oh sehun

sehun's activity

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

upvoted a paper 1 day ago

Self-Evolving Search Index

Paper • 2609.19656 • Published 5 days ago • 52

liked a model 2 days ago

Meanblock/JEV-CPU

Zero-Shot Classification • Updated 3 days ago • 33

liked a model 3 days ago

wanvideo/wan-3-0-video

Text-to-Video • Updated 18 days ago • 10

upvoted 3 papers 3 days ago

ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models

Paper • 2609.18487 • Published 6 days ago • 47

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 5 days ago • 106

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 5 days ago • 77

liked a model 3 days ago

BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF

Text Generation • 27B • Updated 4 days ago • 25.9k • 49

liked a model 4 days ago

Cactus-Compute/needle3

Text Generation • Updated 3 days ago • 54.5k • 177

upvoted a paper 4 days ago

Disentangling Representation Evolution in Transformers through Directional Decomposition

Paper • 2609.15975 • Published 8 days ago • 9

upvoted 2 papers 5 days ago

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published 6 days ago • 75

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Paper • 2609.08418 • Published 14 days ago • 135

liked a model 5 days ago

mlabonne/LFM2.5-230M-Chess

Text Generation • 0.2B • Updated 6 days ago • 1.08k • 27

upvoted a paper 6 days ago

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

Paper • 2609.06107 • Published 17 days ago • 163

liked a model 6 days ago

Cierpliwy/krea2_lineart_edit

Text-to-Image • Updated 6 days ago • 1.31k • 24

upvoted 2 papers 6 days ago

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Paper • 2609.11977 • Published 18 days ago • 116

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

Paper • 2609.15973 • Published 8 days ago • 33

liked a dataset 6 days ago

Yootta/World-SimReady-Home

Updated 2 days ago • 19.1k • 67

liked a model 6 days ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Image-Text-to-Text • 177B • Updated 4 days ago • 68k • 227

upvoted a paper 6 days ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 8 days ago • 242

upvoted a paper 7 days ago

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

Paper • 2609.11682 • Published 12 days ago • 45