Gyusik Seo

willsuh's activity

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

authored 2 papers about 15 hours ago

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs

Paper • 2606.30026 • Published Jun 29 • 6

Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents

Paper • 2610.07785 • Published 2 days ago • 4

upvoted a paper about 19 hours ago

Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents

Paper • 2610.07785 • Published 2 days ago • 4

updated a dataset about 22 hours ago

willsuh/attacca-dataset

Updated about 22 hours ago • 44

updated a model about 22 hours ago

willsuh/attacca

0.2B • Updated about 22 hours ago • 21

upvoted a paper 1 day ago

MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning

Paper • 2610.02824 • Published 6 days ago • 32

published a model 5 days ago

willsuh/attacca

0.2B • Updated about 22 hours ago • 21

published a dataset 5 days ago

willsuh/attacca-dataset

Updated about 22 hours ago • 44

upvoted a paper 8 days ago

Simplex Relaxation for Discrete Diffusion

Paper • 2608.10615 • Published Aug 11 • 7

upvoted 2 papers 3 months ago

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs

Paper • 2606.30026 • Published Jun 29 • 6

Confidence-Aware Tool Orchestration for Robust Video Understanding

Paper • 2606.26904 • Published Jun 25 • 12

upvoted a paper 7 months ago

Are Video Reasoning Models Ready to Go Outside?

Paper • 2603.10652 • Published Mar 11 • 8

upvoted a paper 8 months ago

Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math

Paper • 2602.06291 • Published Feb 6 • 24

upvoted a paper 12 months ago

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Paper • 2510.05684 • Published Oct 7, 2025 • 148