张康宁

zhangkangning's activity

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

upvoted 3 papers 20 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 28 days ago • 97

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published 28 days ago • 169

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published 27 days ago • 221

upvoted a paper 23 days ago

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 25 days ago • 102

upvoted a paper about 1 month ago

SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents

Paper • 2608.18852 • Published Aug 19 • 9

upvoted 4 papers about 2 months ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published Aug 7 • 110

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 103

Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

Paper • 2608.02276 • Published Aug 3 • 4

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

Paper • 2607.28590 • Published Jul 30 • 46

submitted a paper to Daily Papers about 2 months ago

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

Paper • 2607.28590 • Published Jul 30 • 46

upvoted a paper 2 months ago

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Paper • 2607.26784 • Published Jul 29 • 29

updated a model 2 months ago

zhangkangning/VAD_for_Qwen3.5-9b

Image-Text-to-Text • 9B • Updated Jul 28 • 26 • 1

published a model 2 months ago

zhangkangning/VAD_for_Qwen3.5-9b

Image-Text-to-Text • 9B • Updated Jul 28 • 26 • 1

updated a model 2 months ago

zhangkangning/VAD_for_Qwen3.5-4b

Image-Text-to-Text • 5B • Updated Jul 28 • 161 • 2

published a model 2 months ago

zhangkangning/VAD_for_Qwen3.5-4b

Image-Text-to-Text • 5B • Updated Jul 28 • 161 • 2

upvoted a paper 2 months ago

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published Jul 16 • 104

upvoted 3 papers 3 months ago

Latent Reasoning in LLMs as a Vocabulary-Space Superposition

Paper • 2510.15522 • Published Oct 17, 2025 • 7

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published May 22 • 264

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 393

updated a dataset 4 months ago

zhangkangning/mmskills

Viewer • Updated Jun 1 • 515 • 244 • 4