-
USTC
- Hefei, China
-
02:26
(UTC +08:00) - https://home.ustc.edu.cn/~fzr
Stars
Efficient Multimodal Large Language Models: A Survey
Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!
Official pytorch implementation of "RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in LVLMs"
This is the first released survey paper on hallucinations of large vision-language models (LVLMs). To keep track of this field and continuously update our survey, we maintain this repository of relβ¦
This is the official repo for Debiasing Large Visual Language Models, including a Post-Hoc debias method and Visual Debias Decoding strategy.
Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation
[CVPR'2024 Highlight] Official PyTorch implementation of the paper "VTimeLLM: Empower LLM to Grasp Video Moments".
SimPO: Simple Preference Optimization with a Reference-Free Reward
RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness
[ACL 2024 π₯] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted foβ¦
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
When do we not need larger vision models?
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"
GPT4V-level open-source multi-modal model based on Llama3-8B
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
π A curated list of resources dedicated to hallucination of multimodal large language models (MLLM).
π OpenHands: Code Less, Make More
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models
Mixture-of-Experts for Large Vision-Language Models
π₯π₯ LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)
Accelerating the development of large multimodal models (LMMs) with lmms-eval
A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
Code for the paper "Evaluating Large Language Models Trained on Code"