jiang kai

aaa-ceku7's activity

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

upvoted a paper 26 days ago

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Paper • 2610.12242 • Published 27 days ago • 119

authored 11 papers about 2 months ago

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

Paper • 2609.11638 • Published Sep 10 • 224

Vidu S1: A Real-Time Interactive Video Generation Model

Paper • 2607.03118 • Published Jul 3 • 147

TurboServe: Serving Streaming Video Generation Efficiently and Economically

Paper • 2606.19271 • Published Jun 17 • 34

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

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published Dec 18, 2025 • 95

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

Paper • 2509.24006 • Published Sep 28, 2025 • 116

DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Paper • 2509.16117 • Published Sep 19, 2025 • 24

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

Paper • 2505.11594 • Published May 16, 2025 • 75

Visual Generation Without Guidance

Paper • 2501.15420 • Published Jan 26, 2025 • 8

upvoted a paper about 2 months ago

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

Paper • 2609.11638 • Published Sep 10 • 224

upvoted 3 papers 4 months ago

See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents

Paper • 2606.13594 • Published Jun 11 • 6

Vidu S1: A Real-Time Interactive Video Generation Model

Paper • 2607.03118 • Published Jul 3 • 147

TurboServe: Serving Streaming Video Generation Efficiently and Economically

Paper • 2606.19271 • Published Jun 17 • 34

upvoted a paper 6 months ago

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

Paper • 2605.15141 • Published May 14 • 96

upvoted 2 papers 9 months ago

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

New activity in aaa-ceku7/GFT 12 months ago

Add model card for GFT: Visual Generation Without Guidance with pipeline and library tags

#1 opened about 1 year ago by

nielsr