HongbangYuan

HongbangYuan's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 11 days ago

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Paper • 2606.26027 • Published 14 days ago • 18

upvoted a paper 25 days ago

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

Paper • 2606.12882 • Published 27 days ago • 13

upvoted a paper 26 days ago

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

Paper • 2606.12191 • Published 28 days ago • 70

upvoted 2 papers about 1 month ago

DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

Paper • 2605.28421 • Published May 27 • 48

Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration

Paper • 2605.28184 • Published May 27 • 6

upvoted a paper 2 months ago

DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios

Paper • 2604.25914 • Published Apr 28 • 42

upvoted a paper 4 months ago

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

Paper • 2603.02024 • Published Mar 2 • 47

upvoted 2 papers 5 months ago

FASA: Frequency-aware Sparse Attention

Paper • 2602.03152 • Published Feb 3 • 154

Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of Mind

Paper • 2601.15715 • Published Jan 22 • 14

upvoted 2 papers 7 months ago

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Paper • 2512.19673 • Published Dec 22, 2025 • 66

DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

Paper • 2512.04324 • Published Dec 3, 2025 • 160

upvoted a paper 8 months ago

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences

Paper • 2510.23451 • Published Oct 27, 2025 • 28

upvoted 2 papers about 1 year ago

Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis

Paper • 2506.04142 • Published Jun 4, 2025 • 28

MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos

Paper • 2506.04141 • Published Jun 4, 2025 • 31

upvoted a paper over 1 year ago

RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment

Paper • 2412.13746 • Published Dec 18, 2024 • 9