Jintao Zhang

jt-zhang's activity

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

authored a paper 8 days ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 16 days ago • 90

submitted a paper to Daily Papers 9 days ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 16 days ago • 90

authored 2 papers 3 months ago

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

Paper • 2510.08431 • Published Oct 9, 2025 • 8

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

Paper • 2509.24006 • Published Sep 28, 2025 • 118

authored 3 papers 7 months ago

SageAttention2++: A More Efficient Implementation of SageAttention2

Paper • 2505.21136 • Published May 27, 2025 • 45

Accurate INT8 Training Through Dynamic Block-Level Fallback

Paper • 2503.08040 • Published Mar 11, 2025 • 2

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Paper • 2505.18875 • Published May 24, 2025 • 42

authored a paper 8 months ago

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published May 16, 2025 • 75

authored 4 papers 10 months ago

Identifying Sensitive Weights via Post-quantization Integral

Paper • 2503.01901 • Published Feb 28, 2025 • 8

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published Mar 3, 2025 • 7

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Paper • 2502.01776 • Published Feb 3, 2025 • 3

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

Paper • 2502.18137 • Published Feb 25, 2025 • 59

authored 2 papers about 1 year ago

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published Nov 17, 2024 • 57

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

Paper • 2410.02367 • Published Oct 3, 2024 • 50