caoandong
Follow
Stars
Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.
State Management and Multiplayer Networking for Turn-Based Games
Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion
A generative world for general-purpose robotics & embodied AI learning.
Official repo for "IDArb: Intrinsic Decomposition for arbitrary number of input views and illuminations"
Learning Flow Fields in Attention for Controllable Person Image Generation
EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
[ARXIV'24] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
SeekStorm - sub-millisecond full-text search library & multi-tenancy server in Rust
Template repo with the latest tech working together
The official implementation of paper: DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting
Official implementation of OneDiffusion paper
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
A minimal and universal controller for FLUX.1.
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead
ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥
[Preprint] Number it: Temporal Grounding Videos like Flipping Manga
DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
Unifying 3D Mesh Generation with Language Models
Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System