Yuhang Zang

yuhangzang's activity

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

authored a paper 2 days ago

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Paper • 2506.04997 • Published 4 days ago

upvoted a paper 3 days ago

Video World Models with Long-term Spatial Memory

Paper • 2506.05284 • Published 3 days ago • 42

liked a model 6 days ago

valpy/prompt-classification

Text Classification • Updated Apr 18, 2024 • 119 • 8

liked a dataset 6 days ago

launch/ExpertLongBench

Preview • Updated about 22 hours ago • 161 • 4

liked a model 10 days ago

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

Text Generation • Updated 11 days ago • 166k • • 707

liked a model 17 days ago

lightonai/Reason-ModernColBERT

Sentence Similarity • Updated 4 days ago • 2.52k • 180

upvoted a collection 17 days ago

VideoRoPE: What Makes for Good Video Rotary Position Embeddi

Collection

A storage repo for VideoRoPE. • 5 items • Updated Apr 24 • 3

liked a dataset 17 days ago

THU-KEG/AgentIF

Updated 24 days ago • 131 • 4

authored 2 papers 19 days ago

Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning

Paper • 2505.14677 • Published 19 days ago • 15

Visual Agentic Reinforcement Fine-Tuning

Paper • 2505.14246 • Published 20 days ago • 31

upvoted an article 19 days ago

view article

Article

Introducing Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training

By •

23 days ago

• 5

upvoted a paper 19 days ago

Visual Agentic Reinforcement Fine-Tuning

Paper • 2505.14246 • Published 20 days ago • 31

New activity in internlm/internlm-xcomposer2d5-7b-reward 20 days ago

Update README.md

#5 opened 20 days ago by

yuhangzang

liked a dataset 21 days ago

ByteDance/WildDoc

Viewer • Updated 21 days ago • 35.8k • 1.02k • 21

upvoted 2 papers 21 days ago

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

Paper • 2406.13542 • Published Jun 19, 2024 • 17

WorldPM: Scaling Human Preference Modeling

Paper • 2505.10527 • Published 24 days ago • 33

liked a dataset 25 days ago

Rapidata/Hidream_t2i_human_preference

Viewer • Updated 27 days ago • 13k • 608 • 18

liked 2 datasets about 1 month ago

openbmb/Ultra-FineWeb

Viewer • Updated 3 days ago • 1.29B • 32.2k • 152

tokyotech-llm/swallow-code

Viewer • Updated 18 days ago • 129M • 6.97k • 43

authored a paper about 1 month ago

Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning

Paper • 2505.03318 • Published May 6 • 92