LLM Council works together to answer your hardest questions

We’re looking forward to new models based on DINOv3. For now rankings include: Align3R BetterDepth ChronoDepth CUT3R Depth Any Video Depth Anything Depth Pro DepthCrafter Geo4D GRIN L4P M2SVid MASt…

A Robust Approach for LiDAR-Inertial Odometry Without Sensor-Specific Modelling

Connect AI models like Claude & GPT with robots using MCP and ROS.

Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)

Reference PyTorch implementation and models for DINOv3

Visual Perception Engine: fast and flexible framework designed to run multiple perception models in an optimized and concurrent manner on NVIDIA Jetson

The simplest, fastest repository for training/finetuning small-sized VLMs.

Real-time Depth Estimation for Jetson Orin

PyTorch Implementation of AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation (ECCV 2024)

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

A Library for Advanced Deep Time Series Models.

Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)

Official implementation of the paper: "StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling"

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"

YOLOE: Real-Time Seeing Anything [ICCV 2025]

WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecasting (AAAI-2025)

"RAG-Anything: All-in-One RAG System"

This repository collects research papers of large Foundation Models for Scenario Generation and Analysis in Autonomous Driving. The repository will be continuously updated to track the latest update.

A comprehensive collection of PyTorch tutorials covering essential concepts and applications

LiPo: A Lightweight Post-optimization Framework for Smoothing Action Chunks Generated by Learned Policies

Fine-tune LLMs for free with 100+ Notebooks on Google Colab, Kaggle, and more.

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.