Junyao Yang

TberiusJunyao's activity

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

authored 6 papers 2 days ago

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Paper • 2607.18722 • Published 4 days ago • 34

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published 11 days ago • 220

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

Paper • 2607.08964 • Published 16 days ago • 74

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution

Paper • 2601.15075 • Published Feb 5

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Paper • 2601.18491 • Published Jan 26 • 126

RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior

Paper • 2508.03140 • Published Aug 5, 2025

upvoted a paper 3 days ago

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Paper • 2607.18722 • Published 4 days ago • 34

upvoted a paper 9 days ago

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published 11 days ago • 220

upvoted a paper 12 days ago

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

Paper • 2607.08964 • Published 16 days ago • 74

upvoted a paper 16 days ago

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 26 days ago • 51

upvoted a paper about 1 month ago

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Paper • 2606.13473 • Published Jun 11 • 93

upvoted a paper about 2 months ago

TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL

Paper • 2606.01599 • Published Jun 1 • 17

liked a model 3 months ago

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated Jun 22 • 1.65M • • 5.31k

upvoted a paper 3 months ago

TEMPO: Scaling Test-time Training for Large Reasoning Models

Paper • 2604.19295 • Published Apr 21 • 35

upvoted a paper 4 months ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published Apr 8 • 329

liked a dataset 5 months ago

AI45Research/ATBench

Viewer • Updated May 13 • 1.5k • 2.4k • 39

liked 4 models 6 months ago

AI45Research/AgentDoG-FG-Llama3.1-8B

Text Classification • 8B • Updated Feb 6 • 6 • 9

AI45Research/AgentDoG-Llama3.1-8B

Text Classification • 8B • Updated Feb 6 • 6 • 11

AI45Research/AgentDoG-FG-Qwen2.5-7B

Text Classification • 8B • Updated Feb 6 • 17 • 8

AI45Research/AgentDoG-Qwen2.5-7B

Text Classification • 8B • Updated Apr 9 • 18 • 10