Xu

Vettel-Xu's activity

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

liked 3 models about 1 month ago

Goodfire/DeepSeek-R1-SAE-l37

Updated Apr 21 • 16

Goodfire/Llama-3.3-70B-Instruct-SAE-l50

Updated Jan 11 • 130 • 35

PKU-Alignment/SAE-V

Updated May 24 • 2

upvoted 3 papers about 2 months ago

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Paper • 2510.07242 • Published Oct 8 • 30

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training

Paper • 2509.26625 • Published Sep 30 • 43

Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding

Paper • 2509.23050 • Published Sep 27 • 14