arXiv subjects

Derun Li

Publications and source records attributed to Derun Li.

10 recordsLinked to original sources

arXiv2026

DriveMA: Driving Vision-Language-Action Models with verifiable Meta-Actions

Driving Vision-Language-Action Models (Driving VLAs) aim to use language to improve end-to-end planning, but the language-action gap limits this promise. We propose DriveMA, a Driving VLA framework built on verifiable meta-actions, which summarize future ego motion into compact language-domain intentions and can be constructed from expert trajectories with a trajectory-grounded annotation pipeline and can be verified against generated trajectories through rule-based projection. DriveMA exploits this verifiability with action-centric supervised training and a data-efficient turn-level credit assignment reinforcement learning framework, explicitly aligning high-level decisions with low-level trajectory planning through dense rewards and precise credit assignment. DriveMA sets a new state of the art on the Waymo Open Dataset Vision-based E2E Driving, achieving a Rater Feedback Score of 8.060 with a 2B model and further improving it to 8.079 with a 4B model; it also obtains competitive closed-loop planning performance on NAVSIM. These results show that even a simple meta-action interface can achieve state-of-the-art planning when made verifiable and optimized for language-action alignment. Code, data, and models are available at https://tsinghua-mars-lab.github.io/DriveMA.

cs.CV↗

arXiv2026

DriveMA: Rethinking Language Interfaces in Driving VLAs with One-Step Meta-Actions

Driving Vision-Language-Action Models (Driving VLAs) commonly introduce natural-language reasoning as an intermediate interface for end-to-end planning, but reasoning-centric interfaces face three practical bottlenecks: obtaining high-quality reasoning annotations is difficult, generating and understanding long reasoning chains is challenging for compact models, and inference latency is substantially increased. In this paper, we rethink the design of language interfaces in Driving VLAs and show that concise one-step meta-actions are a simple yet effective alternative to verbose reasoning. Meta-actions provide semantic decision grounding while remaining low-entropy, and being automatically derivable from expert trajectories, enabling scalable supervision and reliable trajectory conditioning. Building on this interface, we propose DriveMA, which combines action-centric supervised training with a turn-level credit-assignment reinforcement learning framework that jointly optimizes meta-action correctness, trajectory quality, and trajectory--meta-action consistency. Experiments show that DriveMA already achieves a new state of the art on the Waymo End-to-End Driving Challenge with a 2B model, reaching a Rater Feedback Score (RFS) of 8.060, while its 4B version further improves the state of the art to 8.079; DriveMA also obtains competitive performance on NAVSIM. Ablations demonstrate that one-step meta-actions offer a better practical trade-off between expressiveness, predictability, and inference efficiency than natural-language reasoning or finer-grained action sequences. Code, data, and models will be released to facilitate future research.

cs.CV↗

arXiv2025

OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision

Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the difficulty of constructing accessible yet effective 3D representations without expensive manual annotations, and (2) the loss of fine-grained spatial details in VLMs due to the absence of large-scale 3D vision-language pretraining. To address these challenges, we propose OccVLA, a novel framework that integrates 3D occupancy representations into a unified multimodal reasoning process. Unlike prior approaches that rely on explicit 3D inputs, OccVLA treats dense 3D occupancy as both a predictive output and a supervisory signal, enabling the model to learn fine-grained spatial structures directly from 2D visual inputs. The occupancy predictions are regarded as implicit reasoning processes and can be skipped during inference without performance degradation, thereby adding no extra computational overhead. OccVLA achieves state-of-the-art results on the nuScenes benchmark for trajectory planning and demonstrates superior performance on 3D visual question-answering tasks, offering a scalable, interpretable, and fully vision-based solution for autonomous driving.

cs.AI↗

arXiv2025

Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback

Generating human-like and adaptive trajectories is essential for autonomous driving in dynamic environments. While generative models have shown promise in synthesizing feasible trajectories, they often fail to capture the nuanced variability of personalized driving styles due to dataset biases and distributional shifts. To address this, we introduce TrajHF, a human feedback-driven finetuning framework for generative trajectory models, designed to align motion planning with diverse driving styles. TrajHF incorporates multi-conditional denoiser and reinforcement learning with human feedback to refine multi-modal trajectory generation beyond conventional imitation learning. This enables better alignment with human driving preferences while maintaining safety and feasibility constraints. TrajHF achieves performance comparable to the state-of-the-art on NavSim benchmark. TrajHF sets a new paradigm for personalized and adaptable trajectory generation in autonomous driving.

cs.RO↗

arXiv2025

VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotion

Recent success in legged robot locomotion is attributed to the integration of reinforcement learning and physical simulators. However, these policies often encounter challenges when deployed in real-world environments due to sim-to-real gaps, as simulators typically fail to replicate visual realism and complex real-world geometry. Moreover, the lack of realistic visual rendering limits the ability of these policies to support high-level tasks requiring RGB-based perception like ego-centric navigation. This paper presents a Real-to-Sim-to-Real framework that generates photorealistic and physically interactive "digital twin" simulation environments for visual navigation and locomotion learning. Our approach leverages 3D Gaussian Splatting (3DGS) based scene reconstruction from multi-view images and integrates these environments into simulations that support ego-centric visual perception and mesh-based physical interactions. To demonstrate its effectiveness, we train a reinforcement learning policy within the simulator to perform a visual goal-tracking task. Extensive experiments show that our framework achieves RGB-only sim-to-real policy transfer. Additionally, our framework facilitates the rapid adaptation of robot policies with effective exploration capability in complex new environments, highlighting its potential for applications in households and factories.

cs.RO↗

arXiv2024

SARO: Space-Aware Robot System for Terrain Crossing via Vision-Language Model

The application of vision-language models (VLMs) has achieved impressive success in various robotics tasks. However, there are few explorations for these foundation models used in quadruped robot navigation through terrains in 3D environments. In this work, we introduce SARO (Space Aware Robot System for Terrain Crossing), an innovative system composed of a high-level reasoning module, a closed-loop sub-task execution module, and a low-level control policy. It enables the robot to navigate across 3D terrains and reach the goal position. For high-level reasoning and execution, we propose a novel algorithmic system taking advantage of a VLM, with a design of task decomposition and a closed-loop sub-task execution mechanism. For low-level locomotion control, we utilize the Probability Annealing Selection (PAS) method to effectively train a control policy by reinforcement learning. Numerous experiments show that our whole system can accurately and robustly navigate across several 3D terrains, and its generalization ability ensures the applications in diverse indoor and outdoor scenarios and terrains. Project page: https://saro-vlm.github.io/

cs.RO↗

arXiv2024

AI-based Automatic Segmentation of Prostate on Multi-modality Images: A Review

Prostate cancer represents a major threat to health. Early detection is vital in reducing the mortality rate among prostate cancer patients. One approach involves using multi-modality (CT, MRI, US, etc.) computer-aided diagnosis (CAD) systems for the prostate region. However, prostate segmentation is challenging due to imperfections in the images and the prostate's complex tissue structure. The advent of precision medicine and a significant increase in clinical capacity have spurred the need for various data-driven tasks in the field of medical imaging. Recently, numerous machine learning and data mining tools have been integrated into various medical areas, including image segmentation. This article proposes a new classification method that differentiates supervision types, either in number or kind, during the training phase. Subsequently, we conducted a survey on artificial intelligence (AI)-based automatic prostate segmentation methods, examining the advantages and limitations of each. Additionally, we introduce variants of evaluation metrics for the verification and performance assessment of the segmentation method and summarize the current challenges. Finally, future research directions and development trends are discussed, reflecting the outcomes of our literature survey, suggesting high-precision detection and treatment of prostate cancer as a promising avenue.

eess.IV↗

arXiv2023

Large Trajectory Models are Scalable Motion Predictors and Planners

Motion prediction and planning are vital tasks in autonomous driving, and recent efforts have shifted to machine learning-based approaches. The challenges include understanding diverse road topologies, reasoning traffic dynamics over a long time horizon, interpreting heterogeneous behaviors, and generating policies in a large continuous state space. Inspired by the success of large language models in addressing similar complexities through model scaling, we introduce a scalable trajectory model called State Transformer (STR). STR reformulates the motion prediction and motion planning problems by arranging observations, states, and actions into one unified sequence modeling task. Our approach unites trajectory generation problems with other sequence modeling problems, powering rapid iterations with breakthroughs in neighbor domains such as language modeling. Remarkably, experimental results reveal that large trajectory models (LTMs), such as STR, adhere to the scaling laws by presenting outstanding adaptability and learning efficiency. Qualitative results further demonstrate that LTMs are capable of making plausible predictions in scenarios that diverge significantly from the training data distribution. LTMs also learn to make complex reasonings for long-term planning, without explicit loss designs or costly high-level annotations.

cs.RO↗

arXiv2018

Operation of normal-conducting RF cavities in multi-tesla magnetic fields for muon ionization cooling: a feasibility demonstration

Ionization cooling is the preferred method for producing bright muon beams. This cooling technique requires the operation of normal conducting, radio-frequency (RF) accelerating cavities within the multi-tesla fields of DC solenoid magnets. Under these conditions, cavities exhibit increased susceptibility to RF breakdown, which can damage channel components and imposes limits on channel length and transmission efficiency. We present a solution to the problem of breakdown in strong magnetic fields. We report, for the first time, stable high-vacuum, copper cavity operation at gradients above 50 MV/m and in an external magnetic field of three tesla. This eliminates a significant technical risk that has previously been inherent in ionization cooling channel designs.

physics.acc-ph↗

arXiv2008

rf Breakdown with and without External Magnetic Fields

Neutrino Factories and Muon Colliders' cooling lattices require both high gradient rf and strong focusing solenoids. Experiments have shown that there may be serious problems operating rf in the required magnetic fields. The use of high pressure gas to avoid these problems is discussed, including possible loss problems from electron and ion production by the passage of an ionizing beam. It is also noted that high pressure gas cannot be used in later stages of cooling for a muon collider. Experimental observations using vacuum rf cavities in magnetic fields are discussed, current published models of breakdown with and without magnetic fields are summarized, and some of their predictions compared with observations. A new theory of magnetic field dependent breakdown is presented. It is proposed that electrons emitted by field emission on asperities on one side of a cavity are focused by the magnetic field to the other side where they melt the cavity surface in small spots. Metal is then electrostatically drawn from the molten spots, becomes vaporized and ionized by field emission from the remaining damage and cause breakdown. The theory is fitted to existing 805 MHz data and predictions are made for performance at 201 MHz. The model predicts breakdown gradients significantly below those specified for either the International Scoping Study (ISS) Neutrino Factory or a Muon Collider. Possible solutions to these problems are discussed, including designs for `magnetically insulated rf' in which the cavity walls are designed to be parallel to a chosen magnetic field contour line and consequently damage from field emission is suppressed. An experimental program to study these problems and their possible solution is outlined.

physics.acc-ph↗