Masayoshi Tomizuka

Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation

Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions

VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing

SPACeR: Self-Play Anchoring with Centralized Reference Models

Geometric Constraints as General Interfaces for Robot Manipulation

StreamDiT: Real-Time Streaming Text-to-Video Generation

Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL

REAR: Scalable Test-time Preference Realignment through Reward Decomposition

Bootstrap Off-policy with World Model

WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving

Looking Backward: Streaming Video-to-Video Translation with Feature Banks

Residual-MPPI: Online Policy Customization for Continuous Control

Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios

Bisimulation Metric for Model Predictive Control

PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views

CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving