Young-Jun Lee PRO

passing2961's activity

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

upvoted a paper about 10 hours ago

Self-Improving Pretraining: using post-trained models to pretrain better models

Paper • 2601.21343 • Published 2 days ago • 6

upvoted 12 papers 1 day ago

Linear representations in language models can change dramatically over a conversation

Paper • 2601.20834 • Published 3 days ago • 19

CooperBench: Why Coding Agents Cannot be Your Teammates Yet

Paper • 2601.13295 • Published 12 days ago • 3

Self-Distillation Enables Continual Learning

Paper • 2601.19897 • Published 4 days ago • 19

Towards Pixel-Level VLM Perception via Simple Points Prediction

Paper • 2601.19228 • Published 4 days ago • 15

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

Paper • 2601.18631 • Published 5 days ago • 47

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

Paper • 2601.20614 • Published 3 days ago • 112

FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning

Paper • 2601.18150 • Published 5 days ago • 5

How AI Impacts Skill Formation

Paper • 2601.20245 • Published 3 days ago • 6

SERA: Soft-Verified Efficient Repository Agents

Paper • 2601.20789 • Published 3 days ago • 8

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published 3 days ago • 23

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning

Paper • 2601.20209 • Published 3 days ago • 21

Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

Paper • 2601.19325 • Published 4 days ago • 72

upvoted 2 papers 4 days ago

Agentic Very Long Video Understanding

Paper • 2601.18157 • Published 5 days ago • 16

SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback

Paper • 2601.18202 • Published 5 days ago • 8

upvoted 5 papers 5 days ago

LLM-in-Sandbox Elicits General Agentic Intelligence

Paper • 2601.16206 • Published 9 days ago • 82

EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

Paper • 2601.15876 • Published 9 days ago • 89

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

Paper • 2601.16746 • Published 8 days ago • 86

Endless Terminals: Scaling RL Environments for Terminal Agents

Paper • 2601.16443 • Published 8 days ago • 16

DSGym: A Holistic Framework for Evaluating and Training Data Science Agents

Paper • 2601.16344 • Published 9 days ago • 10