oh sehun

sehun's activity

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

upvoted 3 papers 1 day ago

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

Paper • 2605.28732 • Published 3 days ago • 36

ResearchMath-14K: Scaling Research-Level Mathematics via Agents

Paper • 2605.28003 • Published 3 days ago • 43

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Paper • 2605.27366 • Published 4 days ago • 18

liked a model 3 days ago

jedisct1/MiMo-V2.5-coder-Q2

Text Generation • 309B • Updated 4 days ago • 1.72k • 63

upvoted 5 papers 3 days ago

Macaron-A2UI: A Model for Generative UI in Personal Agents

Paper • 2605.24830 • Published 6 days ago • 77

Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models

Paper • 2605.26895 • Published 4 days ago • 15

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Paper • 2605.27365 • Published 4 days ago • 121

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

Paper • 2605.26114 • Published 5 days ago • 57

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

Paper • 2605.27367 • Published 4 days ago • 67

liked a Space 7 days ago

Running on Zero

Agents

20

Lens

🔍

20

Microsoft Lens & Lens-Turbo — 3.8B text-to-image

liked a dataset 7 days ago

armand0e/qwen3.7-max-pi-traces

Traces • Updated 7 days ago • 47 • 4.76k • 58

upvoted a paper 7 days ago

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

Paper • 2605.16928 • Published 14 days ago • 93

upvoted a paper 8 days ago

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

Paper • 2605.20258 • Published 12 days ago • 30

upvoted 2 papers 9 days ago

Aurora: Unified Video Editing with a Tool-Using Agent

Paper • 2605.18748 • Published 12 days ago • 29

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

Paper • 2605.19833 • Published 11 days ago • 131

upvoted an article 10 days ago

view article

Article

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

• 

allenai

•

11 days ago

• 19

upvoted a paper 10 days ago

Process Rewards with Learned Reliability

Paper • 2605.15529 • Published 15 days ago • 53

upvoted 3 papers 12 days ago

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

Paper • 2605.15824 • Published 15 days ago • 63

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

Paper • 2605.07721 • Published 22 days ago • 29

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

Paper • 2605.12496 • Published 18 days ago • 29