Hu Xiaolin's starred repositories
ustb_choose_course_system
【OUTDATED】北京科技大学选课系统第三方Windows、Linux、Mac、Android、iOS客户端
Neural-Network-Parameter-Diffusion
We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters
zotero-better-bibtex
Make Zotero effective for us LaTeX holdouts
acl-style-files
Official style files for papers submitted to venues of the Association for Computational Linguistics
Hybrid-Decentralized-Optimization
The code for the paper "Hybrid Decentralized Optimization: First- and Zeroth-Order Optimizers Can Be Jointly Leveraged For Faster Convergence"
topology-in-decentralized-learning
Code related to ’Beyond spectral gap: The role of the topology in decentralized learning‘.
Efficient_Foundation_Model_Survey
Survey Paper List - Efficient LLM and Foundation Models
Megatron-LLM
distributed trainer for LLMs
natural-instructions
Expanding natural instructions
GreenTrainer
Code for paper "Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation" (ICLR'24)