Oh Sua

ohsua1986

7 1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

upvoted a paper 1 day ago

Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation

upvoted a paper 1 day ago

LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models

View all activity

Organizations

None yet

upvoted 3 papers 1 day ago

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

Paper • 2610.01780 • Published 6 days ago • 269

Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation

Paper • 2610.02788 • Published 5 days ago • 17

LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models

Paper • 2609.39071 • Published 7 days ago • 55

upvoted 4 papers 2 days ago

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 6 days ago • 45

CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning

Paper • 2609.36820 • Published 8 days ago • 39

Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation

Paper • 2610.01092 • Published 6 days ago • 33

Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts

Paper • 2610.00314 • Published 8 days ago • 101

liked a dataset 2 days ago

XiaomiMiMo/MiMo-V2.6-RL-oss

Viewer • Updated 11 days ago • 7.78k • 87.5k • 843