Selected work

Representative Papers

Pictura: Perspective-View Self-Play at Scale for Driving

Jul 28, 2026

This work addresses the representational gap that arises when driving policies trained with privileged state information are deployed using only first-person visual inputs. To bridge this gap, the authors propose the first purely vision-based self-play training framework that learns driving policies end-to-end directly from agent-centric images. Leveraging the GPU-accelerated multi-agent simulator Pictura and the PPO algorithm, the method achieves highly efficient training—processing 500,000 agent steps (equivalent to 2 million images) per second on a single H100 GPU. The resulting policy, Alberti, trained over 50 billion agent steps (approximately 35 million kilometers), closely matches the performance of privileged-observation baselines and demonstrates zero-shot superiority on re-rendered Waymo scenarios, effectively closing the perception gap between simulation and real-world deployment.

0 citationsRead paper

Human-like autonomy emerges from self-play and a pinch of human data

Jun 11, 2026

This work addresses the incompatibility between existing self-play reinforcement learning–derived driving policies and human driving behavior, which hinders effective coordination in real-world traffic despite ensuring safety. The authors propose a method that integrates an extremely small amount of human driving data—only 30 minutes, representing a 2,500-fold reduction compared to typical imitation learning—as a regularization target within a self-play reinforcement learning framework. This approach guides the policy to simultaneously achieve safety and mimic human driving styles, without requiring complex reward engineering or domain randomization. Trained on a single consumer-grade GPU in under 15 hours, the resulting policy demonstrates strong coordination capabilities with unseen human driving trajectories. Code and demonstration videos are publicly released.

0 citationsRead paper

Geometry-Aware Reinforcement Learning for 2D Irregular Nesting

Jun 09, 2026

This work addresses the limitations of traditional two-dimensional irregular nesting methods, which often suffer from insufficient geometric awareness and reliance on inefficient brute-force search strategies. To overcome these challenges, the authors propose a data-driven approach that integrates a geometry-aware neural encoder with reinforcement learning. The core innovation lies in the design of a Polygon Transformer (PoT) architecture featuring a cross-polygon attention mechanism, alongside the introduction of the first open-source training and evaluation benchmark tailored for complex geometric contours. Trained within a Combinatorial Optimization via Reinforcement Learning (CORL) framework, the resulting agent achieves area utilization performance on par with Sparrow, the current state-of-the-art heuristic solver, while significantly improving exploration efficiency in continuous placement spaces.

0 citationsRead paper

Towards a Joint Understanding of Remote Operation for Vehicles in Public Road Traffic

Jun 09, 2026

Current autonomous driving systems cannot yet handle all traffic scenarios and thus rely on remote operation to enable driverless mobility services; however, a unified conceptual framework bridging multiple disciplines and stakeholders is lacking. This work proposes an interdisciplinary conceptual framework grounded in the differences between human and vehicle information processing, integrating operational modes such as remote assistance and teleoperation. By systematically synthesizing perspectives from human factors engineering, autonomous driving architectures, communication technologies, and regulatory policies, the framework clarifies the boundaries of information processing between humans and vehicles in remote operations. It effectively bridges the semantic gaps among engineering, psychology, informatics, and legal domains, thereby providing a theoretical foundation and collaborative platform for the safe and compliant deployment of remote operations in public road environments.

0 citationsRead paper

Neuromorphic LiDAR-based Bird's Eye View Object Detection using Energy-efficient Spiking Neural Networks

May 24, 2026

This work addresses the challenge of achieving both high accuracy and energy efficiency in LiDAR-based 3D object detection for autonomous driving under stringent power constraints. The authors propose the first end-to-end trainable spiking neural network (SNN) that performs object detection directly from bird’s-eye-view inputs. Leveraging surrogate gradient training, the model supports either fully spiking or membrane potential-based outputs and incorporates a data-driven, learnable spike encoding strategy. Through block-level energy modeling, the method achieves 92.05/87.04/86.51 AP (IoU=0.5) on the KITTI benchmark while reducing synaptic operation energy consumption by 3.33× compared to conventional CNNs, effectively balancing detection accuracy with the requirements of neuromorphic hardware deployment.

0 citationsRead paper

Recent publications

Latest Papers

Pictura: Perspective-View Self-Play at Scale for Driving

Jul 28, 2026

This work addresses the representational gap that arises when driving policies trained with privileged state information are deployed using only first-person visual inputs. To bridge this gap, the authors propose the first purely vision-based self-play training framework that learns driving policies end-to-end directly from agent-centric images. Leveraging the GPU-accelerated multi-agent simulator Pictura and the PPO algorithm, the method achieves highly efficient training—processing 500,000 agent steps (equivalent to 2 million images) per second on a single H100 GPU. The resulting policy, Alberti, trained over 50 billion agent steps (approximately 35 million kilometers), closely matches the performance of privileged-observation baselines and demonstrates zero-shot superiority on re-rendered Waymo scenarios, effectively closing the perception gap between simulation and real-world deployment.

0 citationsRead paper

Human-like autonomy emerges from self-play and a pinch of human data

Jun 11, 2026

This work addresses the incompatibility between existing self-play reinforcement learning–derived driving policies and human driving behavior, which hinders effective coordination in real-world traffic despite ensuring safety. The authors propose a method that integrates an extremely small amount of human driving data—only 30 minutes, representing a 2,500-fold reduction compared to typical imitation learning—as a regularization target within a self-play reinforcement learning framework. This approach guides the policy to simultaneously achieve safety and mimic human driving styles, without requiring complex reward engineering or domain randomization. Trained on a single consumer-grade GPU in under 15 hours, the resulting policy demonstrates strong coordination capabilities with unseen human driving trajectories. Code and demonstration videos are publicly released.

0 citationsRead paper

Geometry-Aware Reinforcement Learning for 2D Irregular Nesting

Jun 09, 2026

This work addresses the limitations of traditional two-dimensional irregular nesting methods, which often suffer from insufficient geometric awareness and reliance on inefficient brute-force search strategies. To overcome these challenges, the authors propose a data-driven approach that integrates a geometry-aware neural encoder with reinforcement learning. The core innovation lies in the design of a Polygon Transformer (PoT) architecture featuring a cross-polygon attention mechanism, alongside the introduction of the first open-source training and evaluation benchmark tailored for complex geometric contours. Trained within a Combinatorial Optimization via Reinforcement Learning (CORL) framework, the resulting agent achieves area utilization performance on par with Sparrow, the current state-of-the-art heuristic solver, while significantly improving exploration efficiency in continuous placement spaces.

0 citationsRead paper

Towards a Joint Understanding of Remote Operation for Vehicles in Public Road Traffic

Jun 09, 2026

Current autonomous driving systems cannot yet handle all traffic scenarios and thus rely on remote operation to enable driverless mobility services; however, a unified conceptual framework bridging multiple disciplines and stakeholders is lacking. This work proposes an interdisciplinary conceptual framework grounded in the differences between human and vehicle information processing, integrating operational modes such as remote assistance and teleoperation. By systematically synthesizing perspectives from human factors engineering, autonomous driving architectures, communication technologies, and regulatory policies, the framework clarifies the boundaries of information processing between humans and vehicles in remote operations. It effectively bridges the semantic gaps among engineering, psychology, informatics, and legal domains, thereby providing a theoretical foundation and collaborative platform for the safe and compliant deployment of remote operations in public road environments.

0 citationsRead paper

Neuromorphic LiDAR-based Bird's Eye View Object Detection using Energy-efficient Spiking Neural Networks

May 24, 2026

This work addresses the challenge of achieving both high accuracy and energy efficiency in LiDAR-based 3D object detection for autonomous driving under stringent power constraints. The authors propose the first end-to-end trainable spiking neural network (SNN) that performs object detection directly from bird’s-eye-view inputs. Leveraging surrogate gradient training, the model supports either fully spiking or membrane potential-based outputs and incorporates a data-driven, learnable spike encoding strategy. Through block-level energy modeling, the method achieves 92.05/87.04/86.51 AP (IoU=0.5) on the KITTI benchmark while reducing synaptic operation energy consumption by 3.33× compared to conventional CNNs, effectively balancing detection accuracy with the requirements of neuromorphic hardware deployment.

0 citationsRead paper