Blogs | Slides

Introducing muP

Mar 13, 2025

In this blog, we introduce muP (Maximal Update Parametrization), which aims at studying the transfer patterns of hyperparameters across model scales.

Blogs

What is the Intrinsic Dimension of Your Data?

Jan 15, 2025

In this blog, we introduce the concept of intrinsic dimension and provide a method to estimate it. It is amazing that ImageNet has only 50 of the intrinsic dimension.

Slides

Bridging the Parallel Decoding of LLMs with the Diffusion Process

Oct 30, 2024

In this blog, we introduce Jacobi Decoding, a parallel decoding algorithm for LLMs and its connection to the diffusion process in terms of high-level concepts.

English
Chinese

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

ICLR 2025, Singapore

Ego3DT: Tracking Every 3D Object in Ego-centric Videos

ACM MM 2024, Melbourne, Australia

^† MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

CVPR 2024, Seattle, WA

^† STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft

CVPR 2024 workshop, Seattle, WA

^† UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning

AAAI 2024, Vancouver, Canada

^† StableVideo: Text-driven Consistency-aware Diffusion Video Editing

ICCV 2023, Paris, France

See and Think: Embodied Agent in Virtual Environment

ECCV 2024, Milano, Italy

^† Learning Diffusion Texture Priors for Image Restoration

CVPR 2024, Seattle, WA

Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation

ICLR 2024 workshop, Vienna, Austria

^† Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation

WACV 2024, Waikoloa, Hawaii

^† Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

ICCV 2023, Paris, France