Byung-Kwan Lee

BK-Lee's activity

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

authored a paper about 10 hours ago

EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation

Paper • 2610.17560 • Published 4 days ago • 22

upvoted a paper about 15 hours ago

EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation

Paper • 2610.17560 • Published 4 days ago • 22

authored a paper 4 days ago

When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better

Paper • 2610.11291 • Published 9 days ago • 23

upvoted a paper 4 days ago

When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better

Paper • 2610.11291 • Published 9 days ago • 23

authored a paper 10 days ago

When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models

Paper • 2610.05719 • Published 12 days ago • 35

upvoted 2 papers 11 days ago

When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models

Paper • 2610.05719 • Published 12 days ago • 35

OSWorld-Pro: Process-based Evaluation for Computer Use Agents

Paper • 2609.24890 • Published 25 days ago • 28

upvoted a paper 13 days ago

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Paper • 2609.35259 • Published 19 days ago • 205

commented 3 papers 15 days ago

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 17 days ago • 119 •

5

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 17 days ago • 119 •

5

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 17 days ago • 119 •

5

authored a paper 15 days ago

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 17 days ago • 119

upvoted 2 papers 16 days ago

EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

Paper • 2609.40340 • Published 17 days ago • 112

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 17 days ago • 119

upvoted a paper 30 days ago

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Paper • 2609.18805 • Published about 1 month ago • 67

upvoted a paper about 2 months ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 162

upvoted 3 papers 2 months ago

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Paper • 2608.10299 • Published Aug 10 • 139

Weak-to-Strong On-Policy Distillation

Paper • 2607.26246 • Published Jul 28 • 59

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 104

upvoted a paper 3 months ago

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Paper • 2607.21653 • Published Jul 22 • 34