Jintao Zhang

jt-zhang's activity

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

authored a paper about 8 hours ago

HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration

Paper • 2603.07815 • Published 8 days ago • 8

submitted a paper to Daily Papers about 16 hours ago

HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration

Paper • 2603.07815 • Published 8 days ago • 8

authored 2 papers 5 days ago

SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

Paper • 2603.08982 • Published 7 days ago • 15

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Paper • 2603.09229 • Published 7 days ago • 68

authored a paper 10 days ago

SageBwd: A Trainable Low-bit Attention

Paper • 2603.02170 • Published 14 days ago • 17

submitted a paper to Daily Papers 11 days ago

SageBwd: A Trainable Low-bit Attention

Paper • 2603.02170 • Published 14 days ago • 17

authored a paper 24 days ago

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published about 1 month ago • 43

submitted a paper to Daily Papers 25 days ago

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published about 1 month ago • 43

authored a paper 25 days ago

SLA2: Sparse-Linear Attention with Learnable Routing and QAT

Paper • 2602.12675 • Published Feb 13 • 55

submitted a paper to Daily Papers 26 days ago

SLA2: Sparse-Linear Attention with Learnable Routing and QAT

Paper • 2602.12675 • Published Feb 13 • 55

submitted a paper to Daily Papers 27 days ago

Geometry-Aware Rotary Position Embedding for Consistent Video World Model

Paper • 2602.07854 • Published Feb 8 • 10

authored 2 papers about 1 month ago

Residual Context Diffusion Language Models

Paper • 2601.22954 • Published Jan 30 • 35

Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

Paper • 2602.02958 • Published Feb 3 • 34

authored a paper 3 months ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published Dec 18, 2025 • 95

submitted a paper to Daily Papers 3 months ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published Dec 18, 2025 • 95

authored a paper 5 months ago

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

Paper • 2510.08431 • Published Oct 9, 2025 • 10

authored a paper 6 months ago

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

Paper • 2509.24006 • Published Sep 28, 2025 • 118

authored 3 papers 10 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