87 66 282

Lee Junbum PRO

beomi

https://junbuml.ee

AI & ML interests

AI/ML GDE. Advancing Low-Resource Language Open Access LLM

Recent Activity

upvoted a paper 10 days ago

Soundwave: Less is More for Speech-Text Alignment in LLMs

upvoted a paper 12 days ago

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation

upvoted a paper 12 days ago

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding

View all activity

Organizations

beomi's activity

upvoted a paper 10 days ago

Soundwave: Less is More for Speech-Text Alignment in LLMs

Paper • 2502.12900 • Published 11 days ago • 76

upvoted 2 papers 12 days ago

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation

Paper • 2502.08690 • Published 17 days ago • 39

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding

Paper • 2502.08946 • Published 16 days ago • 182

upvoted 3 papers 15 days ago

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning

Paper • 2502.06533 • Published 19 days ago • 18

TransMLA: Multi-head Latent Attention Is All You Need

Paper • 2502.07864 • Published 17 days ago • 45

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

Paper • 2502.08910 • Published 16 days ago • 142

upvoted a paper 22 days ago

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning

Paper • 2502.03275 • Published 24 days ago • 14

upvoted a paper 23 days ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 24 days ago • 197

upvoted a paper 25 days ago

s1: Simple test-time scaling

Paper • 2501.19393 • Published 28 days ago • 107

upvoted an article 27 days ago

Article

Welcome to Inference Providers on the Hub 🔥

Jan 28

• 400

upvoted a paper 29 days ago

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Paper • 2501.18585 • Published 29 days ago • 56

upvoted a paper 30 days ago

Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate

Paper • 2501.17703 • Published about 1 month ago • 55

upvoted 3 papers about 1 month ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 335

Do generative video models learn physical principles from watching videos?

Paper • 2501.09038 • Published Jan 14 • 32

MiniMax-01: Scaling Foundation Models with Lightning Attention

Paper • 2501.08313 • Published Jan 14 • 274

upvoted a paper 3 months ago

Training Large Language Models to Reason in a Continuous Latent Space

Paper • 2412.06769 • Published Dec 9, 2024 • 78

upvoted 2 collections 3 months ago

EXAONE-3.5

Collection

EXAONE 3.5 language model series including instruction-tuned models of 2.4B, 7.8B, and 32B. • 10 items • Updated Dec 10, 2024 • 98

Llama 3.3 (All Versions)

Collection

Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions. • 3 items • Updated 2 days ago • 36

upvoted 2 papers 3 months ago

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 129

Free Process Rewards without Process Labels

Paper • 2412.01981 • Published Dec 2, 2024 • 32