Yujin Kim

kimyuji's activity

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

upvoted a paper 6 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 8 days ago • 130

upvoted a paper 10 days ago

PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

Paper • 2608.30597 • Published 25 days ago • 27

upvoted 2 papers 15 days ago

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Paper • 2609.07108 • Published 18 days ago • 36

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published 17 days ago • 82

upvoted 2 papers 21 days ago

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Paper • 2609.00196 • Published 25 days ago • 37

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published 23 days ago • 79

upvoted a paper 29 days ago

Meta^n: Recursive Self-Improvement through Emergent Depth

Paper • 2608.24735 • Published about 1 month ago • 16

upvoted a paper 2 months ago

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Paper • 2607.01874 • Published Jul 2 • 22

upvoted 3 papers 3 months ago

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

Paper • 2607.04412 • Published Jul 5 • 36

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published Jun 27 • 43

ProCUA-SFT Technical Report

Paper • 2606.17321 • Published Jun 15 • 11

upvoted 3 papers 4 months ago

SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations

Paper • 2606.05563 • Published Jun 4 • 56

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Paper • 2605.18703 • Published May 18 • 50

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published May 28 • 79

upvoted a collection 6 months ago

Raon

Collection

10 items • Updated Jul 28 • 46

upvoted a paper 6 months ago

mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT

Paper • 2603.21606 • Published Mar 23 • 39

upvoted a paper 7 months ago

MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

Paper • 2602.17602 • Published Feb 19 • 56

upvoted 3 papers 8 months ago

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 99

Generative Visual Code Mobile World Models

Paper • 2602.01576 • Published Feb 2 • 42

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published Jan 30 • 113