[NeurIPS 2024] WATT: Weight Average Test-Time Adaptation of CLIP

[ICLRW 2024] Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment

EUFCC-CIR: A Composed Image Retrieval Dataset for GLAM Collections

[AAAI-2025] The official code of Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation

When do we not need larger vision models?

Provide with pre-build flash-attention package wheels using GitHub Actions

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

[ICLR 2024] Official repository for "Vision-by-Language for Training-Free Compositional Image Retrieval"

[ICCV 2023] - Composed Image Retrieval on Common Objects in context (CIRCO) dataset

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Rethinking Step-by-step Visual Reasoning in LLMs

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Visual Delta Generator with Large Multi-modal Model for Semi-supervised Composed Image Retrieval - CVPR2024

The official implementation of Natural Language Fine-Tuning

Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object Detection"

Project for "HyperSeg: Towards Universal Visual Segmentation with Large Language Model".

ACM Multimedia 2023 (Oral) - RTQ: Rethinking Video-language Understanding Based on Image-text Model

[ECCV2024] The Official Implementation for ''AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection''

A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.

[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…

A Clip-Hitchiker's Guide to Long Video Retrieval [Arxiv 2022]

The official repository for ICLR2024 paper "FROSTER: Frozen CLIP is a Strong Teacher for Open-Vocabulary Action Recognition"

Collection of Composed Image Retrieval (CIR) papers.

CLIPScore EMNLP code

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge (ICCV 2023)

[ECCV 2024] EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

Evaluation code and datasets for the ACL 2024 paper, VISTA: Visualized Text Embedding for Universal Multi-Modal Retrieval. The original code and model can be accessed at FlagEmbedding.

Code for the paper "Finetuning CLIP to Reason about Pairwise Differences"