Zhizhou Sha's picture

1 25

Zhizhou Sha

JamesSand

·

AI & ML interests

None yet

Organizations

JamesSand's activity

upvoted a paper 1 day ago

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Paper • 2410.21845 • Published 4 days ago • 8

upvoted a paper 6 days ago

Unbounded: A Generative Infinite Game of Character Life Simulation

Paper • 2410.18975 • Published 9 days ago • 34

upvoted a paper 8 days ago

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Paper • 2410.16268 • Published 12 days ago • 65

upvoted a paper 25 days ago

Differential Transformer

Paper • 2410.05258 • Published 26 days ago • 165

upvoted 2 papers about 2 months ago

Seed-Music: A Unified Framework for High Quality and Controlled Music Generation

Paper • 2409.09214 • Published Sep 13 • 45

TokenCompose: Grounding Diffusion with Token-level Supervision

Paper • 2312.03626 • Published Dec 6, 2023 • 5

upvoted a paper 2 months ago

Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time

Paper • 2408.13233 • Published Aug 23 • 20

upvoted a paper 3 months ago

SAM 2: Segment Anything in Images and Videos

Paper • 2408.00714 • Published Aug 1 • 106

upvoted 4 papers 5 months ago

Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models

Paper • 2406.11831 • Published Jun 17 • 19

ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Paper • 2406.12793 • Published Jun 18 • 31

DiTFastAttn: Attention Compression for Diffusion Transformer Models

Paper • 2406.08552 • Published Jun 12 • 22

Diffusion for World Modeling: Visual Details Matter in Atari

Paper • 2405.12399 • Published May 20 • 27

upvoted 2 papers 6 months ago

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

Paper • 2405.01434 • Published May 2 • 51

MoDE: CLIP Data Experts via Clustering

Paper • 2404.16030 • Published Apr 24 • 12

upvoted a collection 6 months ago

MOE papers to read

Copied from MoE using https://huggingface.co/spaces/librarian-bots/collection_cloner. • 82 items • Updated Jun 21 • 3

upvoted 3 papers 7 months ago

SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Paper • 2401.15024 • Published Jan 26 • 68

Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation

Paper • 2403.16990 • Published Mar 25 • 25

TextCraftor: Your Text Encoder Can be Image Quality Controller

Paper • 2403.18978 • Published Mar 27 • 13

upvoted a paper 8 months ago

Sora Generates Videos with Stunning Geometrical Consistency

Paper • 2402.17403 • Published Feb 27 • 16

upvoted a paper 9 months ago

Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation

Paper • 2401.15688 • Published Jan 28 • 11