Muhammad Maaz's starred repositories
ConvNeXt-V2
Code release for ConvNeXt V2 model
Video-ChatGPT
[ACL 2024 🔥] 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 for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
groundingLMM
[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.
prompt-pretraining
Official implementation for the paper "Prompt Pre-Training with Over Twenty-Thousand Classes for Open-Vocabulary Visual Recognition"
Video-LLaVA
PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models
SwiftFormer
[ICCV'23] Official repository of paper SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
PromptAlign
[NeurIPS 2023] Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization
ClimateGPT
[EMNLP'23] ClimateGPT: a specialized LLM for conversations related to Climate Change and Sustainability topics in both English and Arabic languages.
Multimodality-Representation-Learning
This repository provides a comprehensive collection of research papers focused on multimodal representation learning, all of which have been cited and discussed in the survey just accepted https://dl.acm.org/doi/abs/10.1145/3617833 .
vlm-evaluation
VLM Evaluation: Benchmark for VLMs, spanning text generation tasks from VQA to Captioning
llmblueprint
[ICLR 2024] Official code for the paper "LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts"
hateclipper
Hate-CLIPper: Multimodal Hateful Meme Classification with Explicit Cross-modal Interaction of CLIP features - Accepted at EMNLP 2022 Workshop
composed-video-retrieval
Composed Video Retrieval