Dokyoon

leeloolee

Eruly

AI & ML interests

Recent Activity

reacted to BestWishYsh's post with 🔥 1 day ago

🚨 Hot Take: GPT-4o might NOT be a purely autoregressive model! 🚨 There’s a high chance it has a diffusion head. 🤯 If true, this could be a game-changer for AI architecture. What do you think? 🤔👇 Code: https://github.com/PicoTrex/GPT-ImgEval Paper: https://huggingface.co/papers/2504.02782

published a dataset 5 days ago

sionic-ai/reasoning

published a dataset 5 days ago

sionic-ai/reasoning-0.01-ko

View all activity

Organizations

leeloolee's activity

reacted to BestWishYsh's post with 🔥 1 day ago

Post

2456

🚨 Hot Take: GPT-4o might NOT be a purely autoregressive model! 🚨

There’s a high chance it has a diffusion head. 🤯 If true, this could be a game-changer for AI architecture. What do you think? 🤔👇

Code: https://github.com/PicoTrex/GPT-ImgEval
Paper: GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation (2504.02782)

published 2 datasets 5 days ago

sionic-ai/reasoning

Viewer • Updated Jul 30, 2024 • 30.4k • 1

sionic-ai/reasoning-0.01-ko

Viewer • Updated Aug 16, 2024 • 29.9k • 1 • 5

liked a Space 6 days ago

2.42k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

liked a model 16 days ago

BAAI/llm-embedder

Feature Extraction • Updated Nov 14, 2023 • 33.9k • • 120

upvoted a paper 16 days ago

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

Paper • 2503.16219 • Published 18 days ago • 46

liked a dataset 19 days ago

nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim

Updated 6 days ago • 30.8k • 105

upvoted a paper 25 days ago

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published 28 days ago • 41

liked 2 models about 1 month ago

chandar-lab/NeoBERT

Feature Extraction • Updated 13 days ago • 6.17k • 103

moonshotai/Moonlight-16B-A3B-Instruct

Text Generation • Updated Mar 3 • 3.49k • 138

upvoted a paper about 2 months ago

LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization

Paper • 2502.13922 • Published Feb 19 • 25

liked a model about 2 months ago

nomic-ai/nomic-embed-text-v2-moe

upvoted a paper about 2 months ago

s1: Simple test-time scaling

Paper • 2501.19393 • Published Jan 31 • 115

liked a model about 2 months ago

lerobot/pi0

Robotics • Updated Mar 6 • 13.7k • 205

upvoted a paper about 2 months ago

Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach

Paper • 2502.03639 • Published Feb 5 • 9

liked a dataset 2 months ago

ServiceNow-AI/R1-Distill-SFT

Viewer • Updated Feb 8 • 1.85M • 2.83k • 294

upvoted a paper 2 months ago

DiffuEraser: A Diffusion Model for Video Inpainting

Paper • 2501.10018 • Published Jan 17 • 14

published a model 3 months ago

leeloolee/gkd-model

Updated Jan 21

reacted to mitkox's post with 👀 3 months ago

Post

1427

Training a model to reason in the continuous latent space based on Meta's Coconut.
If it all works will apply it on the MiniCPM-o SVD-LR.
Endgame is a multimodal, adaptive, and efficient foundational on device AI model.

2 replies

liked a model 3 months ago

NovaSky-AI/Sky-T1-32B-Preview

Text Generation • Updated Jan 13 • 39.5k • 542