Chinese University of Hong Kong, Shenzhen

CUHKSZ's activity

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

yeyeyewang 

submitted a paper to Daily Papers 13 days ago

Janus: Disaggregating Attention and Experts for Scalable MoE Inference

Paper • 2512.13525 • Published 15 days ago • 5

guangyil 

authored 2 papers about 1 month ago

Character Mixing for Video Generation

Paper • 2510.05093 • Published Oct 6 • 6

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

Paper • 2511.09057 • Published Nov 12 • 76

Kullpar 

authored a paper 7 months ago

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs

Paper • 2506.03077 • Published Jun 3 • 17

guangyil 

authored 2 papers 8 months ago

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play

Paper • 2505.02707 • Published May 5 • 85

LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

Paper • 2504.19838 • Published Apr 28 • 22

whatlegequ 

authored 8 papers 10 months ago

Inducing Neural Collapse in Deep Long-tailed Learning

Paper • 2302.12453 • Published Feb 24, 2023

Elucidating The Design Space of Classifier-Guided Diffusion Generation

Paper • 2310.11311 • Published Oct 17, 2023

Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization

Paper • 2306.02595 • Published Jun 5, 2023

On the Expressive Power of a Variant of the Looped Transformer

Paper • 2402.13572 • Published Feb 21, 2024

Towards Understanding How Transformer Perform Multi-step Reasoning with Matching Operation

Paper • 2405.15302 • Published May 24, 2024

Elucidating the design space of language models for image generation

Paper • 2410.16257 • Published Oct 21, 2024

Rewards Are Enough for Fast Photo-Realistic Text-to-image Generation

Paper • 2503.13070 • Published Mar 17 • 10

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Paper • 2503.06674 • Published Mar 9 • 8

chongjie 

authored 3 papers over 1 year ago

StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

Paper • 2406.16864 • Published Jun 24, 2024 • 3

LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset

Paper • 2312.12418 • Published Dec 19, 2023 • 2

MVImgNet: A Large-scale Dataset of Multi-view Images

Paper • 2303.06042 • Published Mar 10, 2023

guangyil 

authored 3 papers over 1 year ago

Composable Text Controls in Latent Space with ODEs

Paper • 2208.00638 • Published Aug 1, 2022

Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

Paper • 2106.15078 • Published Jun 29, 2021

Pandora: Towards General World Model with Natural Language Actions and Video States

Paper • 2406.09455 • Published Jun 12, 2024 • 16