33 162 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 8 days ago

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

upvoted a paper 9 days ago

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

upvoted a paper 9 days ago

Skywork Open Reasoner 1 Technical Report

View all activity

Organizations

BK-Lee's activity

commented 3 papers about 1 month ago

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Paper • 2504.20157 • Published Apr 28 • 37 •

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Paper • 2504.20157 • Published Apr 28 • 37 •

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Paper • 2504.20157 • Published Apr 28 • 37 •

commented a paper 6 months ago

VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models

Paper • 2412.01822 • Published Dec 2, 2024 • 15 •

New activity in BK-Lee/Phantom-7B 7 months ago

Open-sourcing fine-tuning code

#1 opened 7 months ago by

aayush14

New activity in BK-Lee/Meteor-MLM 7 months ago

Add pipeline tag

#2 opened 7 months ago by

nielsr

commented a paper 8 months ago

Intriguing Properties of Large Language and Vision Models

Paper • 2410.04751 • Published Oct 7, 2024 • 16 •

New activity in BK-Lee/CoLLaVO-7B 8 months ago

Link model to paper, add model card

#1 opened 8 months ago by

nielsr

New activity in BK-Lee/MoAI-7B 8 months ago

Add link to paper, pipeline tag

#7 opened 8 months ago by

nielsr

commented a paper 8 months ago

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Paper • 2409.17146 • Published Sep 25, 2024 • 115 •

commented 2 papers 11 months ago

Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge

Paper • 2407.03958 • Published Jul 4, 2024 • 22 •

TokenPacker: Efficient Visual Projector for Multimodal LLM

Paper • 2407.02392 • Published Jul 2, 2024 • 24 •

commented a paper 12 months ago

TroL: Traversal of Layers for Large Language and Vision Models

Paper • 2406.12246 • Published Jun 18, 2024 • 36 •

New activity in BK-Lee/Meteor about 1 year ago

Add example input

#1 opened about 1 year ago by

merve

New activity in zero-gpu-explorers/README about 1 year ago

Error!

#63 opened about 1 year ago by

BK-Lee

New activity in BK-Lee/Meteor-Mamba about 1 year ago

question on computation cost

#3 opened about 1 year ago by

MicFizzy

commented a paper about 1 year ago

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models

Paper • 2405.15574 • Published May 24, 2024 • 56 •

New activity in BK-Lee/Meteor-Mamba about 1 year ago

thank you!

#2 opened about 1 year ago by

MicFizzy

commented a paper about 1 year ago

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models

Paper • 2405.15574 • Published May 24, 2024 • 56 •

New activity in BK-Lee/Meteor-MLM about 1 year ago

Add paper's link to link the model to the paper on Daily Papers page.

#1 opened about 1 year ago by

AdinaY