GPT4V-level open-source multi-modal model based on Llama3-8B

CLIP-Mamba: CLIP Pretrained Mamba Models with OOD and Hessian Evaluation

MoVA: Adapting Mixture of Vision Experts to Multimodal Context

[ACM MM 2024] Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization

VMamba: Visual State Space Models，code is based on mamba

Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

Instruct-tune LLaMA on consumer hardware

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

[CVPR'23 Best Paper Award] Planning-oriented Autonomous Driving

UniMD: Towards Unifying Moment retrieval and temporal action Detection

[ECCV 2024] ShareGPT4V: Improving Large Multi-modal Models with Better Captions

Efficient Multimodal Large Language Models: A Survey

a state-of-the-art-level open visual language model | 多模态预训练模型

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Mixture-of-Experts for Large Vision-Language Models

(CVPR2024) Realigning Confidence with Temporal Saliency Information for Point-level Weakly-Supervised Temporal Action Localization

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

[ECCV 2022] Dual-Evidential Learning for Weakly-supervised Temporal Action Localization

The implement for Dynamic Semantic-based Graph Convolution Network for Skeleton-based Human Action Recognition

The official code of Semantic-Guided Representation Enhancement for Multi-Label Image Classification, TCSVT 2024.

[CVPR 2023] Official repository of paper titled "Fine-tuned CLIP models are efficient video learners".

Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

VadCLIP official Pytorch implementation

Code for our IJCV 2023 paper "CLIP-guided Prototype Modulating for Few-shot Action Recognition".