Identifying Sensitive Weights via Post-quantization Integral
Paper
•
2503.01901
•
Published
•
8
Yuezhou Hu
yuezhouhu
·
AI & ML interests
My research interests include efficient machine learning, particularly efficient training and inference.
Recent Activity
upvoted
a
paper
21 days ago
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative
Decoders
commented on
a paper
21 days ago
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative
Decoders
authored
a paper
21 days ago
Identifying Sensitive Weights via Post-quantization Integral
Organizations
authored
4
papers
21 days ago
Accelerating Transformer Pre-training with 2:4 Sparsity
Paper
•
2404.01847
•
Published
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
Paper
•
2409.09099
•
Published
CAST: Continuous and Differentiable Semi-Structured Sparsity-Aware Training for Large Language Models
Paper
•
2509.25996
•
Published
authored
3
papers
22 days ago
Pruning Large Language Models with Semi-Structural Adaptive Sparse Training
Paper
•
2407.20584
•
Published
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
Paper
•
2510.04767
•
Published
•
26
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
Paper
•
2510.19779
•
Published
•
58