caiyuchen

caiyuchen's activity

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

authored a paper 2 days ago

Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors

Paper • 2609.34344 • Published 13 days ago • 4

submitted a paper to Daily Papers 2 days ago

Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors

Paper • 2609.34344 • Published 13 days ago • 4

updated a dataset 18 days ago

caiyuchen/OPV-Instruction

Viewer • Updated 18 days ago • 16.9k • 40

published a dataset 18 days ago

caiyuchen/OPV-Instruction

Viewer • Updated 18 days ago • 16.9k • 40

updated a dataset 18 days ago

caiyuchen/OPV-Code

Viewer • Updated 18 days ago • 27.2k • 55

published a dataset 18 days ago

caiyuchen/OPV-Code

Viewer • Updated 18 days ago • 27.2k • 55

updated a dataset 18 days ago

caiyuchen/OPV-Science

Viewer • Updated 18 days ago • 4.34k • 45

published a dataset 18 days ago

caiyuchen/OPV-Science

Viewer • Updated 18 days ago • 4.34k • 45

updated a dataset 18 days ago

caiyuchen/OPV-Math

Viewer • Updated 18 days ago • 71.2k • 53

published a dataset 18 days ago

caiyuchen/OPV-Math

Viewer • Updated 18 days ago • 71.2k • 53

updated 4 models 2 months ago

caiyuchen/Qwen2.5-7B-Dpsk-Instruct-Following-RL

8B • Updated Aug 5 • 6

caiyuchen/Qwen2.5-1.5B-Dpsk-Science-RL

2B • Updated Aug 5 • 5

caiyuchen/Qwen3-8B-Code-RL

8B • Updated Aug 5 • 7

caiyuchen/Qwen3-4B-Non-Thinking-Math-RL

4B • Updated Aug 5 • 10

published 4 models 2 months ago

caiyuchen/Qwen2.5-7B-Dpsk-Instruct-Following-RL

8B • Updated Aug 5 • 6

caiyuchen/Qwen2.5-1.5B-Dpsk-Science-RL

2B • Updated Aug 5 • 5

caiyuchen/Qwen3-8B-Code-RL

8B • Updated Aug 5 • 7

caiyuchen/Qwen3-4B-Non-Thinking-Math-RL

4B • Updated Aug 5 • 10

upvoted a paper 3 months ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published Jul 9 • 79

updated a dataset 3 months ago

caiyuchen/cryptoalpha-panel

Viewer • Updated Jul 5 • 1.81M • 54