TSAIL group

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

TurboDiffusion: video generation acceleration framework that could accelerate end-to-end video generation by 100-205x with negligible video quality loss.

Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving, CVPR 2023

Official implementation for "ControlVideo: Adding Conditional Control for One Shot Text-to-Video Editing"

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

Official code of Motus: A Unified Latent Action World Model

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)