[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”

Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)

Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN accuracy.

[EMNLP 2022] This is the code repo for our EMNLP‘22 paper "COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning".

Zero-shot Entity Linking with blitz start in 3 minutes. Hard negative mining and encoder for all entities are also included in this implementation.

The official implementation of "Diversity-Guided MLP Reduction for Efficient Large Vision Transformers"

A toolkit for research on multimodal representation learning

Pytorch implementation of CVPR'16 paper "Learning Deep Representations of Fine-Grained Visual Descriptions", by Reed et al.

Transductive Zero-Shot Hashing For Multi-Label Image Retrieval

[ICCV 2021] PyTorch implementation of "Universal Cross-Domain Retrieval: Generalizing across Classes and Domains"

[https://arxiv.org/abs/2208.09198] Test-Time Training for Universal Cross-Domain Retrieval

Пересказ статей по rag

This is the open-source repository for the project "Solo-Synth GAN" which is one of the latest zero shot generative adversarial network

Controlled depth ablation of a BERT bi-encoder across training budgets and seeds on three BEIR tasks (nfcorpus, scifact, fiqa). L3–L12 is flat within seed noise at 20K steps; 80K training degrades every depth on zero-shot transfer (−45% NDCG@10 on fiqa for L12).

Generate Suno AI music from OpenCLI, download MP3 and lyrics, and manage song history and status from the terminal