Wenkai Yang

Keven16's activity

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

authored a paper 1 day ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published 5 days ago • 77

upvoted a paper 4 days ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published 5 days ago • 77

authored a paper about 1 month ago

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

Paper • 2603.14465 • Published Mar 15 • 23

updated a dataset about 1 month ago

Keven16/OPSD-Example-Data

Viewer • Updated Mar 18 • 49.1k • 78

published a dataset about 1 month ago

Keven16/OPSD-Example-Data

Viewer • Updated Mar 18 • 49.1k • 78

upvoted a paper about 1 month ago

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

Paper • 2603.14465 • Published Mar 15 • 23

updated 2 models about 1 month ago

Keven16/Qwen3-4B-Non-Thinking-RL-Code-Step300

4B • Updated Mar 16 • 343

Keven16/Qwen3-4B-Non-Thinking-RL-Math-Step500

4B • Updated Mar 16 • 2.72k

published 2 models about 1 month ago

Keven16/Qwen3-4B-Non-Thinking-RL-Code-Step300

4B • Updated Mar 16 • 343

Keven16/Qwen3-4B-Non-Thinking-RL-Math-Step500

4B • Updated Mar 16 • 2.72k

liked a dataset about 1 month ago

LulaCola/AgentProcessBench

Viewer • Updated Mar 18 • 1k • 387 • 14

authored 2 papers 2 months ago

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Paper • 2602.12125 • Published Feb 12 • 62

Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning

Paper • 2506.07851 • Published Jun 9, 2025

updated a dataset 2 months ago

Keven16/G-OPD-Training-Data

Viewer • Updated Feb 17 • 134k • 491

published a dataset 2 months ago

Keven16/G-OPD-Training-Data

Viewer • Updated Feb 17 • 134k • 491

upvoted a paper 2 months ago

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Paper • 2602.12125 • Published Feb 12 • 62

submitted a paper to Daily Papers 2 months ago

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Paper • 2602.12125 • Published Feb 12 • 62

upvoted 2 papers 2 months ago

Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning

Paper • 2602.09439 • Published Feb 10 • 13

AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research

Paper • 2602.06540 • Published Feb 6 • 21

upvoted a paper 3 months ago

DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution

Paper • 2601.13761 • Published Jan 20 • 16