Alternatives and similar repositories for perception_models:

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

• NVlabs / RADIO
  Official repository for "AM-RADIO: Reduce All Domains Into One"
  ☆1,117Updated last week
• mit-han-lab / vila-u
  [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
  ☆299Updated this week
• NVlabs / describe-anything
  Implementation for Describe Anything: Detailed Localized Image and Video Captioning
  ☆390Updated this week
• NVlabs / PS3
  Scaling Vision Pre-Training to 4K Resolution
  ☆124Updated 3 weeks ago
• allenai / molmo
  Code for the Molmo Vision-Language Model
  ☆377Updated 4 months ago
• facebookresearch / jepa-intuitive-physics
  This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"
  ☆142Updated 2 months ago
• rccchoudhury / rlt
  Official Implementation for our NeurIPS 2024 paper, "Don't Look Twice: Run-Length Tokenization for Faster Video Transformers".
  ☆206Updated 3 weeks ago
• bfshi / scaling_on_scales
  When do we not need larger vision models?
  ☆388Updated 2 months ago
• dfan / webssl
  Code for Scaling Language-Free Visual Representation Learning (WebSSL)
  ☆245Updated this week
• vision-x-nyu / thinking-in-space
  Official repo and evaluation implementation of VSI-Bench
  ☆463Updated last month
• hustvl / EVF-SAM
  Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"
  ☆397Updated last month
• bytedance / 1d-tokenizer
  This repo contains the code for 1D tokenizer and generator
  ☆838Updated last month
• facebookresearch / unibench
  Python Library to evaluate VLM models' robustness across diverse benchmarks
  ☆201Updated this week
• TencentARC / SEED-Voken
  SEED-Voken: A Series of Powerful Visual Tokenizers
  ☆868Updated 2 months ago
• frank-xwang / UnSAM
  [NeurIPS 2024] Code release for "Segment Anything without Supervision"
  ☆461Updated 6 months ago
• remyxai / VQASynth
  Compose multimodal datasets 🎹
  ☆351Updated this week
• baaivision / EVE
  EVE Series: Encoder-Free Vision-Language Models from BAAI
  ☆322Updated last month
• tulip-berkeley / open_clip
  An open source implementation of CLIP (With TULIP Support)
  ☆132Updated last month
• naver-ai / rope-vit
  [ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"
  ☆315Updated 4 months ago
• WisconsinAIVision / ViP-LLaVA
  [CVPR2024] ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
  ☆319Updated 9 months ago
• tulerfeng / Video-R1
  Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]
  ☆469Updated 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…
  ☆366Updated this week
• Haiyang-W / GiT
  [ECCV2024 Oral🔥] Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"
  ☆346Updated 3 months ago
• facebookresearch / metamorph
  Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning
  ☆123Updated this week
• DAMO-NLP-SG / Inf-CLIP
  [CVPR 2025 Highlight] The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for C…
  ☆240Updated 3 months ago
• NVIDIA / Cosmos-Tokenizer
  A suite of image and video neural tokenizers
  ☆1,614Updated 2 months ago
• LeslieTrue / SFTvsRL
  Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
  ☆265Updated 2 months ago
• microsoft / LLM2CLIP
  LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.
  ☆506Updated last month
• dvlab-research / Seg-Zero
  Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"
  ☆325Updated 2 weeks ago
• baaivision / NOVA
  [ICLR 2025] Autoregressive Video Generation without Vector Quantization
  ☆477Updated this week