This is your work, valued
RemoteCLIP. 🛰️ Official repository of paper "RemoteCLIP: A Vision Language Foundation Model for Remote Sensing" (IEEE TGRS)
579VirtualConductor. 🎶 Music-Driven Conducting Motion Generation (IEEE ICME'21 Best Demo)
98subobjects. Official repository of paper "Subobject-level Image Tokenization" (ICML-25)
94polite-flamingo. 🦩 Official repository of paper "Visual Instruction Tuning with Polite Flamingo" (AAAI-24 Oral)
65MEP-3M. 🎁 A Large-scale Multi-modal E-Commerce Products Dataset (LTDL@IJCAI-21 Best Dataset & Pattern Recognition 2023)
43ITRA. A codebase for flexible and efficient Image Text Representation Alignment
24HHForecasting. 💦 A codebase for data-driven hydrological time-series forecasting, with official implementation of FloodDAN.
20instruct-flamingo. 🚀 Codebase and Fondation Models for Visual Instruction Tuning
14Linguistic-Similarity. Official repo of paper "Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language Models" in NeurIPS 2024 Workshop on Foundation Model Interventions (MINT) and COLING 2025
7DriverFatigueDetection.
5ITRA-Documentations. Python
5DirectSAM. Python
5subobjects-VLM. Jupyter Notebook
3contrastor-value-embedding. Python
2AIM-Group-Home-Page. HTML
2Seq2Seq-AutoEncoder. Jupyter Notebook
1