MoDeGPT: Modular Decomposition for Large Language Model Compression
Paper
•
2408.09632
•
Published
Shangqian Gao
sgao84
·
AI & ML interests
Efficient Machine Learning for LLMs, Diffusion Models, etc.
Recent Activity
authored
a paper
1 day ago
MoDeGPT: Modular Decomposition for Large Language Model Compression
authored
a paper
1 day ago
FlexiGPT: Pruning and Extending Large Language Models with Low-Rank
Weight Sharing
authored
a paper
1 day ago
ToMoE: Converting Dense Large Language Models to Mixture-of-Experts
through Dynamic Structural Pruning
Organizations
authored
7
papers
1 day ago
FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing
Paper
•
2501.14713
•
Published
ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning
Paper
•
2501.15316
•
Published
•
3
Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
Paper
•
2505.17100
•
Published
All-in-One Tuning and Structural Pruning for Domain-Specific LLMs
Paper
•
2412.14426
•
Published
Cost-Aware Contrastive Routing for LLMs
Paper
•
2508.12491
•
Published
GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models
Paper
•
2601.07632
•
Published
•
2
authored
a
paper
over 1 year ago