Domain-agnostic multi-agent software design and evolution harness

Cosmos-Reason2 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.

This repository contains the code for the paper - "Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision" (CVPR 2026)

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.

Stereo4D dataset and processing code

Unofficial DynaDUSt3R reimplementation trained on Stereo4D (research only).

NextFlow🚀: Unified Sequential Modeling Activates Multimodal Understanding and Generation

[ICLR 2026] Training Visual Reasoners with Multimodal Verifiers

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

[arXiv 2023] Set-of-Mark Prompting for GPT-4V and LMMs

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Official repository of paper "Subobject-level Image Tokenization" (ICML-25)

Official inference framework for 1-bit LLMs

Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

Everything about the SmolLM and SmolVLM family of models

A suite of image and video neural tokenizers

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

Densely Captioned Images (DCI) dataset repository.

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/sp…

Waymo Open Dataset

Data release for the ImageInWords (IIW) paper.

Referring Expression Datasets API

[IJCV 2026] Multimodal Referring Segmentation

code for affordance-r1

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

Reference PyTorch implementation and models for DINOv3

Official Repository for MolmoAct