32 110 11

Byung-Kwan Lee

BK-Lee

https://sites.google.com/view/byungkwanlee

AI & ML interests

Computer Vision, Machine Learning, Vision Language Models

Recent Activity

upvoted a paper 2 days ago

Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

upvoted a paper 6 days ago

Video-R1: Reinforcing Video Reasoning in MLLMs

upvoted a paper 8 days ago

Qwen2.5-Omni Technical Report

View all activity

Organizations

BK-Lee's activity

upvoted a paper 2 days ago

Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

Paper • 2504.00595 • Published 3 days ago • 26

upvoted a paper 6 days ago

Video-R1: Reinforcing Video Reasoning in MLLMs

Paper • 2503.21776 • Published 8 days ago • 74

upvoted a paper 8 days ago

Qwen2.5-Omni Technical Report

Paper • 2503.20215 • Published 9 days ago • 113

upvoted 2 papers 11 days ago

OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement

Paper • 2503.17352 • Published 14 days ago • 21

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't

Paper • 2503.16219 • Published 15 days ago • 46

upvoted 2 papers 14 days ago

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Paper • 2503.16419 • Published 15 days ago • 65

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Paper • 2503.15558 • Published 16 days ago • 44

upvoted 2 papers 15 days ago

Visual-RFT: Visual Reinforcement Fine-Tuning

Paper • 2503.01785 • Published Mar 3 • 74

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Paper • 2503.14476 • Published 17 days ago • 112

upvoted 2 papers 16 days ago

Transformers without Normalization

Paper • 2503.10622 • Published 22 days ago • 147

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Paper • 2503.07536 • Published 25 days ago • 83

upvoted a paper 18 days ago

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Paper • 2503.11647 • Published 21 days ago • 125

upvoted a paper 19 days ago

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Paper • 2503.10460 • Published 22 days ago • 27

upvoted a paper 25 days ago

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published 29 days ago • 89

upvoted a paper about 1 month ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published Feb 19 • 178

upvoted a paper about 2 months ago

Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models

Paper • 2501.14818 • Published Jan 20 • 4

upvoted 3 papers 2 months ago

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Paper • 2501.13629 • Published Jan 23 • 47

SRMT: Shared Memory for Multi-agent Lifelong Pathfinding

Paper • 2501.13200 • Published Jan 22 • 67

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Paper • 2501.12599 • Published Jan 22 • 112