Causal World Modeling for Robot Control

2601.21998

Mastering Diverse Domains through World Models

2301.04104

Consistency Models

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

2307.01952

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

2403.12945

HumanPlus: Humanoid Shadowing and Imitation from Humans

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

2401.16013

OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

2410.21845

Octo: An Open-Source Generalist Robot Policy

2405.12213

Demonstrating GPU Parallelized Robot Simulation and Rendering for Generalizable Embodied AI with ManiSkill3

2410.00425

PaliGemma 2: A Family of Versatile VLMs for Transfer

2412.03555

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

2404.07191

TripoSR: Fast 3D Object Reconstruction from a Single Image

2403.02151

LTX-Video: Realtime Video Latent Diffusion

2501.00103

YOLOv10: Real-Time End-to-End Object Detection

2405.14458

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

2411.07975

FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control

2505.22642

Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models

2506.09042