조은서's picture

5 7

조은서

asherlo

AI & ML interests

Paper replication and lightweight experiments. Building practical tools.

Recent Activity

liked a dataset 1 day ago

surenreddy/object365

upvoted a paper 2 days ago

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

liked a model 3 days ago

mistralai/Mistral-7B-v0.1

View all activity

Organizations

None yet

upvoted a paper 2 days ago

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

Paper • 2605.27355 • Published 11 days ago • 7

upvoted a paper 6 days ago

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published 10 days ago • 419

upvoted a paper about 2 months ago

An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU

Paper • 2603.16428 • Published Mar 17 • 51

upvoted a paper 2 months ago

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Paper • 2603.25746 • Published Mar 26 • 155

upvoted a paper 3 months ago

SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

Paper • 2603.16859 • Published Mar 17 • 249