Alternatives and similar repositories for Cosmos

Users that are interested in Cosmos are comparing it to the libraries listed below

• deepseek-ai / Janus
  Janus-Series: Unified Multimodal Understanding and Generation Models
  ☆17,411Updated 5 months ago
• NVIDIA / Isaac-GR00T
  NVIDIA Isaac GR00T N1.5 is the world's first open foundation model for generalized humanoid robot reasoning and skills.
  ☆4,272Updated last week
• manycore-research / SpatialLM
  SpatialLM: Training Large Language Models for Structured Indoor Modeling
  ☆3,424Updated last week
• NVIDIA / Cosmos-Tokenizer
  A suite of image and video neural tokenizers
  ☆1,637Updated 4 months ago
• QwenLM / Qwen2.5-VL
  Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆11,207Updated last month
• facebookresearch / jepa
  PyTorch code and models for V-JEPA self-supervised learning from video.
  ☆3,102Updated 4 months ago
• Physical-Intelligence / openpi
  ☆3,805Updated this week
• openvla / openvla
  OpenVLA: An open-source vision-language-action model for robotic manipulation.
  ☆3,122Updated 3 months ago
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,286Updated last month
• facebookresearch / vjepa2
  PyTorch code and models for VJEPA2 self-supervised learning from video.
  ☆1,650Updated this week
• NVlabs / VILA
  VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…
  ☆3,356Updated last week
• Tencent-Hunyuan / HunyuanVideo
  HunyuanVideo: A Systematic Framework For Large Video Generation Model
  ☆10,489Updated 3 weeks ago
• apple / ml-depth-pro
  Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
  ☆4,593Updated 2 months ago
• Genesis-Embodied-AI / Genesis
  A generative world for general-purpose robotics & embodied AI learning.
  ☆25,357Updated this week
• facebookresearch / sam2
  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…
  ☆15,974Updated 6 months ago
• simplescaling / s1
  s1: Simple test-time scaling
  ☆6,468Updated this week
• microsoft / Magma
  [CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
  ☆1,735Updated last month
• computerhistory / AlexNet-Source-Code
  This package contains the original 2012 AlexNet code.
  ☆2,658Updated 3 months ago
• MoonshotAI / Kimi-k1.5
  ☆3,381Updated 3 months ago
• Jiayi-Pan / TinyZero
  Minimal reproduction of DeepSeek R1-Zero
  ☆11,942Updated 2 months ago
• facebookresearch / sapiens
  High-resolution models for human tasks.
  ☆5,056Updated 7 months ago
• apple / ml-fastvlm
  This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
  ☆4,267Updated last month
• NVlabs / Sana
  SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
  ☆4,300Updated 3 weeks ago
• ML-GSAI / LLaDA
  Official PyTorch implementation for "Large Language Diffusion Models"
  ☆2,435Updated 2 weeks ago
• dzhng / deep-research
  An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large…
  ☆16,837Updated 3 weeks ago
• volcengine / verl
  verl: Volcano Engine Reinforcement Learning for LLMs
  ☆10,204Updated this week
• deepseek-ai / DeepSeek-VL
  DeepSeek-VL: Towards Real-World Vision-Language Understanding
  ☆3,900Updated last year
• isaac-sim / IsaacLab
  Unified framework for robot learning built on NVIDIA Isaac Sim
  ☆4,028Updated this week
• huggingface / smollm
  Everything about the SmolLM2 and SmolVLM family of models
  ☆2,606Updated this week
• nvidia-cosmos / cosmos-transfer1
  Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…
  ☆521Updated this week