Sim-to-Real Transfer

FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation

FasTac: A Curved Multispectral Vision-Based Tactile Sensor for High-Speed High-Precision 3D Shape and Force Perception

PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball

ContactFlow: A video action conditioning that transfers across embodiments

Fei-Fei Li on Spatial Intelligence and Robotics

Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design

Data Pyramid for Embodied Manipulation

AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation

Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids

Exp2VLA: Enabling Vision-Language-Action for Drone Navigation from Expert Demonstrations

LENS: LLM-guided Environment Simplification for Planning and Control in Clutter

Directional Constraints for Efficient Exploration in Safe Reinforcement Learning

Masked Visual Actions for Unified World Modeling

Handroid: Bridging Dexterous Hand and Humanoid

RoboTTT: Context Scaling for Robot Policies

Agile perceptive multi-skill locomotion for quadrupedal robots in the wild

Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection

Worlds in One Demo: A Synthetic Data Engine for Learning Open-World Mobile Manipulation

Towards Human-level Dexterous Teleoperation

B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations

DemoBridge: A Simulation-in-the-Loop Toolkit for Single-View Human Demonstration Retargeting

AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance

ContactMimic: Humanoid Object Interaction via Contact Control

DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation

Native Video-Action Pretraining for Generalizable Robot Control

Calf-Integrated Arms for Bimanual Quadruped Loco-Manipulation

LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation

SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing

Decoupling the Declarative from the Procedural in Vision-Language-Action Models

CoDex: Learning Compositional Dexterous Functional Manipulation without Demonstrations

Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models

Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments

SPACE: Enabling Learning from Cross-Robot Data Toward Generalist Policies

TactX: Learning Shared Tactile Representations Across Diverse Sensors

VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes

DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand

SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation

(Many) of Us Want Home Robots. What's the Holdup?

Bridging Performance and Generalization in Reinforcement Learning for Agile Flight

Scalable Behavior Cloning with Open Data, Training, and Evaluation

VibeAct: Vibration to Actions for Contact-Rich Reactive Robot Dexterity

CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation

Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?

PhysVLA: Towards Physically-Grounded VLA for Embodied Robotic Manipulation

SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors

OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation

ENPIRE: Agentic Robot Policy Self-Improvement in the Real World

Generating Robot Hands from Human Demonstrations

Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

TactSpace: Learning a Physics-enriched Shared Latent Space for Tactile Sim-to-Real Transfer

Mana: Dexterous Manipulation of Articulated Tools

WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation

WT-UMI: Tactile-based Whole-Body Manipulation via Force-Supervised Contact-Aware Planning

FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning

IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation

TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation

MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation

OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation

Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filtering

GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors

Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

RDGen: Demonstration Generation for High-Quality Robot Learning via Reinforcement Learning

VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models

Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representation

Cybo-Waiter: A Physical Agentic Framework for Humanoid Whole-Body Locomotion-Manipulation

When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation

Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score Network

Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors

TacSE3: Equivariant SE(3) Motion Estimation from Low-Texture Visuotactile Images for In-Gripper Tracking and Compensation

RLDX-1 Technical Report

Rev Lebaredian (NVIDIA) — SCSP AI+ Expo

CoCo-InEKF: State Estimation with Learned Contact Covariances in Dynamic, Contact-Rich Scenarios

Learning while Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies

DOT-Sim: Differentiable Optical Tactile Simulation with Precise Real-to-Sim Physical Calibration

FlexiTac: A Low-Cost, Open-Source, Scalable Tactile Sensing Solution for Robotic Systems

MotuBrain: An Advanced World Action Model for Robot Control

RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects

dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model

Deepak Pathak & Abhinav Gupta (Skild AI) — One Brain, Any Robot

FLASH: Fast Learning via GPU-Accelerated Simulation for High-Fidelity Deformable Manipulation in Minutes

Novel Algorithms for Smoothly Differentiable and Efficiently Vectorizable Contact Manifold Construction

Switch: Learning Agile Skills Switching for Humanoid Robots

A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies

Learning Versatile Humanoid Manipulation with Touch Dreaming

Simulator Adaptation for Sim-to-Real Learning of Legged Locomotion via Proprioceptive Distribution Matching

ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation

Sergey Levine — The Robot Revolution Nobody Is Talking About

Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks

A-SLIP: Acoustic Sensing for Continuous In-hand Slip Estimation

Learning Humanoid Standing-up Control across Diverse Postures

RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains

SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds

Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation

CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection

MobileManiBench: Simplifying Model Verification for Mobile Manipulation

ForeAct: Steering Your VLA with Efficient Visual Foresight Planning

Functional Force-Aware Retargeting from Virtual Human Demos to Soft Robot Policies

Learning Humanoid Navigation from Human Data

SMASH: Mastering Scalable Whole-Body Skills for Humanoid Ping-Pong with Egocentric Vision

SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

Scaling World Model for Hierarchical Manipulation Policies

Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization

ST4VLA: Spatially Guided Training for Vision-Language-Action Models

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction

SoftMimicGen: A Data Generation System for Scalable Robot Learning in Deformable Object Manipulation

UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds

Bernt Børnich (1X) — Meet NEO, Your Robot Butler in Training

Interview with DeepMind's Jie Tan: Robotics, Cross-Embodiment, World Models, Gemini Robotics 1.5, and Google

Lindon Gao, Dyna Robotics, Sebastian Spitzer, AI Infra, HPE - F50 Physical AI Summit