we explore the integration of SPOT within a multimodal large language model structure, further enhancing visual text parsing capabilities on four tasks, thereby confirming the generality of SPOT prompting technique. The code is available at \href{https://github.com/AlibabaResearch/AdvancedLiterateMachinery}{AdvancedLiterateMachinery}.

cs.CV↗

arXiv2026

Triviality Corrected Endogenous Reward

Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that require either annotated data or powerful closed-source models. Inspired by recent work on unsupervised reinforcement learning for mathematical reasoning using confidence-based endogenous rewards, we investigate whether this principle can be adapted to open-ended writing tasks. We find that directly applying confidence rewards leads to Triviality Bias: the policy collapses toward high-probability outputs, reducing diversity and meaningful content. We propose TCER (Triviality Corrected Endogenous Reward), which addresses this bias by rewarding the relative information gain between a specialist policy and a generalist reference policy, modulated by a probability-dependent correction mechanism. Across multiple writing benchmarks and model architectures, TCER achieves consistent improvements without external supervision. Furthermore, TCER also transfers effectively to mathematical reasoning, validating the generality of our approach across different generation tasks.

cs.CL↗

arXiv2026

Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos

The transition from image to video understanding requires vision-language models (VLMs) to shift from recognizing static patterns to reasoning over temporal dynamics such as motion trajectories, speed changes, and state transitions. Yet current post-training methods fall short due to two critical limitations: (1) existing datasets often lack temporal-centricity, where answers can be inferred from isolated keyframes rather than requiring holistic temporal integration; and (2) training data generated by proprietary models contains systematic errors in fundamental temporal perception, such as confusing motion directions or misjudging speeds. We introduce SynRL, a post-training framework that teaches models temporal primitives, the fundamental building blocks of temporal understanding including direction, speed, and state tracking. Our key insight is that these abstract primitives, learned from programmatically generated synthetic videos, transfer effectively to real-world scenarios. We decompose temporal understanding into short-term perceptual primitives (speed, direction) and long-term cognitive primitives, constructing 7.7K CoT and 7K RL samples with ground-truth frame-level annotations through code-based video generation. Despite training on simple geometric shapes, SynRL achieves substantial improvements across 15 benchmarks spanning temporal grounding, complex reasoning, and general video understanding. Remarkably, our 7.7K synthetic CoT samples outperform Video-R1 with 165K real-world samples. We attribute this to fundamental temporal skills, such as tracking frame by frame changes and comparing velocity, that transfer effectively from abstract synthetic patterns to complex real-world scenarios. This establishes a new paradigm for video post-training: video temporal learning through carefully designed synthetic data provides a more cost efficient scaling path.

cs.CV↗

arXiv2026

EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation

Although the effectiveness of Large Language Models (LLMs) as judges (LLM-as-a-judge) has been validated, their performance remains limited in open-ended tasks, particularly in story evaluation. Accurate story evaluation is crucial not only for assisting human quality judgment but also for providing key signals to guide story generation. However, existing methods face a dilemma: prompt engineering for closed-source models suffers from poor adaptability, while fine-tuning approaches for open-source models lack the rigorous reasoning capabilities essential for story evaluation. To address this, we propose the Self-Evolving Pairwise Reasoning (EvolvR) framework. Grounded in pairwise comparison, the framework first self-synthesizes score-aligned Chain-of-Thought (CoT) data via a multi-persona strategy. To ensure data quality, these raw CoTs undergo a self-filtering process, utilizing multi-agents to guarantee their logical rigor and robustness. Finally, the evaluator trained on the refined data is deployed as a reward model to guide the story generation task. Experimental results demonstrate that our framework achieves state-of-the-art (SOTA) performance on three evaluation benchmarks including StoryER, HANNA and OpenMEVA. Furthermore, when served as a reward model, it significantly enhances the quality of generated stories, thereby fully validating the superiority of our self-evolving approach.

cs.CL↗

arXiv2026

From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning

The cold-start initialization stage plays a pivotal role in training Multimodal Large Reasoning Models (MLRMs), yet its mechanisms remain insufficiently understood. To analyze this stage, we introduce the Visual Attention Score (VAS), an attention-based metric that quantifies how much a model attends to visual tokens. We find that reasoning performance is strongly correlated with VAS (r=0.9616): models with higher VAS achieve substantially stronger multimodal reasoning. Surprisingly, multimodal cold-start fails to elevate VAS, resulting in attention distributions close to the base model, whereas text-only cold-start leads to a clear increase. We term this counter-intuitive phenomenon Lazy Attention Localization. To validate its causal role, we design training-free interventions that directly modulate attention allocation during inference, performance gains of 1$-$2% without any retraining. Building on these insights, we further propose Attention-Guided Visual Anchoring and Reflection (AVAR), a comprehensive cold-start framework that integrates visual-anchored data synthesis, attention-guided objectives, and visual-anchored reward shaping. Applied to Qwen2.5-VL-7B, AVAR achieves an average gain of 7.0% across 7 multimodal reasoning benchmarks. Ablation studies further confirm that each component of AVAR contributes step-wise to the overall gains. The code, data, and models are available at https://github.com/lrlbbzl/Qwen-AVAR.

cs.CV↗

arXiv2026

Tower of Babel in Cross-Cultural Communication: A Case Study of #Give Me a Chinese Name# Dialogues During the "TikTok Refugees'' Event

The sudden influx of "TikTok refugees'' into the Chinese platform RedNote in early 2025 created an unprecedented, large-scale online cross-cultural communication event between the West and East. Although prior HCI research has studied user behavior in social media, most work remains confined to monolingual or single-cultural contexts, leaving cross-linguistic and cultural dynamics underexplored. To address this gap, we focused on a particularly challenging cross-cultural encoding-decoding task that remains stubbornly beyond the reach of machine translation, i.e., foreign newcomers asking Chinese users for Chinese names, and examined how people collectively constructed a digital "Babel Tower'' through various information encoding strategies. We collected and analyzed over 70,000 comments from RedNote with a creative human-in-the-loop approach using large language models, deriving a systematic framework summarizing cross-cultural information encoding strategies, how they are combined and layered to complicate decoding, and how they relate to engagement metrics such as the number of likes.

cs.HC↗

arXiv2026

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

In this report, we introduce the Qwen3-VL-Embedding and Qwen3-VL-Reranker model series, the latest extensions of the Qwen family built on the Qwen3-VL foundation model. Together, they provide an end-to-end pipeline for high-precision multimodal search by mapping diverse modalities, including text, images, document images, and video, into a unified representation space. The Qwen3-VL-Embedding model employs a multi-stage training paradigm, progressing from large-scale contrastive pre-training to reranking model distillation, to generate semantically rich high-dimensional vectors. It supports Matryoshka Representation Learning, enabling flexible embedding dimensions, and handles inputs up to 32k tokens. Complementing this, Qwen3-VL-Reranker performs fine-grained relevance estimation for query-document pairs using a cross-encoder architecture with cross-attention mechanisms. Both model series inherit the multilingual capabilities of Qwen3-VL, supporting more than 30 languages, and are released in $\textbf{2B}$ and $\textbf{8B}$ parameter sizes to accommodate diverse deployment requirements. Empirical evaluations demonstrate that the Qwen3-VL-Embedding series achieves state-of-the-art results across diverse multimodal embedding evaluation benchmarks. Specifically, Qwen3-VL-Embedding-8B attains an overall score of $\textbf{77.8}$ on MMEB-V2, ranking first among all models (as of January 8, 2025). This report presents the architecture, training methodology, and practical capabilities of the series, demonstrating their effectiveness on various multimodal retrieval tasks, including image-text retrieval, visual question answering, and video-text matching.

cs.CL↗

arXiv2025

Rigidity for homogeneous solutions to the two-dimensional Euler equations in sector-type domains

We study the rigidity problem for $(-α)$-homogeneous solutions to the two-dimensional incompressible stationary Euler equations in sector-type domains $Ω_{a, b, θ_0}:= \{(r,θ): a 0$, and $b = +\infty$ or $b < +\infty$, we show that if a solution satisfies some homogeneity assumptions on the boundary of $Ω_{a, b, θ_0}$ and if the radial or angular component of the velocity does not vanish in $\overline{Ω_{a, b, θ_0}}\setminus\{\bm{0}\}$, then it must be homogeneous throughout $\overline{Ω_{a, b, θ_0}}\setminus\{\bm{0}\}$.

math.AP↗

arXiv2025

Qwen3-VL Technical Report

We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows.

cs.CV↗

arXiv2025

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Real-world clinical decision-making requires integrating heterogeneous data, including medical text, 2D images, 3D volumes, and videos, while existing AI systems fail to unify all these signals, limiting their utility. In this paper, we introduce Hulu-Med, a transparent, generalist medical Vision-Language Model (VLM) designed to unify language-only, 2D/3D vision-language, and video understanding within a single architecture. Hulu-Med is trained on a curated corpus of 16.7 million samples, comprising exclusively public or synthetic data, spanning 12 major anatomical systems and 14 medical imaging modalities. Hulu-Med employs a medical-aware token-reduction strategy that prunes redundant visual tokens, achieving up to a 55% reduction for 3D and video inputs, improving cross-modal efficiency, and enabling training at 7B-32B parameter scales in approximately 4,000-40,000 GPU hours. Across 30 public in-domain and out-of-domain medical benchmarks-covering text reasoning, visual question answering, report generation, multilingual dialogue, video understanding, and rare disease diagnosis-Hulu-Med surpasses existing open-source models on 27 of 30 benchmarks and outperforms proprietary systems such as GPT-4o on 16 benchmarks. Despite being a VLM, Hulu-Med outperforms GPT-4o and matches GPT-o1 on the text-only HealthBench. For the first time in the community, we provide a fully transparent, reproducible and cost-effective pipeline for holistic medical vision-language understanding by releasing our end-to-end data curation, training procedures, and model parameters. Code and models are available at https://github.com/ZJUI-AI4H/Hulu-Med.

cs.CV↗

arXiv2025

Layout-Aware Parsing Meets Efficient LLMs: A Unified, Scalable Framework for Resume Information Extraction and Evaluation

Automated resume information extraction is critical for scaling talent acquisition, yet its real-world deployment faces three major challenges: the extreme heterogeneity of resume layouts and content, the high cost and latency of large language models (LLMs), and the lack of standardized datasets and evaluation tools. In this work, we present a layout-aware and efficiency-optimized framework for automated extraction and evaluation that addresses all three challenges. Our system combines a fine-tuned layout parser to normalize diverse document formats, an inference-efficient LLM extractor based on parallel prompting and instruction tuning, and a robust two-stage automated evaluation framework supported by new benchmark datasets. Extensive experiments show that our framework significantly outperforms strong baselines in both accuracy and efficiency. In particular, we demonstrate that a fine-tuned compact 0.6B LLM achieves top-tier accuracy while significantly reducing inference latency and computational cost. The system is fully deployed in Alibaba's intelligent HR platform, supporting real-time applications across its business units.

cs.CL↗

arXiv2025

DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in document understanding. However, their reasoning processes remain largely black-box, making it difficult to ensure reliability and trustworthiness, especially in high-stakes domains such as legal, financial, and medical document analysis. Existing methods use fixed Chain-of-Thought (CoT) reasoning with supervised fine-tuning (SFT) but suffer from catastrophic forgetting, poor adaptability, and limited generalization across domain tasks. In this paper, we propose DocThinker, a rule-based Reinforcement Learning (RL) framework for dynamic inference-time reasoning. Instead of relying on static CoT templates, DocThinker autonomously refines reasoning strategies via policy learning, generating explainable intermediate results, including structured reasoning processes, rephrased questions, regions of interest (RoI) supporting the answer, and the final answer. By integrating multi-objective rule-based rewards and KL-constrained optimization, our method mitigates catastrophic forgetting and enhances both adaptability and transparency. Extensive experiments on multiple benchmarks demonstrate that DocThinker significantly improves generalization while producing more explainable and human-understandable reasoning steps. Our findings highlight RL as a powerful alternative for enhancing explainability and adaptability in MLLM-based document understanding. Code will be available at https://github.com/wenwenyu/DocThinker.

cs.CV↗

arXiv2025

Bias-preserving and error-detectable entangling operations in a superconducting dual-rail system

For useful quantum computation, error-corrected machines are required that can dramatically reduce the inevitable errors experienced by physical qubits. While significant progress has been made in approaching and exceeding the surface-code threshold in superconducting platforms, large gains in the logical error rate with increasing system size remain out of reach. This is due both to the large number of required physical qubits and the need to operate far below threshold. Importantly, by exploiting the biases and structure of the physical errors, this threshold can be raised. Erasure qubits achieve this by detecting certain errors at the hardware level. Dual-rail qubits encoded in superconducting cavities are a promising erasure qubit wherein the dominant error, photon loss, can be detected and converted to an erasure. In these approaches, the complete set of operations, including two qubit gates, must be high performance and preserve as much of the desirable hierarchy or bias in the errors as possible. Here, we design and realize a novel two-qubit gate for dual-rail erasure qubits based on superconducting microwave cavities. The gate is high-speed ($\sim$500 ns duration), and yields a residual gate infidelity after error detection below 0.1%. Moreover, we experimentally demonstrate that this gate largely preserves the favorable error structure of idling dual-rail qubits, making it ideal for error correction. We measure low erasure rates of $\sim$0.5% per gate, as well as low and asymmetric dephasing errors that occur at least three times more frequently on control qubits compared to target qubits. Bit-flip errors are practically nonexistent, bounded at the few parts per million level. This error asymmetry has not been well explored but is extremely useful in quantum error correction and flag-qubit contexts, where it can create a faster path to effective error-corrected systems.

quant-ph↗

arXiv2025

MAER-Nav: Bidirectional Motion Learning Through Mirror-Augmented Experience Replay for Robot Navigation

Deep Reinforcement Learning (DRL) based navigation methods have demonstrated promising results for mobile robots, but suffer from limited action flexibility in confined spaces. Conventional DRL approaches predominantly learn forward-motion policies, causing robots to become trapped in complex environments where backward maneuvers are necessary for recovery. This paper presents MAER-Nav (Mirror-Augmented Experience Replay for Robot Navigation), a novel framework that enables bidirectional motion learning without requiring explicit failure-driven hindsight experience replay or reward function modifications. Our approach integrates a mirror-augmented experience replay mechanism with curriculum learning to generate synthetic backward navigation experiences from successful trajectories. Experimental results in both simulation and real-world environments demonstrate that MAER-Nav significantly outperforms state-of-the-art methods while maintaining strong forward navigation capabilities. The framework effectively bridges the gap between the comprehensive action space utilization of traditional planning methods and the environmental adaptability of learning-based approaches, enabling robust navigation in scenarios where conventional DRL methods consistently fail.

cs.RO↗

arXiv2025

Generative Compositor for Few-Shot Visual Information Extraction

Visual Information Extraction (VIE), aiming at extracting structured information from visually rich document images, plays a pivotal role in document processing. Considering various layouts, semantic scopes, and languages, VIE encompasses an extensive range of types, potentially numbering in the thousands. However, many of these types suffer from a lack of training data, which poses significant challenges. In this paper, we propose a novel generative model, named Generative Compositor, to address the challenge of few-shot VIE. The Generative Compositor is a hybrid pointer-generator network that emulates the operations of a compositor by retrieving words from the source text and assembling them based on the provided prompts. Furthermore, three pre-training strategies are employed to enhance the model's perception of spatial context information. Besides, a prompt-aware resampler is specially designed to enable efficient matching by leveraging the entity-semantic prior contained in prompts. The introduction of the prompt-based retrieval mechanism and the pre-training strategies enable the model to acquire more effective spatial and semantic clues with limited training samples. Experiments demonstrate that the proposed method achieves highly competitive results in the full-sample training, while notably outperforms the baseline in the 1-shot, 5-shot, and 10-shot settings.

cs.CV↗

arXiv2025

Beyond Visibility Limits: A DRL-Based Navigation Strategy for Unexpected Obstacles

Distance-based reward mechanisms in deep reinforcement learning (DRL) navigation systems suffer from critical safety limitations in dynamic environments, frequently resulting in collisions when visibility is restricted. We propose DRL-NSUO, a novel navigation strategy for unexpected obstacles that leverages the rate of change in LiDAR data as a dynamic environmental perception element. Our approach incorporates a composite reward function with environmental change rate constraints and dynamically adjusted weights through curriculum learning, enabling robots to autonomously balance between path efficiency and safety maximization. We enhance sensitivity to nearby obstacles by implementing short-range feature preprocessing of LiDAR data. Experimental results demonstrate that this method significantly improves both robot and pedestrian safety in complex scenarios compared to traditional DRL-based methods. When evaluated on the BARN navigation dataset, our method achieved superior performance with success rates of 94.0% at 0.5 m/s and 91.0% at 1.0 m/s, outperforming conservative obstacle expansion strategies. These results validate DRL-NSUO's enhanced practicality and safety for human-robot collaborative environments, including intelligent logistics applications.

cs.RO↗

arXiv2025

Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation

This work focuses on enhancing the generalization performance of deep reinforcement learning-based robot navigation in unseen environments. We present a novel data augmentation approach called scenario augmentation, which enables robots to navigate effectively across diverse settings without altering the training scenario. The method operates by mapping the robot's observation into an imagined space, generating an imagined action based on this transformed observation, and then remapping this action back to the real action executed in simulation. Through scenario augmentation, we conduct extensive comparative experiments to investigate the underlying causes of suboptimal navigation behaviors in unseen environments. Our analysis indicates that limited training scenarios represent the primary factor behind these undesired behaviors. Experimental results confirm that scenario augmentation substantially enhances the generalization capabilities of deep reinforcement learning-based navigation systems. The improved navigation framework demonstrates exceptional performance by producing near-optimal trajectories with significantly reduced navigation time in real-world applications.

cs.RO↗

arXiv2025

Qwen2.5-VL Technical Report

We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.

cs.CV↗