DI YIN

DIYIN's activity

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

liked a dataset about 2 hours ago

llm-jp/RefinedVision

Viewer • Updated 2 days ago • 1.24k • 300 • 8

updated a collection 1 day ago

ContextPilot

Collection

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL • 3 items • Updated 1 day ago

liked a model 1 day ago

tencent/ContextPilot-14B

Text Generation • 15B • Updated 3 days ago • 407 • 16

liked 3 datasets 2 days ago

LivXue/Standard-Multimodal-Explanation

Updated Sep 18, 2025 • 40 • 2

taesiri/BlindLoop-Generations

Viewer • Updated 8 days ago • 1.7M • 21 • 2

lingshu-medical-mllm/lingshu_training_data_medical_domain

Viewer • Updated 3 days ago • 118M • 10 • 3

liked a dataset 3 days ago

tencent/ElephantBench

Viewer • Updated 3 days ago • 1.09k • 169 • 5

authored 5 papers 3 days ago

Latent Visual Cache for Video Reasoning

Paper • 2607.02607 • Published Jul 1 • 1

Thinking in Video: Can Video Generators Really Reason About the Real World?

Paper • 2607.17523 • Published Jul 20 • 1

PoLi-RL: A Point-to-List Reinforcement Learning Framework for Conditional Semantic Textual Similarity

Paper • 2510.04080 • Published Feb 28 • 2

Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge

Paper • 2608.28478 • Published 6 days ago • 17

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

Paper • 2608.28476 • Published 6 days ago • 26

upvoted 5 papers 3 days ago

Thinking in Video: Can Video Generators Really Reason About the Real World?

Paper • 2607.17523 • Published Jul 20 • 1

Latent Visual Cache for Video Reasoning

Paper • 2607.02607 • Published Jul 1 • 1

PoLi-RL: A Point-to-List Reinforcement Learning Framework for Conditional Semantic Textual Similarity

Paper • 2510.04080 • Published Feb 28 • 2

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

Paper • 2608.28476 • Published 6 days ago • 26

Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge

Paper • 2608.28478 • Published 6 days ago • 17

liked a dataset 6 days ago

RefVideo6M/RefVideo6M

Updated 3 days ago • 14k • 11