Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

MOMENT: A Family of Open Time-series Foundation Models, ICML'24

Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]

A curated list of academic papers and resources on Physical AI — focusing on Vision-Language-Action (VLA) models, world models, embodied ai, and robotic foundation models.

Official repository for "CLIP model is an Efficient Continual Learner".

Google Cloud Medical Imaging ML Development Accelerators

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

In this course navigates through the LLMOps pipeline, enabling you to preprocess training data for supervised fine-tuning and deploy custom Large Language Models (LLMs).

🐍📦 High-performance cosine similarity ranking for Retrieval-Augmented Generation (RAG) pipelines.

This repository is for profiling, extracting, visualizing and reusing generative AI weights to hopefully build more accurate AI models and audit/scan weights at rest to identify knowledge domains for risk(s).

Glycan Informed Foundational Framework for Learning Abstract Representations, based on Combinatorial Complexes and Heterogeneous GNNs

Course assignments of COL828:- Advanced Computer Vision course at IIT Delhi under Professor Chetan Arora

An improved temporal data pipeline with foundational model for battery State of Health (SOH) prediction (R²->0.99) using advanced time series decomposition (D3R, CEEMDAN) and transformer-based methods. Utilized 100-150 features (ARIMA-based, Rolling statistics, Degradation indicators)

🔋 Predict battery State of Health (SOH) with a cutting-edge model using time series decomposition and transformer methods for accurate results.

Short course's of deeplearning.ai

An interactive dashboard for time-series forecasting using state-of-the-art foundational models.

A high-level framework for fine-tuning and deploying foundational models using enterprise-specific datasets.

A collection of medical imaging and machine learning projects, including foundational segmentation models.

Vaayushop Foundational models for Finance & DIY model for corporates

We introduce Weight Sharing Attention to improve state representation in Reinforcement Learning. By combining embeddings from different Foundational Models, WSA enhances learning efficiency. Tested on Atari games, it performs on par with advanced methods and addresses issues like out-of-distribution data.

Provide Whisper-based audio transcription and translation with lightweight C++ libraries for easy integration into LLM projects.