oh sehun

sehun's activity

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

upvoted 7 papers 1 day ago

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published 6 days ago • 82

MobileMoE: Scaling On-Device Mixture of Experts

Paper • 2605.27358 • Published 7 days ago • 13

YoCausal: How Far is Video Generation from World Model? A Causality Perspective

Paper • 2605.30346 • Published 5 days ago • 43

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Paper • 2605.30263 • Published 5 days ago • 52

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Paper • 2605.30161 • Published 5 days ago • 54

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published 5 days ago • 71

NeuROK: Generative 4D Neural Object Kinematics

Paper • 2605.30347 • Published 5 days ago • 8

upvoted a paper 3 days ago

LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents

Paper • 2605.29559 • Published 5 days ago • 12

upvoted 3 papers 4 days ago

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

Paper • 2605.28732 • Published 6 days ago • 38

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

Paper • 2605.28003 • Published 6 days ago • 48

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

Paper • 2605.27366 • Published 7 days ago • 24

liked a model 6 days ago

jedisct1/MiMo-V2.5-coder-Q2

Text Generation • 309B • Updated 7 days ago • 1.93k • 69

upvoted 5 papers 6 days ago

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

Paper • 2605.24830 • Published 9 days ago • 80

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

Paper • 2605.26895 • Published 7 days ago • 18

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

Paper • 2605.27365 • Published 7 days ago • 131

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

Paper • 2605.26114 • Published 8 days ago • 60

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

Paper • 2605.27367 • Published 7 days ago • 69

liked a Space 10 days ago

Running on Zero

Agents

21

Lens

🔍

21

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

liked a dataset 10 days ago

armand0e/qwen3.7-max-pi-traces

Traces • Updated 10 days ago • 47 • 6k • 63

upvoted a paper 10 days ago

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

Paper • 2605.16928 • Published 17 days ago • 93