Wenhao Yu

Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection ACL 2026 Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding ACL 2026 MotionEdit: Benchmarking and Learning Motion-Centric Image Editing CVPR 2026 ReCode: Updating Code API Knowledge with Reinforcement Learning AAAI 2026 SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs CVPR 2026 WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms EACL 2026 BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions ICLR 2025 Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots NAACL 2025 DocBench: A Benchmark for Evaluating LLM-based Document Reading Systems NAACL 2025 DSBench: How Far Are Data Science Agents from Becoming Data Science Experts? ICLR 2025 GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation AAAI 2025 Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining RSS 2025 LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing CoRL 2025 LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory ICLR 2025 OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization ACL 2025 PoseLLaVA: Pose Centric Multimodal LLM for Fine-Grained 3D Pose Manipulation AAAI 2025 RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph ICLR 2025 Retrieval-augmented GUI Agents with Generative Guidelines EMNLP 2025 STDArm: Transfer Visuomotor Policy From Static Data Training to Dynamic Robot Manipulation RSS 2025 Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling EMNLP 2025 Vision Language Models are In-Context Value Learners ICLR 2025 WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model EMNLP 2025 Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models EMNLP 2024 Dense X Retrieval: What Retrieval Granularity Should We Use? EMNLP 2024 Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination CoRL 2024 Gradient shaping for multi-constraint safe reinforcement learning L4DC 2024 Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning EMNLP 2024 Learning to Learn Faster from Human Feedback with Language Model Predictive Control RSS 2024 Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs CoRL 2024 OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning NeurIPS 2024 PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs ICML 2024 PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning ACL 2024 RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches ICLR 2024 Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations NAACL 2024 WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models ACL 2024 APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning ACL 2023 A Survey of Deep Learning for Mathematical Reasoning ACL 2023 A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods EACL 2023 Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models EMNLP 2023 CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller CoRL 2023 Constrained Decision Transformer for Offline Safe Reinforcement Learning ICML 2023 Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning NeurIPS 2023 Continuous Versatile Jumping Using Learned Action Residuals L4DC 2023 Generate rather than Retrieve: Large Language Models are Strong Context Generators ICLR 2023 GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation NeurIPS 2023 IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions EMNLP 2023 Language to Rewards for Robotic Skill Synthesis CoRL 2023 Large Language Models are Built-in Autoregressive Search Engines ACL 2023 Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation EMNLP 2023 Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization ICLR 2023 Pre-training Language Models for Comparative Reasoning EMNLP 2023 SayTap: Language to Quadrupedal Locomotion CoRL 2023 Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism CoRL 2023 A Unified Encoder-Decoder Framework with Entity Memory EMNLP 2022 Dict-BERT: Enhancing Language Model Pre-training with Dictionary ACL 2022 Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts ACL 2022 Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts NAACL 2022 Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering EMNLP 2022 Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering EMNLP 2022 KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering ACL 2022 Knowledge-Augmented Methods for Natural Language Processing ACL 2022 Learning from Counterfactual Links for Link Prediction ICML 2022 Learning Semantics-Aware Locomotion Skills from Human Demonstration CoRL 2022 Retrieval Augmentation for Commonsense Reasoning: A Unified Approach EMNLP 2022 Retrieval-augmented Generation across Heterogeneous Knowledge NAACL 2022 Task Compass: Scaling Multi-task Pre-training with Task Prefix EMNLP 2022 Injecting Entity Types into Entity-Guided Text Generation EMNLP 2021 Knowledge-Enriched Natural Language Generation EMNLP 2021 Sentence-Permuted Paragraph Generation EMNLP 2021 Technical Question Answering across Tasks and Domains NAACL 2021 Validating Label Consistency in NER Data Annotation EMNLP 2021 Visual-Locomotion: Learning to Walk on Complex Terrains with Vision CoRL 2021 A Technical Question Answering System with Transfer Learning EMNLP 2020 Crossing Variational Autoencoders for Answer Retrieval ACL 2020 Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER EMNLP 2020 Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method EMNLP 2019 Learning Novel Policies For Tasks ICML 2019 Policy Transfer with Strategy Optimization ICLR 2019 Preparing for the Unknown: Learning a Universal Policy with Online System Identification RSS 2017