6 6

Jintao Zhang

jt-zhang

https://jt-zhang.github.io/

jtzhang-6

AI & ML interests

Efficient ML

Recent Activity

upvoted a paper 17 days ago

SAGE: A Framework of Precise Retrieval for RAG

commented on a paper 17 days ago

SAGE: A Framework of Precise Retrieval for RAG

authored a paper 20 days ago

Identifying Sensitive Weights via Post-quantization Integral

View all activity

Organizations

None yet

jt-zhang's activity

upvoted a paper 17 days ago

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published 23 days ago • 5

commented a paper 17 days ago

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published 23 days ago • 5 •

authored 3 papers 20 days ago

Identifying Sensitive Weights via Post-quantization Integral

Paper • 2503.01901 • Published 27 days ago • 7

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published 23 days ago • 5

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

Paper • 2502.01776 • Published Feb 3

upvoted a paper 20 days ago

Identifying Sensitive Weights via Post-quantization Integral

Paper • 2503.01901 • Published 27 days ago • 7

commented a paper 20 days ago

Identifying Sensitive Weights via Post-quantization Integral

Paper • 2503.01901 • Published 27 days ago • 7 •

updated a collection 26 days ago

efficient ml

Collection

2 items • Updated 26 days ago

authored a paper 29 days ago

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

Paper • 2502.18137 • Published 29 days ago • 54

upvoted a paper 29 days ago

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

Paper • 2502.18137 • Published 29 days ago • 54

commented a paper 29 days ago

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

Paper • 2502.18137 • Published 29 days ago • 54 •

upvoted a paper 3 months ago

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

Paper • 2412.14711 • Published Dec 19, 2024 • 16

commented 4 papers 3 months ago

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

Paper • 2412.14711 • Published Dec 19, 2024 • 16 •

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

Paper • 2411.10958 • Published Nov 17, 2024 • 55 •

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

Paper • 2411.10958 • Published Nov 17, 2024 • 55 •

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

Paper • 2411.10958 • Published Nov 17, 2024 • 55 •

authored a paper 4 months ago

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

Paper • 2411.10958 • Published Nov 17, 2024 • 55

upvoted a paper 4 months ago

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

Paper • 2411.10958 • Published Nov 17, 2024 • 55

commented 2 papers 4 months ago

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

Paper • 2411.10958 • Published Nov 17, 2024 • 55 •

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

Paper • 2411.10958 • Published Nov 17, 2024 • 55 •