Stars
Awesome Incremental Learning
PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"
Awesome papers & datasets specifically focused on long-term videos.
[CVPR'2024 Highlight] Official PyTorch implementation of the paper "VTimeLLM: Empower LLM to Grasp Video Moments".
The official code of Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval (AAAI2024)
🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.
A curated list of recent diffusion models for video generation, editing, and various other applications.
[ICCV2023] - CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation
[TPAMI2024] Codes and Models for VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
CVPR and NeurIPS poster examples and templates. May we have in-person poster session soon!
✨✨Latest Advances on Multimodal Large Language Models
[NIPS2023] Code and Model for VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列
Deep Fourier Ranking Quantization for Semi-Supervised Image Retrieval -- TIP22
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
MomentDiff: Generative Video Moment Retrieval from Random to Real--NeurIPS 2023
[Communications Chemistry 2023] Highly accurate and large-scale collision cross section prediction with graph neural network for compound identification
[ICCV 2023] Official implement of <Disentangle then Parse: Night-time Semantic Segmentation with Illumination Disentanglement>
Official implementation of "Self-slimmed Vision Transformer" (ECCV2022)
[CVPR 2024] SimDA: Simple Diffusion Adapter for Efficient Video Generation