Zhibo Yang

Chengxi Liao, Tao Xu, Zulong Chen et al.

Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spider, BIRD, and Spider~2.0 evaluate schema generalization, large-scale databases, and realistic workflows, but largely overlook enterprise scenarios where SQL generation depends on private business knowledge, such as internal metrics, reporting conventions, and organizational rules. We introduce EntSQL, an enterprise-oriented Text-to-SQL benchmark for evaluating long-context grounding over proprietary business documents. EntSQL contains 1,066 aligned Chinese-English semantic examples across five business domains, with most examples requiring domain knowledge beyond the question and schema and involving complex SQL structures. On English inputs, the best evaluated system reaches only 15.9\% when long-form documents are provided, highlighting the difficulty of grounding SQL generation in enterprise knowledge.

Zhibo Yang, Sounak Mondal, Seoyoung Ahn et al.

Most models of visual attention aim at predicting either top-down or bottom-up control, as studied using different visual search and free-viewing tasks. In this paper we propose the Human Attention Transformer (HAT), a single model that predicts both forms of attention control. HAT uses a novel transformer-based architecture and a simplified foveated retina that collectively create a spatio-temporal awareness akin to the dynamic visual working memory of humans. HAT not only establishes a new state-of-the-art in predicting the scanpath of fixations made during target-present and target-absent visual search and ``taskless'' free viewing, but also makes human gaze behavior interpretable. Unlike previous methods that rely on a coarse grid of fixation cells and experience information loss due to fixation discretization, HAT features a sequential dense prediction architecture and outputs a dense heatmap for each fixation, thus avoiding discretizing fixations. HAT sets a new standard in computational attention, which emphasizes effectiveness, generality, and interpretability. HAT's demonstrated scope and applicability will likely inspire the development of new attention models that can better predict human behavior in various attention-demanding scenarios. Code is available at https://github.com/cvlab-stonybrook/HAT.

Zhibo Yang, Rujiao Long, Pengfei Wang et al.

Recently, Visual Information Extraction (VIE) has been becoming increasingly important in both the academia and industry, due to the wide range of real-world applications. Previously, numerous works have been proposed to tackle this problem. However, the benchmarks used to assess these methods are relatively plain, i.e., scenarios with real-world complexity are not fully represented in these benchmarks. As the first contribution of this work, we curate and release a new dataset for VIE, in which the document images are much more challenging in that they are taken from real applications, and difficulties such as blur, partial occlusion, and printing shift are quite common. All these factors may lead to failures in information extraction. Therefore, as the second contribution, we explore an alternative approach to precisely and robustly extract key information from document images under such tough conditions. Specifically, in contrast to previous methods, which usually either incorporate visual information into a multi-modal architecture or train text spotting and information extraction in an end-to-end fashion, we explicitly model entities as semantic points, i.e., center points of entities are enriched with semantic information describing the attributes and relationships of different entities, which could largely benefit entity labeling and linking. Extensive experiments on standard benchmarks in this field as well as the proposed dataset demonstrate that the proposed method can achieve significantly enhanced performance on entity labeling and linking, compared with previous state-of-the-art models. Dataset is available at https://www.modelscope.cn/datasets/damo/SIBR/summary.

Sounak Mondal, Zhibo Yang, Seoyoung Ahn et al.

Predicting human gaze is important in Human-Computer Interaction (HCI). However, to practically serve HCI applications, gaze prediction models must be scalable, fast, and accurate in their spatial and temporal gaze predictions. Recent scanpath prediction models focus on goal-directed attention (search). Such models are limited in their application due to a common approach relying on trained target detectors for all possible objects, and the availability of human gaze data for their training (both not scalable). In response, we pose a new task called ZeroGaze, a new variant of zero-shot learning where gaze is predicted for never-before-searched objects, and we develop a novel model, Gazeformer, to solve the ZeroGaze problem. In contrast to existing methods using object detector modules, Gazeformer encodes the target using a natural language model, thus leveraging semantic similarities in scanpath prediction. We use a transformer-based encoder-decoder architecture because transformers are particularly useful for generating contextual representations. Gazeformer surpasses other models by a large margin on the ZeroGaze setting. It also outperforms existing target-detection models on standard gaze prediction for both target-present and target-absent search tasks. In addition to its improved performance, Gazeformer is more than five times faster than the state-of-the-art target-present visual search model.

Zhibo Yang, Sounak Mondal, Seoyoung Ahn et al.

The prediction of human gaze behavior is important for building human-computer interactive systems that can anticipate a user's attention. Computer vision models have been developed to predict the fixations made by people as they search for target objects. But what about when the image has no target? Equally important is to know how people search when they cannot find a target, and when they would stop searching. In this paper, we propose the first data-driven computational model that addresses the search-termination problem and predicts the scanpath of search fixations made by people searching for targets that do not appear in images. We model visual search as an imitation learning problem and represent the internal knowledge that the viewer acquires through fixations using a novel state representation that we call Foveated Feature Maps (FFMs). FFMs integrate a simulated foveated retina into a pretrained ConvNet that produces an in-network feature pyramid, all with minimal computational overhead. Our method integrates FFMs as the state representation in inverse reinforcement learning. Experimentally, we improve the state of the art in predicting human target-absent search behavior on the COCO-Search18 dataset

Ruilin Luo, Chufan Shi, Yizhen Zhang et al.

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.

Zhibo Yang

Sparse causal attention is usually described by sequence locality: nearby tokens should remain easy to access, while distant tokens may be dropped to reduce cost. This paper studies a mismatch between sequence locality and attention-graph reachability. In fixed block causal attention, two adjacent tokens can be disconnected in the attention graph at every depth. We formalize this boundary artifact through structural dependency sets: if every attention layer uses the same fixed block causal mask and all remaining operations are positionwise, a target representation can depend only on tokens in its own block prefix. This yields an architecture-level boundary-copy separation for a constructed K-way boundary-copy distribution, with top-1 accuracy upper bound 1/K and expected cross-entropy lower bound log K. We then derive phase-conditioned coverage functions showing that reachability depends on both source-target distance and the target's offset within its block. These coverage laws predict when a sparse pattern should fail, when a repair can help, and why sliding-window attention and boundary repair are not interchangeable. Boundary Bridge Attention is treated as a constructive witness: it preserves the fixed block path and adds zero-additional-parameter auxiliary causal edges near block boundaries using shared projections. Controlled 1024-token experiments show that gains concentrate in coverage-aligned diagnostics. As secondary external-validity evidence, a fixed-checkpoint 8K-token Qwen2.5-7B probe shows the same coverage-incomparability pattern. The contribution is a theory-guided diagnostic framework for locality-reachability mismatch in block-sparse causal attention, together with phase-conditioned coverage analysis and a minimal constructive repair.

Yifan Ji, Zhipeng Xu, Zhenghao Liu et al.

Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images. To enable a comprehensive and systematic evaluation across realistic and diverse application scenarios, we introduce UNIKIE-BENCH, a unified benchmark designed to rigorously evaluate the KIE capabilities of LMMs. UNIKIE-BENCH consists of two complementary tracks: a constrained-category KIE track with scenario-predefined schemas that reflect practical application needs, and an open-category KIE track that extracts any key information that is explicitly present in the document. Experiments on 15 state-of-the-art LMMs reveal substantial performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios. These findings underscore persistent challenges in grounding accuracy and layout-aware reasoning for LMM-based KIE. All codes and datasets are available at https://github.com/NEUIR/UNIKIE-BENCH.

Sibo Song, Jianqiang Wan, Zhibo Yang et al.

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves cross-modal interaction between the two modalities: vision and language, since text is the written form of language. Concretely, we propose to learn contextualized, joint representations through vision-language pre-training, for the sake of enhancing the performance of scene text detectors. Towards this end, we devise a pre-training architecture with an image encoder, a text encoder and a cross-modal encoder, as well as three pretext tasks: image-text contrastive learning (ITC), masked language modeling (MLM) and word-in-image prediction (WIP). The pre-trained model is able to produce more informative representations with richer semantics, which could readily benefit existing scene text detectors (such as EAST and PSENet) in the down-stream text detection task. Extensive experiments on standard benchmarks demonstrate that the proposed paradigm can significantly improve the performance of various representative text detectors, outperforming previous pre-training approaches. The code and pre-trained models will be publicly released.

Jianyuan Deng, Zhibo Yang, Hehe Wang et al.

Artificial intelligence (AI) has been widely applied in drug discovery with a major task as molecular property prediction. Despite booming techniques in molecular representation learning, key elements underlying molecular property prediction remain largely unexplored, which impedes further advancements in this field. Herein, we conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets, a suite of opioids-related datasets and two additional activity datasets from the literature. To investigate the predictive power in low-data and high-data space, a series of descriptors datasets of varying sizes are also assembled to evaluate the models. In total, we have trained 62,820 models, including 50,220 models on fixed representations, 4,200 models on SMILES sequences and 8,400 models on molecular graphs. Based on extensive experimentation and rigorous comparison, we show that representation learning models exhibit limited performance in molecular property prediction in most datasets. Besides, multiple key elements underlying molecular property prediction can affect the evaluation results. Furthermore, we show that activity cliffs can significantly impact model prediction. Finally, we explore into potential causes why representation learning models can fail and show that dataset size is essential for representation learning models to excel.

Mingxin Li, Yanzhao Zhang, Dingkun Long et al.

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.

Peng Wang, Zhaohai Li, Jun Tang et al.

Reading text from images (either natural scenes or documents) has been a long-standing research topic for decades, due to the high technical challenge and wide application range. Previously, individual specialist models are developed to tackle the sub-tasks of text reading (e.g., scene text recognition, handwritten text recognition and mathematical expression recognition). However, such specialist models usually cannot effectively generalize across different sub-tasks. Recently, generalist models (such as GPT-4V), trained on tremendous data in a unified way, have shown enormous potential in reading text in various scenarios, but with the drawbacks of limited accuracy and low efficiency. In this work, we propose Platypus, a generalized specialist model for text reading. Specifically, Platypus combines the best of both worlds: being able to recognize text of various forms with a single unified architecture, while achieving excellent accuracy and high efficiency. To better exploit the advantage of Platypus, we also construct a text reading dataset (called Worms), the images of which are curated from previous datasets and partially re-labeled. Experiments on standard benchmarks demonstrate the effectiveness and superiority of the proposed Platypus model. Model and data will be made publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/Platypus.

Qiuyue Wang, Mingsheng Li, Jian Guan et al.

Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In this work, we study whether heterogeneous embodied decision-making problems can be unified within a single vision-language-action model. We present Qwen-VLA, a unified embodied foundation model that extends Qwen's vision-language modeling stack from perception, understanding, and reasoning to continuous action and trajectory generation through a DiT-based action decoder. Qwen-VLA is trained with a large-scale joint pretraining recipe over diverse data sources, including robotics manipulation trajectories, human egocentric demonstrations, synthetic simulation data, vision-and-language navigation data, trajectory-centric supervision, and auxiliary vision-language data. To support multiple robot platforms, we introduce embodiment-aware prompt conditioning, where robot-specific textual descriptions specify the current embodiment and control convention. We further cast manipulation, navigation, and trajectory prediction into a unified action-and-trajectory prediction framework, enabling transferable visual grounding, spatial reasoning, and continuous action generation across robot morphologies, task families, and environments. Experiments on manipulation, navigation, and trajectory-centric benchmarks show consistent multi-task performance and out-of-distribution generalization under variations in scene layout, background, lighting, object configuration, and robot embodiment. Qwen-VLA-Instruct achieves 97.9% on LIBERO, 73.7% on Simpler-WidowX, 86.1%/87.2% on RoboTwin-Easy/Hard, 69.0% OSR on R2R, 59.6% SR on RxR, 76.9% average OOD success in real-world ALOHA experiments, and 26.6% zero-shot success on DOMINO dynamic manipulation.

Sounak Mondal, Seoyoung Ahn, Zhibo Yang et al.

For computer systems to effectively interact with humans using spoken language, they need to understand how the words being generated affect the users' moment-by-moment attention. Our study focuses on the incremental prediction of attention as a person is seeing an image and hearing a referring expression defining the object in the scene that should be fixated by gaze. To predict the gaze scanpaths in this incremental object referral task, we developed the Attention in Referral Transformer model or ART, which predicts the human fixations spurred by each word in a referring expression. ART uses a multimodal transformer encoder to jointly learn gaze behavior and its underlying grounding tasks, and an autoregressive transformer decoder to predict, for each word, a variable number of fixations based on fixation history. To train ART, we created RefCOCO-Gaze, a large-scale dataset of 19,738 human gaze scanpaths, corresponding to 2,094 unique image-expression pairs, from 220 participants performing our referral task. In our quantitative and qualitative analyses, ART not only outperforms existing methods in scanpath prediction, but also appears to capture several human attention patterns, such as waiting, scanning, and verification.

Tongkun Guan, Zhibo Yang, Jianqiang Wan et al.

When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual deficiencies or reasoning limitations? Through systematic scaling analysis that independently scales perception and reasoning components, we uncover a critical insight: scaling perception consistently outperforms scaling reasoning. This reveals perception as the true lever limiting current STEM visual reasoning. Motivated by this insight, our work focuses on systematically enhancing the perception capabilities of MLLMs by establishing code as a powerful perceptual medium--executable code provides precise semantics that naturally align with the structured nature of STEM visuals. Specifically, we construct ICC-1M, a large-scale dataset comprising 1M Image-Caption-Code triplets that materializes this code-as-perception paradigm through two complementary approaches: (1) Code-Grounded Caption Generation treats executable code as ground truth for image captions, eliminating the hallucinations inherent in existing knowledge distillation methods; (2) STEM Image-to-Code Translation prompts models to generate reconstruction code, mitigating the ambiguity of natural language for perception enhancement. To validate this paradigm, we further introduce STEM2Code-Eval, a novel benchmark that directly evaluates visual perception in STEM domains. Unlike existing work relying on problem-solving accuracy as a proxy that only measures problem-relevant understanding, our benchmark requires comprehensive visual comprehension through executable code generation for image reconstruction, providing deterministic and verifiable assessment. Code is available at https://github.com/TongkunGuan/Qwen-CodePercept.

Denghao Ma, Qing Liu, Zulong Chen et al.

Document classification forms the backbone of modern enterprise content management, yet existing benchmarks remain trapped in oversimplified paradigms -- single domain settings with flat label structures -- that bear little resemblance to the hierarchical, multi-modal, and cross-domain nature of real-world business documents. This gap not only misrepresents practical complexity but also stifles progress toward industrially viable document intelligence. To bridge this gap, we construct the first Multi-level, Multi-domain, Multi-modal document classification Benchmark (MMM-Bench). MMM-Bench includes (1) a deeply hierarchical taxonomy spanning five levels that capture the authentic organizational logic of business documentation; and (2) 5,990 real-world multi-modal documents meticulously curated from 12 commercial domains in Alibaba. Each document is manually annotated with a complete hierarchical path by domain experts. We establish comprehensive baselines on MMM-Bench, which consists of open-weight models and API-based models. Through systematic experiments, we identify four fundamental challenges within MMM-Bench and propose corresponding insights. To provide a solid foundation for advancing research in multi-level, multi-domain document classification, we release all of the data and the evaluation toolkit of MMM-Bench at https://github.com/MMMDC-Bench/MMMDC-Bench.

Jianqiang Wan, Sibo Song, Wenwen Yu et al.

Recently, visually-situated text parsing (VsTP) has experienced notable advancements, driven by the increasing demand for automated document understanding and the emergence of Generative Large Language Models (LLMs) capable of processing document-based questions. Various methods have been proposed to address the challenging problem of VsTP. However, due to the diversified targets and heterogeneous schemas, previous works usually design task-specific architectures and objectives for individual tasks, which inadvertently leads to modal isolation and complex workflow. In this paper, we propose a unified paradigm for parsing visually-situated text across diverse scenarios. Specifically, we devise a universal model, called OmniParser, which can simultaneously handle three typical visually-situated text parsing tasks: text spotting, key information extraction, and table recognition. In OmniParser, all tasks share the unified encoder-decoder architecture, the unified objective: point-conditioned text generation, and the unified input & output representation: prompt & structured sequences. Extensive experiments demonstrate that the proposed OmniParser achieves state-of-the-art (SOTA) or highly competitive performances on 7 datasets for the three visually-situated text parsing tasks, despite its unified, concise design. The code is available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery.

Yuanzhi Zhu, Jiawei Liu, Feiyu Gao et al.

Recently, with the rapid advancements of generative models, the field of visual text generation has witnessed significant progress. However, it is still challenging to render high-quality text images in real-world scenarios, as three critical criteria should be satisfied: (1) Fidelity: the generated text images should be photo-realistic and the contents are expected to be the same as specified in the given conditions; (2) Reasonability: the regions and contents of the generated text should cohere with the scene; (3) Utility: the generated text images can facilitate related tasks (e.g., text detection and recognition). Upon investigation, we find that existing methods, either rendering-based or diffusion-based, can hardly meet all these aspects simultaneously, limiting their application range. Therefore, we propose in this paper a visual text generator (termed SceneVTG), which can produce high-quality text images in the wild. Following a two-stage paradigm, SceneVTG leverages a Multimodal Large Language Model to recommend reasonable text regions and contents across multiple scales and levels, which are used by a conditional diffusion model as conditions to generate text images. Extensive experiments demonstrate that the proposed SceneVTG significantly outperforms traditional rendering-based methods and recent diffusion-based methods in terms of fidelity and reasonability. Besides, the generated images provide superior utility for tasks involving text detection and text recognition. Code and datasets are available at AdvancedLiterateMachinery.

Zhipeng Xu, Junhao Ji, Zulong Chen et al.

Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capability in document literacy. However, their effectiveness in real-world applications remains underexplored, as existing benchmarks adopt task scopes misaligned with practical applications and assume homogeneous acquisition conditions. To address this gap, we introduce CC-OCR V2, a comprehensive and challenging OCR benchmark tailored to real-world document processing. CC-OCR V2 focuses on practical enterprise document processing tasks and incorporates hard and corner cases that are critical yet underrepresented in prior benchmarks, covering 5 major OCR-centric tracks: text recognition, document parsing, document grounding, key information extraction, and document question answering, comprising 7,093 high-difficulty samples. Extensive experiments on 14 advanced LMMs reveal that current models fall short of real-world application requirements. Even state-of-the-art LMMs exhibit substantial performance degradation across diverse tasks and scenarios. These findings reveal a significant gap between performance on current benchmarks and effectiveness in real-world applications. We release the full dataset and evaluation toolkit at https://github.com/eioss/CC-OCR-V2.

Bangbang Zhou, Hangdi Xing, Yifan Chen et al.

Document parsing converts visually rich documents into machine-readable structured representations, forming a crucial foundation for information systems. Although many benchmarks have been proposed for document parsing, they remain inadequate for realistic scenarios. Existing benchmarks either focus on specific tasks or assess only single-page, text-centric settings, making them insufficient for practical multi-page parsing. Moreover, they lack fine-grained evaluation of semantic continuity, hierarchical structure recovery, and visual content preservation. To address these gaps, we propose MPDocBench-Parse, a benchmark for multi-page document parsing in real-world applications. It contains 433 manually annotated documents with 3,246 pages, covering 15 document types in English and Chinese, with diverse layout styles, and supports document-level end-to-end evaluation. We further design a comprehensive protocol for content fidelity and logical structure, covering text, table, and formula recognition, truncated text and table merging, figure extraction, reading order, and heading hierarchy recovery. Experiments show that, while existing models perform well on basic text extraction, they still suffer clear limitations in semantic continuity integration, visual content parsing, and hierarchical structure recovery. MPDocBench-Parse provides a unified foundation for advancing document parsing toward more realistic scenarios.

Humen Zhong, Zhibo Yang, Zhaohai Li et al.

Text recognition is an inherent integration of vision and language, encompassing the visual texture in stroke patterns and the semantic context among the character sequences. Towards advanced text recognition, there are three key challenges: (1) an encoder capable of representing the visual and semantic distributions; (2) a decoder that ensures the alignment between vision and semantics; and (3) consistency in the framework during pre-training, if it exists, and fine-tuning. Inspired by masked autoencoding, a successful pre-training strategy in both vision and language, we propose an innovative scene text recognition approach, named VL-Reader. The novelty of the VL-Reader lies in the pervasive interplay between vision and language throughout the entire process. Concretely, we first introduce a Masked Visual-Linguistic Reconstruction (MVLR) objective, which aims at simultaneously modeling visual and linguistic information. Then, we design a Masked Visual-Linguistic Decoder (MVLD) to further leverage masked vision-language context and achieve bi-modal feature interaction. The architecture of VL-Reader maintains consistency from pre-training to fine-tuning. In the pre-training stage, VL-Reader reconstructs both masked visual and text tokens, while in the fine-tuning stage, the network degrades to reconstruct all characters from an image without any masked regions. VL-reader achieves an average accuracy of 97.1% on six typical datasets, surpassing the SOTA by 1.1%. The improvement was even more significant on challenging datasets. The results demonstrate that vision and language reconstructor can serve as an effective scene text recognizer.

Wenwen Yu, Zhibo Yang, Jianqiang Wan et al.

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 text localization and recognition capabilities, thereby confirming the generality of SPOT prompting technique. The code is available at \href{https://github.com/AlibabaResearch/AdvancedLiterateMachinery}{AdvancedLiterateMachinery}.

Songtao Jiang, Sibo Song, Chenyi Zhou et al.

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.

Shuai Bai, Keqin Chen, Xuejing Liu et al. · pku

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.

Songtao Jiang, Yuan Wang, Sibo Song et al.

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.

Jinyu Long, Jetic Gū, Binhao Bai et al.

Speech enhancement is a demanding task in automated speech processing pipelines, focusing on separating clean speech from noisy channels. Transformer based models have recently bested RNN and CNN models in speech enhancement, however at the same time they are much more computationally expensive and require much more high quality training data, which is always hard to come by. In this paper, we present an improvement for speech enhancement models that maintains the expressiveness of self-attention while significantly reducing model complexity, which we have termed Spectrum Attention Fusion. We carefully construct a convolutional module to replace several self-attention layers in a speech Transformer, allowing the model to more efficiently fuse spectral features. Our proposed model is able to achieve comparable or better results against SOTA models but with significantly smaller parameters (0.58M) on the Voice Bank + DEMAND dataset.

Wenwen Yu, Zhibo Yang, Yuliang Liu et al.

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.

Xinda Wang, Zhengxu Hou, Yangshijie Zhang et al.

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.

Jianyuan Deng, Zhibo Yang, Iwao Ojima et al.

Artificial intelligence (AI) has been transforming the practice of drug discovery in the past decade. Various AI techniques have been used in a wide range of applications, such as virtual screening and drug design. In this survey, we first give an overview on drug discovery and discuss related applications, which can be reduced to two major tasks, i.e., molecular property prediction and molecule generation. We then discuss common data resources, molecule representations and benchmark platforms. Furthermore, to summarize the progress of AI in drug discovery, we present the relevant AI techniques including model architectures and learning paradigms in the papers surveyed. We expect that this survey will serve as a guide for researchers who are interested in working at the interface of artificial intelligence and drug discovery. We also provide a GitHub repository (https://github.com/dengjianyuan/Survey_AI_Drug_Discovery) with the collection of papers and codes, if applicable, as a learning resource, which is regularly updated.

Wenhai Wang, Xuebo Liu, Xiaozhong Ji et al.

Scene text spotting aims to detect and recognize the entire word or sentence with multiple characters in natural images. It is still challenging because ambiguity often occurs when the spacing between characters is large or the characters are evenly spread in multiple rows and columns, making many visually plausible groupings of the characters (e.g. "BERLIN" is incorrectly detected as "BERL" and "IN" in Fig. 1(c)). Unlike previous works that merely employed visual features for text detection, this work proposes a novel text spotter, named Ambiguity Eliminating Text Spotter (AE TextSpotter), which learns both visual and linguistic features to significantly reduce ambiguity in text detection. The proposed AE TextSpotter has three important benefits. 1) The linguistic representation is learned together with the visual representation in a framework. To our knowledge, it is the first time to improve text detection by using a language model. 2) A carefully designed language module is utilized to reduce the detection confidence of incorrect text lines, making them easily pruned in the detection stage. 3) Extensive experiments show that AE TextSpotter outperforms other state-of-the-art methods by a large margin. For example, we carefully select a validation set of extremely ambiguous samples from the IC19-ReCTS dataset, where our approach surpasses other methods by more than 4%. The code has been released at https://github.com/whai362/AE_TextSpotter. The image list and evaluation scripts of the validation set have been released at https://github.com/whai362/TDA-ReCTS.

Yongchao Xu, Yukang Wang, Wei Zhou et al.

Scene text detection is an important step of scene text reading system. The main challenges lie on significantly varied sizes and aspect ratios, arbitrary orientations and shapes. Driven by recent progress in deep learning, impressive performances have been achieved for multi-oriented text detection. Yet, the performance drops dramatically in detecting curved texts due to the limited text representation (e.g., horizontal bounding boxes, rotated rectangles, or quadrilaterals). It is of great interest to detect curved texts, which are actually very common in natural scenes. In this paper, we present a novel text detector named TextField for detecting irregular scene texts. Specifically, we learn a direction field pointing away from the nearest text boundary to each text point. This direction field is represented by an image of two-dimensional vectors and learned via a fully convolutional neural network. It encodes both binary text mask and direction information used to separate adjacent text instances, which is challenging for classical segmentation-based approaches. Based on the learned direction field, we apply a simple yet effective morphological-based post-processing to achieve the final detection. Experimental results show that the proposed TextField outperforms the state-of-the-art methods by a large margin (28% and 8%) on two curved text datasets: Total-Text and CTW1500, respectively, and also achieves very competitive performance on multi-oriented datasets: ICDAR 2015 and MSRA-TD500. Furthermore, TextField is robust in generalizing to unseen datasets. The code is available at https://github.com/YukangWang/TextField.

Yuan Yao, Qiushi Yang, Humen Zhong et al.

Open-world referring segmentation requires grounding unconstrained language expressions to precise pixel-level regions. Existing multimodal large language models (MLLMs) exhibit strong open-world visual grounding, but their outputs remain limited to sparse bounding-box coordinates and are insufficient for dense visual prediction. Recent MLLM-based segmentation methods either directly predict sparse contour coordinates, struggling to reconstruct continuous object boundaries, or rely on external segmentation foundation models such as the Segment Anything Model (SAM), introducing substantial architectural and deployment overhead. We present Qwen3-VL-Seg, a parameter-efficient framework that treats the MLLM-predicted box as a semantically grounded structural prior and decodes it into pixel-level referring segmentation. At its core, a lightweight box-guided mask decoder combines multi-scale spatial feature injection, spatial-semantic query construction, box-guided high-resolution pixel fusion, and iterative mask-aware query refinement, introducing only 17M parameters (about 0.4\% of the base model). For scalable open-world training, we construct SA1B-ORS, an SA-1B-derived dataset with two subsets: SA1B-CoRS (category-oriented samples) and SA1B-DeRS (descriptive, instance-specific samples). For evaluation, we curate ORS-Bench, a manually screened benchmark with in-distribution and out-of-distribution subsets covering diverse referring expression types. Extensive experiments on referring expression segmentation, visual grounding, and ORS-Bench show that Qwen3-VL-Seg performs strongly across closed-set and open-world settings, with clear advantages on language-intensive instructions and strong out-of-distribution generalization. Evaluations on general multimodal benchmarks further show that the model broadly preserves general-purpose multimodal competence after segmentation-oriented adaptation.

Xinda Wang, Zhengxu Hou, Yangshijie Zhang et al.

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.

Zhibo Yang, Jun Tang, Zhaohai Li et al.

Large Multimodal Models (LMMs) have demonstrated impressive performance in recognizing document images with natural language instructions. However, it remains unclear to what extent capabilities in literacy with rich structure and fine-grained visual challenges. The current landscape lacks a comprehensive benchmark to effectively measure the literate capabilities of LMMs. Existing benchmarks are often limited by narrow scenarios and specified tasks. To this end, we introduce CC-OCR, a comprehensive benchmark that possesses a diverse range of scenarios, tasks, and challenges. CC-OCR comprises four OCR-centric tracks: multi-scene text reading, multilingual text reading, document parsing, and key information extraction. It includes 39 subsets with 7,058 full annotated images, of which 41% are sourced from real applications, and released for the first time. We evaluate nine prominent LMMs and reveal both the strengths and weaknesses of these models, particularly in text grounding, multi-orientation, and hallucination of repetition. CC-OCR aims to comprehensively evaluate the capabilities of LMMs on OCR-centered tasks, facilitating continued progress in this crucial area.

Yuyi Zhang, Yuanzhi Zhu, Dezhi Peng et al.

Text recognition, especially for complex scripts like Chinese, faces unique challenges due to its intricate character structures and vast vocabulary. Traditional one-hot encoding methods struggle with the representation of hierarchical radicals, recognition of Out-Of-Vocabulary (OOV) characters, and on-device deployment due to their computational intensity. To address these challenges, we propose HierCode, a novel and lightweight codebook that exploits the innate hierarchical nature of Chinese characters. HierCode employs a multi-hot encoding strategy, leveraging hierarchical binary tree encoding and prototype learning to create distinctive, informative representations for each character. This approach not only facilitates zero-shot recognition of OOV characters by utilizing shared radicals and structures but also excels in line-level recognition tasks by computing similarity with visual features, a notable advantage over existing methods. Extensive experiments across diverse benchmarks, including handwritten, scene, document, web, and ancient text, have showcased HierCode's superiority for both conventional and zero-shot Chinese character or text recognition, exhibiting state-of-the-art performance with significantly fewer parameters and fast inference speed.

Rujiao Long, Hangdi Xing, Zhibo Yang et al.

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes or learning to directly generate the corresponding markup sequences from the table images. However, existing approaches either count on additional heuristic rules to recover the table structures, or face challenges in capturing long-range dependencies within tables, resulting in increased complexity. In this paper, we propose an alternative paradigm. We model TSR as a logical location regression problem and propose a new TSR framework called LORE, standing for LOgical location REgression network, which for the first time regresses logical location as well as spatial location of table cells in a unified network. Our proposed LORE is conceptually simpler, easier to train, and more accurate than other paradigms of TSR. Moreover, inspired by the persuasive success of pre-trained models on a number of computer vision and natural language processing tasks, we propose two pre-training tasks to enrich the spatial and logical representations at the feature level of LORE, resulting in an upgraded version called LORE++. The incorporation of pre-training in LORE++ has proven to enjoy significant advantages, leading to a substantial enhancement in terms of accuracy, generalization, and few-shot capability compared to its predecessor. Experiments on standard benchmarks against methods of previous paradigms demonstrate the superiority of LORE++, which highlights the potential and promising prospect of the logical location regression paradigm for TSR.

Shuai Bai, Yuxuan Cai, Ruizhe Chen et al.

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.

Fanwei Zhu, Jinke Yu, Zulong Chen et al.

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.

Zhibo Yang, Wei Hua, Sibo Song et al.

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.

Jiawei Liu, Yuanzhi Zhu, Feiyu Gao et al.

Generating visual text in natural scene images is a challenging task with many unsolved problems. Different from generating text on artificially designed images (such as posters, covers, cartoons, etc.), the text in natural scene images needs to meet the following four key criteria: (1) Fidelity: the generated text should appear as realistic as a photograph and be completely accurate, with no errors in any of the strokes. (2) Reasonability: the text should be generated on reasonable carrier areas (such as boards, signs, walls, etc.), and the generated text content should also be relevant to the scene. (3) Utility: the generated text can facilitate to the training of natural scene OCR (Optical Character Recognition) tasks. (4) Controllability: The attribute of the text (such as font and color) should be controllable as needed. In this paper, we propose a two stage method, SceneVTG++, which simultaneously satisfies the four aspects mentioned above. SceneVTG++ consists of a Text Layout and Content Generator (TLCG) and a Controllable Local Text Diffusion (CLTD). The former utilizes the world knowledge of multi modal large language models to find reasonable text areas and recommend text content according to the nature scene background images, while the latter generates controllable multilingual text based on the diffusion model. Through extensive experiments, we respectively verified the effectiveness of TLCG and CLTD, and demonstrated the state-of-the-art text generation performance of SceneVTG++. In addition, the generated images have superior utility in OCR tasks like text detection and text recognition. Codes and datasets will be available.

Rujiao Long, Pengfei Wang, Zhibo Yang et al.

End-to-end visual information extraction (VIE) aims at integrating the hierarchical subtasks of VIE, including text spotting, word grouping, and entity labeling, into a unified framework. Dealing with the gaps among the three subtasks plays a pivotal role in designing an effective VIE model. OCR-dependent methods heavily rely on offline OCR engines and inevitably suffer from OCR errors, while OCR-free methods, particularly those employing a black-box model, might produce outputs that lack interpretability or contain hallucinated content. Inspired by CenterNet, DeepSolo, and ESP, we propose HIP, which models entities as HIerarchical Points to better conform to the hierarchical nature of the end-to-end VIE task. Specifically, such hierarchical points can be flexibly encoded and subsequently decoded into desired text transcripts, centers of various regions, and categories of entities. Furthermore, we devise corresponding hierarchical pre-training strategies, categorized as image reconstruction, layout learning, and language enhancement, to reinforce the cross-modality representation of the hierarchical encoders. Quantitative experiments on public benchmarks demonstrate that HIP outperforms previous state-of-the-art methods, while qualitative results show its excellent interpretability.

Xiangwei Jiang, Rujiao Long, Nan Xue et al.

This paper addresses the problem of document image dewarping, which aims at eliminating the geometric distortion in document images for document digitization. Instead of designing a better neural network to approximate the optical flow fields between the inputs and outputs, we pursue the best readability by taking the text lines and the document boundaries into account from a constrained optimization perspective. Specifically, our proposed method first learns the boundary points and the pixels in the text lines and then follows the most simple observation that the boundaries and text lines in both horizontal and vertical directions should be kept after dewarping to introduce a novel grid regularization scheme. To obtain the final forward mapping for dewarping, we solve an optimization problem with our proposed grid regularization. The experiments comprehensively demonstrate that our proposed approach outperforms the prior arts by large margins in terms of readability (with the metrics of Character Errors Rate and the Edit Distance) while maintaining the best image quality on the publicly-available DocUNet benchmark.

Humen Zhong, Jun Tang, Wenhai Wang et al.

Recent approaches for end-to-end text spotting have achieved promising results. However, most of the current spotters were plagued by the inconsistency problem between text detection and recognition. In this work, we introduce and prove the existence of the inconsistency problem and analyze it from two aspects: (1) inconsistency of text recognition features between training and testing, and (2) inconsistency of optimization targets between text detection and recognition. To solve the aforementioned issues, we propose a differentiable Auto-Rectification Module (ARM) together with a new training strategy to enable propagating recognition loss back into detection branch, so that our detection branch can be jointly optimized by detection and recognition targets, which largely alleviates the inconsistency problem between text detection and recognition. Based on these designs, we present a simple yet robust end-to-end text spotting framework, termed Auto-Rectification Text Spotter (ARTS), to detect and recognize arbitrarily-shaped text in natural scenes. Extensive experiments demonstrate the superiority of our method. In particular, our ARTS-S achieves 77.1% end-to-end text spotting F-measure on Total-Text at a competitive speed of 10.5 FPS, which significantly outperforms previous methods in both accuracy and inference speed.

Rujiao Long, Wen Wang, Nan Xue et al.

This paper tackles the problem of table structure parsing (TSP) from images in the wild. In contrast to existing studies that mainly focus on parsing well-aligned tabular images with simple layouts from scanned PDF documents, we aim to establish a practical table structure parsing system for real-world scenarios where tabular input images are taken or scanned with severe deformation, bending or occlusions. For designing such a system, we propose an approach named Cycle-CenterNet on the top of CenterNet with a novel cycle-pairing module to simultaneously detect and group tabular cells into structured tables. In the cycle-pairing module, a new pairing loss function is proposed for the network training. Alongside with our Cycle-CenterNet, we also present a large-scale dataset, named Wired Table in the Wild (WTW), which includes well-annotated structure parsing of multiple style tables in several scenes like the photo, scanning files, web pages, \emph{etc.}. In experiments, we demonstrate that our Cycle-CenterNet consistently achieves the best accuracy of table structure parsing on the new WTW dataset by 24.6\% absolute improvement evaluated by the TEDS metric. A more comprehensive experimental analysis also validates the advantages of our proposed methods for the TSP task.

Wenhai Wang, Enze Xie, Xiang Li et al.

Scene text detection and recognition have been well explored in the past few years. Despite the progress, efficient and accurate end-to-end spotting of arbitrarily-shaped text remains challenging. In this work, we propose an end-to-end text spotting framework, termed PAN++, which can efficiently detect and recognize text of arbitrary shapes in natural scenes. PAN++ is based on the kernel representation that reformulates a text line as a text kernel (central region) surrounded by peripheral pixels. By systematically comparing with existing scene text representations, we show that our kernel representation can not only describe arbitrarily-shaped text but also well distinguish adjacent text. Moreover, as a pixel-based representation, the kernel representation can be predicted by a single fully convolutional network, which is very friendly to real-time applications. Taking the advantages of the kernel representation, we design a series of components as follows: 1) a computationally efficient feature enhancement network composed of stacked Feature Pyramid Enhancement Modules (FPEMs); 2) a lightweight detection head cooperating with Pixel Aggregation (PA); and 3) an efficient attention-based recognition head with Masked RoI. Benefiting from the kernel representation and the tailored components, our method achieves high inference speed while maintaining competitive accuracy. Extensive experiments show the superiority of our method. For example, the proposed PAN++ achieves an end-to-end text spotting F-measure of 64.9 at 29.2 FPS on the Total-Text dataset, which significantly outperforms the previous best method. Code will be available at: https://git.io/PAN.

Minghang He, Minghui Liao, Zhibo Yang et al.

Over the past few years, the field of scene text detection has progressed rapidly that modern text detectors are able to hunt text in various challenging scenarios. However, they might still fall short when handling text instances of extreme aspect ratios and varying scales. To tackle such difficulties, we propose in this paper a new algorithm for scene text detection, which puts forward a set of strategies to significantly improve the quality of text localization. Specifically, a Text Feature Alignment Module (TFAM) is proposed to dynamically adjust the receptive fields of features based on initial raw detections; a Position-Aware Non-Maximum Suppression (PA-NMS) module is devised to selectively concentrate on reliable raw detections and exclude unreliable ones; besides, we propose an Instance-wise IoU loss for balanced training to deal with text instances of different scales. An extensive ablation study demonstrates the effectiveness and superiority of the proposed strategies. The resulting text detection system, which integrates the proposed strategies with a leading scene text detector EAST, achieves state-of-the-art or competitive performance on various standard benchmarks for text detection while keeping a fast running speed.

Zhibo Yang, Muhammet Bastan, Xinliang Zhu et al.

Proxy-based metric learning losses are superior to pair-based losses due to their fast convergence and low training complexity. However, existing proxy-based losses focus on learning class-discriminative features while overlooking the commonalities shared across classes which are potentially useful in describing and matching samples. Moreover, they ignore the implicit hierarchy of categories in real-world datasets, where similar subordinate classes can be grouped together. In this paper, we present a framework that leverages this implicit hierarchy by imposing a hierarchical structure on the proxies and can be used with any existing proxy-based loss. This allows our model to capture both class-discriminative features and class-shared characteristics without breaking the implicit data hierarchy. We evaluate our method on five established image retrieval datasets such as In-Shop and SOP. Results demonstrate that our hierarchical proxy-based loss framework improves the performance of existing proxy-based losses, especially on large datasets which exhibit strong hierarchical structure.

Zhibo Yang, Lihan Huang, Yupei Chen et al.

Being able to predict human gaze behavior has obvious importance for behavioral vision and for computer vision applications. Most models have mainly focused on predicting free-viewing behavior using saliency maps, but these predictions do not generalize to goal-directed behavior, such as when a person searches for a visual target object. We propose the first inverse reinforcement learning (IRL) model to learn the internal reward function and policy used by humans during visual search. The viewer's internal belief states were modeled as dynamic contextual belief maps of object locations. These maps were learned by IRL and then used to predict behavioral scanpaths for multiple target categories. To train and evaluate our IRL model we created COCO-Search18, which is now the largest dataset of high-quality search fixations in existence. COCO-Search18 has 10 participants searching for each of 18 target-object categories in 6202 images, making about 300,000 goal-directed fixations. When trained and evaluated on COCO-Search18, the IRL model outperformed baseline models in predicting search fixation scanpaths, both in terms of similarity to human search behavior and search efficiency. Finally, reward maps recovered by the IRL model reveal distinctive target-dependent patterns of object prioritization, which we interpret as a learned object context.

Jianyuan Deng, Zhibo Yang, Yao Li et al.

Naloxone, an opioid antagonist, has been widely used to save lives from opioid overdose, a leading cause for death in the opioid epidemic. However, naloxone has short brain retention ability, which limits its therapeutic efficacy. Developing better opioid antagonists is critical in combating the opioid epidemic.Instead of exhaustively searching in a huge chemical space for better opioid antagonists, we adopt reinforcement learning which allows efficient gradient-based search towards molecules with desired physicochemical and/or biological properties. Specifically, we implement a deep reinforcement learning framework to discover potential lead compounds as better opioid antagonists with enhanced brain retention ability. A customized multi-objective reward function is designed to bias the generation towards molecules with both sufficient opioid antagonistic effect and enhanced brain retention ability. Thorough evaluation demonstrates that with this framework, we are able to identify valid, novel and feasible molecules with multiple desired properties, which has high potential in drug discovery.

Gregory J. Zelinsky, Yupei Chen, Seoyoung Ahn et al.

Understanding how goal states control behavior is a question ripe for interrogation by new methods from machine learning. These methods require large and labeled datasets to train models. To annotate a large-scale image dataset with observed search fixations, we collected 16,184 fixations from people searching for either microwaves or clocks in a dataset of 4,366 images (MS-COCO). We then used this behaviorally-annotated dataset and the machine learning method of Inverse-Reinforcement Learning (IRL) to learn target-specific reward functions and policies for these two target goals. Finally, we used these learned policies to predict the fixations of 60 new behavioral searchers (clock = 30, microwave = 30) in a disjoint test dataset of kitchen scenes depicting both a microwave and a clock (thus controlling for differences in low-level image contrast). We found that the IRL model predicted behavioral search efficiency and fixation-density maps using multiple metrics. Moreover, reward maps from the IRL model revealed target-specific patterns that suggest, not just attention guidance by target features, but also guidance by scene context (e.g., fixations along walls in the search of clocks). Using machine learning and the psychologically-meaningful principle of reward, it is possible to learn the visual features used in goal-directed attention control.