Jintao Zhang

jt-zhang's activity

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

upvoted a paper 1 day ago

Intrinsic Distribution Matching

Paper • 2610.39633 • Published 3 days ago • 20

upvoted a paper 10 days ago

StreamEval: Evaluating Interactive Streaming Video Generation Models

Paper • 2610.28402 • Published 12 days ago • 86

upvoted a paper about 1 month ago

EasyPPO: Stabilizing the Critic Is Key

Paper • 2609.36802 • Published Sep 29 • 31

upvoted a paper about 2 months ago

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

Paper • 2609.11638 • Published Sep 10 • 276

upvoted 2 collections 4 months ago

efficient ml

Collection

13 items • Updated Jul 10 • 3

Streaming_Video_Gen

Collection

2 items • Updated Sep 15 • 1

upvoted 3 papers 4 months ago

Vidu S1: A Real-Time Interactive Video Generation Model

Paper • 2607.03118 • Published Jul 3 • 150

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Paper • 2607.01647 • Published Jul 2 • 36

TurboServe: Serving Streaming Video Generation Efficiently and Economically

Paper • 2606.19271 • Published Jun 17 • 35

upvoted 4 papers 6 months ago

FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale

Paper • 2605.14445 • Published May 14 • 21

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Paper • 2605.15141 • Published May 14 • 96

KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

Paper • 2605.04956 • Published May 6 • 8

Speculative Decoding for Autoregressive Video Generation

Paper • 2604.17397 • Published Apr 19 • 12

upvoted a paper 7 months ago

6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models

Paper • 2603.18742 • Published Mar 19 • 9

upvoted 6 papers 8 months ago

HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration

Paper • 2603.07815 • Published Mar 8 • 10

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

Paper • 2603.09229 • Published Mar 10 • 85

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

Paper • 2603.08982 • Published Mar 9 • 16

SageBwd: A Trainable Low-bit Attention

Paper • 2603.02170 • Published Mar 2 • 19

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

Paper • 2602.13515 • Published Feb 13 • 45

SLA2: Sparse-Linear Attention with Learnable Routing and QAT

Paper • 2602.12675 • Published Feb 13 • 59