Bin Wang

ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning CVPR 2026 DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation AAAI 2026 Large Language Models Struggle with Unreasonability in Math Problems AAAI 2026 MM-ACT: Learn from Multimodal Parallel Generation to Act CVPR 2026 MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing ACL 2026 OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning CVPR 2026 RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection AAAI 2026 ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration CVPR 2026 TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration CVPR 2026 TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition CVPR 2026 UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition CVPR 2026 Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Sampling IJCAI 2025 Chimera: Improving Generalist Model with Domain-Specific Experts ICCV 2025 Function-to-Style Guidance of LLMs for Code Translation ICML 2025 GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training ICLR 2025 Global Eye: Breaking the “Fixed Thinking Pattern” during the Instruction Expansion Process ACL 2025 HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation ACL 2025 Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching CVPR 2025 LEGION: Learning to Ground and Explain for Synthetic Image Detection ICCV 2025 Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study NAACL 2025 OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation ICCV 2025 OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text ICLR 2025 OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations CVPR 2025 PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning COLING 2025 ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation NAACL 2025 SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing ACL 2025 Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology AAAI 2025 TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization ACL 2025 Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization IJCAI 2025 ToolACE: Winning the Points of LLM Function Calling ICLR 2025 A Comprehensive Evaluation of Quantization Strategies for Large Language Models ACL 2024 A New Dataset and Framework for Real-World Blurred Images Super-Resolution ECCV 2024 DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy ACL 2024 DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization NeurIPS 2024 Distribution-Aware Data Expansion with Diffusion Models NeurIPS 2024 EmpathyEar: An Open-source Avatar Multimodal Empathetic Chatbot ACL 2024 Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts CVPR 2024 InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD NeurIPS 2024 Mixture of Diverse Size Experts EMNLP 2024 Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents ACL 2024 MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding EMNLP 2024 OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation CVPR 2024 Parrot Captions Teach CLIP to Spot Text ECCV 2024 Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations ACL 2024 Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information Extraction ACL 2024 ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback EMNLP 2024 ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval COLING 2024 Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark ICLR 2024 Tree-Planner: Efficient Close-loop Task Planning with Large Language Models ICLR 2024 VIGC: Visual Instruction Generation and Correction AAAI 2024 W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation AAAI 2024 BERT-ERC: Fine-Tuning BERT Is Enough for Emotion Recognition in Conversation AAAI 2023 ChiPFormer: Transferable Chip Placement via Offline Decision Transformer ICML 2023 Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization NeurIPS 2023 EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought NeurIPS 2023 Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation EMNLP 2023 Exploring Better Text Image Translation with Multimodal Codebook ACL 2023 In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model EMNLP 2023 Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection ICLR 2023 Low-Confidence Samples Mining for Semi-supervised Object Detection IJCAI 2023 MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL ICML 2023 MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions ACL 2023 Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution ICCV 2023 The Xiaomi AI Lab’s Speech Translation Systems for IWSLT 2023 Offline Task, Simultaneous Task and Speech-to-Speech Task ACL 2023 V3Det: Vast Vocabulary Visual Detection Dataset ICCV 2023 BIT-Xiaomi’s System for AutoSimTrans 2022 NAACL 2022 C3KG: A Chinese Commonsense Conversation Knowledge Graph ACL 2022 DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning NeurIPS 2022 MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation ACL 2022 Offline-to-Online Co-Evolutional User Simulator and Dialogue System EMNLP 2022 Semi-supervised Object Detection with Adaptive Class-Rebalancing Self-Training AAAI 2022 Socially-Attentive Policy Optimization in Multi-Agent Self-Driving System CoRL 2022 The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022 ACL 2022 Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training COLING 2022 Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning AAAI 2021 Model-Based Reinforcement Learning via Imagination with Derived Memory NeurIPS 2021 Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension AAAI 2021 An Iterative Multi-Source Mutual Knowledge Transfer Framework for Machine Reading Comprehension IJCAI 2020 Focus-Constrained Attention Mechanism for CVAE-based Response Generation EMNLP 2020 Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism COLING 2020 Modeling Discourse Structure for Document-level Neural Machine Translation ACL 2020 Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets IJCAI 2020 Xiaomi’s Submissions for IWSLT 2020 Open Domain Translation Task ACL 2020 Adaptive Convolution for Multi-Relational Learning NAACL 2019 Low Shot Box Correction for Weakly Supervised Object Detection IJCAI 2019 Neural Collective Entity Linking Based on Recurrent Random Walk Network Learning IJCAI 2019 Implicit Non-linear Similarity Scoring for Recognizing Unseen Classes IJCAI 2018 Improving Knowledge Graph Embedding Using Simple Constraints ACL 2018 Where to Prune: Using LSTM to Guide End-to-end Pruning IJCAI 2018 Attentive Path Combination for Knowledge Graph Completion ACML 2017 Jointly Embedding Knowledge Graphs and Logical Rules EMNLP 2016 Knowledge Base Completion via Coupled Path Ranking ACL 2016 Multi-Granularity Chinese Word Embedding EMNLP 2016 Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks COLING 2016 Context-Dependent Knowledge Graph Embedding EMNLP 2015 Knowledge Base Completion Using Embeddings and Rules IJCAI 2015 Semantically Smooth Knowledge Graph Embedding ACL 2015 A Regularized Competition Model for Question Difficulty Estimation in Community Question Answering Services EMNLP 2014 Using Clustering to Improve Retrieval Evaluation without Relevance Judgments COLING 2010