-
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding
Paper • 2307.15337 • Published • 37 -
DiTFastAttn: Attention Compression for Diffusion Transformer Models
Paper • 2406.08552 • Published • 25 -
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Paper • 2406.02540 • Published • 2 -
Can LLMs Learn by Teaching? A Preliminary Study
Paper • 2406.14629 • Published • 20
Tsinghua-NICS-EFC
university
AI & ML interests
None defined yet.