jiang kai

jiang kai on Hugging Face Daily Papers: 11 papers, 8 in the top 3 of their day, 1,333 upvotes.

1. Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation 695 upvotes, #1 of 2026-09-15
2. Vidu S1: A Real-Time Interactive Video Generation Model 138 upvotes, #1 of 2026-07-10
3. TurboServe: Serving Streaming Video Generation Efficiently and Economically 34 upvotes, #2 of 2026-07-02
4. SageBwd: A Trainable Low-bit Attention 17 upvotes, #10 of 2026-03-06
5. SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning 43 upvotes, #3 of 2026-02-20
6. SLA2: Sparse-Linear Attention with Learnable Routing and QAT 52 upvotes, #1 of 2026-02-19
7. TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times 88 upvotes, #1 of 2025-12-25
8. SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention 109 upvotes, #1 of 2025-09-30
9. DiffusionNFT: Online Diffusion Reinforcement with Forward Process 20 upvotes, #8 of 2025-09-23
10. SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training 58 upvotes, #2 of 2025-05-21
11. Visual Generation Without Guidance 8 upvotes, #9 of 2025-01-28

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.