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.
-
Updated
Feb 24, 2026 - Python
#
foundational-models
Here are 10 public repositories matching this topic...
👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]
nlp computer-vision image-captioning clip blip multimodal zero-shot-detection foundational-models llava segment-anything open-vocabulary-detection open-vocabulary-segmentation grounding-dino
-
Updated
Feb 29, 2024 - Python
Official repository for "CLIP model is an Efficient Continual Learner".
-
Updated
Dec 13, 2022 - Python
ACM Multimedia 2023 (Oral) - RTQ: Rethinking Video-language Understanding Based on Image-text Model
machine-learning deep-learning multi-modal video-understanding vision-and-language video-language video-language-pretraining foundational-models
-
Updated
Jan 31, 2024 - Python
🐍📦 High-performance cosine similarity ranking for Retrieval-Augmented Generation (RAG) pipelines.
cosine-similarity reranking ranking-system rag python-rust large-language-models llm foundational-models retrieval-augmented-generation
-
Updated
Dec 24, 2025 - Python
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).
ai deep-learning blender tiff transformers weights image-to-image blender-python llm stable-diffusion foundational-models generative-ai safetensors blip2 gptq
-
Updated
Dec 18, 2023 - Python
Course assignments of COL828:- Advanced Computer Vision course at IIT Delhi under Professor Chetan Arora
computer-vision transformers object-detection openai-clip foundational-models grounding-dino vision-language-models
-
Updated
Nov 29, 2025 - Python
🔋 Predict battery State of Health (SOH) with a cutting-edge model using time series decomposition and transformer methods for accurate results.
rolling-statistics foundational-models gru-neural-network ceemdan-lstm-arima emd-gru-arima-hybrid d3r-decomposition arima-based-features grid-scale-energy-storage-monitoring predictive-maintenance-scheduling battery-lifecycle-optimization
-
Updated
Mar 2, 2026 - Python
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)
rolling-statistics foundational-models gru-neural-network ceemdan-lstm-arima emd-gru-arima-hybrid d3r-decomposition arima-based-features grid-scale-energy-storage-monitoring predictive-maintenance-scheduling battery-lifecycle-optimization
-
Updated
Jan 25, 2026 - Python
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.
-
Updated
Jul 16, 2024 - Python
Improve this page
Add a description, image, and links to the foundational-models topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the foundational-models topic, visit your repo's landing page and select "manage topics."