Geary.Z

zotero-arxiv-daily. Recommend new arxiv papers of your interest daily according to your Zotero libarary.

lmm-r1. Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

VL-RLHF. A RLHF Infrastructure for Vision-Language Models

doma_py. Automatically hold idle GPU.

seu-thesis-typst. 东南大学Typst论文模板库

doma. Guarantee the minimum of GPU utilization percentage.

TideDra.github.io. My blog

Latex-Report-Template-for-SEU. 本项目维护SEU实验报告Latex模板

verl. verl: Volcano Engine Reinforcement Learning for LLMs

HA-DPO. Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Multimodality-Linking. Python

mert-mel. Python

lmms-eval. Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.