Young-Jun Lee PRO

passing2961's activity

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

upvoted 2 papers 9 days ago

On-Policy Delta Distillation for Multilingual Math Reasoning

Paper • 2608.05802 • Published 11 days ago • 32

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published 11 days ago • 34

upvoted 4 papers 10 days ago

Weak-to-Strong On-Policy Distillation

Paper • 2607.26246 • Published 20 days ago • 56

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published 14 days ago • 172

K-EXAONE 2.0 Technical Report

Paper • 2608.04505 • Published 12 days ago • 25

NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap

Paper • 2608.04397 • Published 12 days ago • 23

upvoted 2 papers 15 days ago

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

Paper • 2607.27372 • Published 19 days ago • 19

AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis

Paper • 2607.28618 • Published 18 days ago • 302

upvoted a paper 19 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 21 days ago • 493

upvoted 2 papers 20 days ago

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

Paper • 2607.21653 • Published 26 days ago • 32

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Paper • 2607.22529 • Published 24 days ago • 48

liked a dataset 22 days ago

HuggingFaceCode/stack-v3-train

Preview • Updated 2 days ago • 244k • 344

upvoted a paper 23 days ago

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

Paper • 2607.20911 • Published 25 days ago • 26

liked a Space 26 days ago

Running

62

Don't Train the Model, Evolve the Harness

🌿

62

Evolving an agent's harness, not its model, on Harvey's LAB

upvoted 2 papers 27 days ago

DSWorld: A Data Science World Model for Efficient Autonomous Agents

Paper • 2607.15901 • Published about 1 month ago • 12

Recursive Harness Self-Improvement

Paper • 2607.15524 • Published about 1 month ago • 26

upvoted a paper about 1 month ago

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

Paper • 2607.14777 • Published Jul 16 • 106