Fengzhuo Zhang

Fengzhuo's activity

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

submitted a paper to Daily Papers about 2 months ago

Demystifying the Slash Pattern in Attention: The Role of RoPE

Paper • 2601.08297 • Published Jan 13 • 4

authored a paper 12 months ago

Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework

Paper • 2503.10704 • Published Mar 12, 2025 • 5

authored 3 papers about 1 year ago

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

Paper • 2410.13846 • Published Oct 17, 2024 • 2

When Attention Sink Emerges in Language Models: An Empirical View

Paper • 2410.10781 • Published Oct 14, 2024

What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization

Paper • 2305.19420 • Published May 30, 2023