Microsoft Research Asia – Tokyo - Microsoft Research: Publications

Microsoft Research Asia

Microsoft Research Asia – Tokyo

출판물

자료 보기:

- Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement
  
  Kinam Kim, Namiko Saito, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  2026 10th Annual Conference on Robot Learning | November 2026
  
  Publication
- ESP: Energy-Score Policy for One-Step Multimodal Action Generation
  
  Lilika Makabe, Heecheol Kim, Yasuyuki Matsushita
  
  October 2026
  
  arXiv | October 2026
  
  Publication
- DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
  
  Seongheon Park, Heecheol Kim, Shulin Tian, Lilika Makabe, Namiko Saito, Katsushi Ikeuchi, Sharon Li, Yasuyuki Matsushita
  
  October 2026
  
  arXiv | October 2026
  
  Preprint
  
  Preprint
- VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL
  
  Namiko Saito, Kinam Kim, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration
  
  Heecheol Kim, Namiko Saito, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  June 2026
  
  arXiv | June 2026
  
  Publication

- Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement
  
  Kinam Kim, Namiko Saito, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  2026 10th Annual Conference on Robot Learning | November 2026
  
  Publication
- ESP: Energy-Score Policy for One-Step Multimodal Action Generation
  
  Lilika Makabe, Heecheol Kim, Yasuyuki Matsushita
  
  October 2026
  
  arXiv | October 2026
  
  Publication
- DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
  
  Seongheon Park, Heecheol Kim, Shulin Tian, Lilika Makabe, Namiko Saito, Katsushi Ikeuchi, Sharon Li, Yasuyuki Matsushita
  
  October 2026
  
  arXiv | October 2026
  
  Preprint
  
  Preprint
- VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL
  
  Namiko Saito, Kinam Kim, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration
  
  Heecheol Kim, Namiko Saito, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement
  
  Kinam Kim, Namiko Saito, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  2026 10th Annual Conference on Robot Learning | November 2026
  
  Publication
- DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
  
  Seongheon Park, Heecheol Kim, Shulin Tian, Lilika Makabe, Namiko Saito, Katsushi Ikeuchi, Sharon Li, Yasuyuki Matsushita
  
  October 2026
  
  arXiv | October 2026
  
  Preprint
  
  Preprint
- VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL
  
  Namiko Saito, Kinam Kim, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  September 2026
  
  arXiv | September 2026
  
  Publication

- Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement
  
  Kinam Kim, Namiko Saito, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  2026 10th Annual Conference on Robot Learning | November 2026
  
  Publication
- ESP: Energy-Score Policy for One-Step Multimodal Action Generation
  
  Lilika Makabe, Heecheol Kim, Yasuyuki Matsushita
  
  October 2026
  
  arXiv | October 2026
  
  Publication
- DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
  
  Seongheon Park, Heecheol Kim, Shulin Tian, Lilika Makabe, Namiko Saito, Katsushi Ikeuchi, Sharon Li, Yasuyuki Matsushita
  
  October 2026
  
  arXiv | October 2026
  
  Preprint
  
  Preprint
- VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL
  
  Namiko Saito, Kinam Kim, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration
  
  Heecheol Kim, Namiko Saito, Katsushi Ikeuchi, Yasuyuki Matsushita
  
  June 2026
  
  arXiv | June 2026
  
  Publication

Microsoft Research Asia – Tokyo

출판물

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

ESP: Energy-Score Policy for One-Step Multimodal Action Generation

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL

ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration

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

ESP: Energy-Score Policy for One-Step Multimodal Action Generation

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL

ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration

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

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL

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

ESP: Energy-Score Policy for One-Step Multimodal Action Generation

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL

ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration