oh sehun

sehun's activity

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

upvoted a paper 4 days ago

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Paper • 2605.16928 • Published 11 days ago • 90

upvoted a paper 5 days ago

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Paper • 2605.20258 • Published 9 days ago • 30

upvoted 2 papers 6 days ago

Aurora: Unified Video Editing with a Tool-Using Agent

Paper • 2605.18748 • Published 9 days ago • 29

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

Paper • 2605.19833 • Published 8 days ago • 129

upvoted an article 7 days ago

view article

Article

OlmoEarth v1.1: A more efficient family of Earth observation models

• 

allenai

•

8 days ago

• 19

upvoted a paper 7 days ago

Process Rewards with Learned Reliability

Paper • 2605.15529 • Published 12 days ago • 52

upvoted 7 papers 9 days ago

FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization

Paper • 2605.15824 • Published 12 days ago • 62

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models

Paper • 2605.07721 • Published 19 days ago • 29

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

Paper • 2605.12496 • Published 15 days ago • 28

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

Paper • 2605.15128 • Published 13 days ago • 60

Long Context Pre-Training with Lighthouse Attention

Paper • 2605.06554 • Published 20 days ago • 29

Nexus : An Agentic Framework for Time Series Forecasting

Paper • 2605.14389 • Published 13 days ago • 6

PhysBrain 1.0 Technical Report

Paper • 2605.15298 • Published 13 days ago • 142

upvoted 7 papers 13 days ago

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Paper • 2605.13779 • Published 14 days ago • 217

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

Paper • 2605.12178 • Published 15 days ago • 60

Key-Value Means

Paper • 2605.09877 • Published 16 days ago • 25

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published 14 days ago • 97

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published 14 days ago • 59

Teaching Language Models to Think in Code

Paper • 2605.07237 • Published 16 days ago • 30

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

Paper • 2605.10899 • Published 16 days ago • 75