Alternatives and similar repositories for PS3

Users that are interested in PS3 are comparing it to the libraries listed below

• allenai / molmo2
  Code for the Molmo2 Vision-Language Model
  ☆151Updated last month
• facebookresearch / webssl
  Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).
  ☆201Updated 9 months ago
• rccchoudhury / rlt
  Official Implementation for our NeurIPS 2024 paper, "Don't Look Twice: Run-Length Tokenization for Faster Video Transformers".
  ☆235Updated 10 months ago
• marinero4972 / Open-o3-Video
  Official implementation of "Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence"
  ☆129Updated last month
• SihanXU / nepa
  PyTorch implementation of NEPA
  ☆308Updated 2 weeks ago
• facebookresearch / pixio
  Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction
  ☆345Updated 2 weeks ago
• iSEE-Laboratory / ReferDINO
  (ICCV 2025) ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations
  ☆128Updated 2 months ago
• NVlabs / QLIP
  [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
  ☆95Updated 11 months ago
• hustvl / DiG
  [CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
  ☆177Updated 11 months ago
• OpenSenseNova / SenseNova-SI
  Scaling Spatial Intelligence with Multimodal Foundation Models
  ☆170Updated this week
• baaivision / URSA
  [ICLR 2026] 🐻 Uniform Discrete Diffusion with Metric Path for Video Generation
  ☆98Updated 3 weeks ago
• YuqingWang1029 / PAR
  [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project
  ☆184Updated 10 months ago
• hustvl / MaTVLM
  ☆58Updated 8 months ago
• lxtGH / DenseWorld-1M
  Code and dataset link for "DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World"
  ☆122Updated 4 months ago
• andrehuang / loftup
  [ICCV'25 oral] Official Code for "LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"
  ☆249Updated 3 weeks ago
• PaulCouairon / JAFAR
  [NeurIPS 2025] Official code for JAFAR: Jack up Any Feature at Any Resolution
  ☆216Updated 2 months ago
• End2End-Diffusion / iREPA
  Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?
  ☆216Updated last month
• UX-Decoder / FIND
  [NeurIPS 2024] Official implementation of the paper "Interfacing Foundation Models' Embeddings"
  ☆129Updated last year
• ymq2017 / entitysam
  [CVPR'2025] EntitySAM: Segment Everything in Video
  ☆60Updated 6 months ago
• Yangr116 / VST
  Visual Spatial Tuning
  ☆172Updated last week
• tulip-berkeley / open_clip
  An open source implementation of CLIP (With TULIP Support)
  ☆165Updated 8 months ago
• UCSC-VLAA / OpenVision
  [ICCV 2025] OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
  ☆454Updated last week
• TIGER-AI-Lab / Vamba
  Code for the paper "Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers" [ICCV 2025]
  ☆100Updated 6 months ago
• ByteDance-Seed / SAIL
  Implementation for "The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer"
  ☆79Updated 3 months ago
• wren93 / tuna
  ☆88Updated last month
• alimohammadiamirhossein / smite
  Pytorch Implementation of "SMITE: Segment Me In TimE" (ICLR 2025)
  ☆212Updated 2 months ago
• facebookresearch / Action100M
  A Large-scale Video Action Dataset
  ☆388Updated 3 weeks ago
• berkeley-hipie / segllm
  Code release for "SegLLM: Multi-round Reasoning Segmentation"
  ☆127Updated 11 months ago
• RobinWu218 / SimDINO
  [ICML 2025] Official Implementation for SimDINO/SimDINOv2
  ☆192Updated 10 months ago
• IDEA-Research / RexSeek
  [ICCV2025] Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark
  ☆177Updated 3 months ago