arXiv subjects

Xinchen Li

Publications and source records attributed to Xinchen Li.

12 recordsLinked to original sources

arXiv2026

$\tau_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation

Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no mechanism to allocate additional computation to difficult or consequential choices. We introduce $\tau_0$-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem through world-model-guided test-time computation. At each inference step, the high-level policy uses execution memory to generate a subtask and, when needed, searches over alternatives before committing to its output. A low-level policy then executes the generated subtask across multiple robot embodiments. The policy is trained on 40,115 hours of heterogeneous real-world data with multimodal co-training. Across in-domain and distribution-shifted settings, allocating additional test-time computation substantially improves next-subtask prediction accuracy, and these gains translate into higher closed-loop success on long-horizon robot manipulation tasks.

cs.RO↗

arXiv2026

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

Generalist robot policies increasingly benefit from large-scale pretraining, but offline data alone is insufficient for robust real-world deployment. Deployed robots encounter distribution shifts, long-tail failures, task variations, and human correction opportunities that fixed demonstration datasets cannot fully capture. We present Learning While Deploying (LWD), a fleet-scale offline-to-online reinforcement learning framework for continual post-training of generalist Vision-Language-Action (VLA) policies. Starting from a pretrained VLA policy, LWD closes the loop between deployment, shared physical experience, policy improvement, and redeployment by using autonomous rollouts and human interventions collected across a robot fleet. To stabilize learning from heterogeneous, sparse-reward fleet data, LWD combines Distributional Implicit Value Learning (DIVL) for robust value estimation with Q-learning via Adjoint Matching (QAM) for policy extraction in flow-based VLA action generators. We validate LWD on a fleet of 16 dual-arm robots across eight real-world manipulation tasks, including semantic grocery restocking and 3--5 minute long-horizon tasks. A single generalist policy improves as fleet experience accumulates, reaching an average success rate of 95%, with the largest gains on long-horizon tasks.

cs.RO↗

arXiv2026

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of methodological evolution. In particular, it does not capture the structured relationships that explain how and why research methods emerge, adapt, and build upon one another. With the rise of AI-driven research agents as a new class of consumers of scientific knowledge, this limitation becomes increasingly consequential, as such agents cannot reliably reconstruct method evolution topologies from unstructured text. We introduce Intern-Atlas, a methodological evolution graph that automatically identifies method-level entities, infers lineage relationships among methodologies, and captures the bottlenecks that drive transitions between successive innovations. Built from 1,030,314 papers spanning AI conferences, journals, and arXiv preprints, the resulting graph comprises 9,410,201 semantically typed edges, each grounded in verbatim source evidence, forming a queryable causal network of methodological development. To operationalize this structure, we further propose a self-guided temporal tree search algorithm for constructing evolution chains that trace the progression of methods over time. We evaluate the quality of the resulting graph against expert-curated ground-truth evolution chains and observe strong alignment. In addition, we demonstrate that Intern-Atlas enables downstream applications in idea evaluation and automated idea generation. We position methodological evolution graphs as a foundational data layer for the emerging automated scientific discovery.

cs.AI↗

arXiv2026

Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models

Block-wise decoding effectively improves the inference speed and quality in diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel unmasking. However, existing block-wise decoding methods typically partition blocks in a rigid and fixed manner, which inevitably fragments complete semantic or syntactic constituents, leading to suboptimal performance. Inspired by the entropy reduction hypothesis (ERH), we recognize that constituent boundaries offer greater opportunities for uncertainty reduction, which motivates us to employ entropy analysis for identifying constituent boundaries. Therefore, we propose Swordsman, an entropy-driven adaptive block-wise decoding framework for DLMs. Swordsman adaptively partitions blocks by identifying entropy shifts between adjacent tokens to better align with semantic or syntactic constituent boundaries. In addition, Swordsman dynamically adjusts unmasking thresholds conditioned on the real-time unmasking status within a block, further improving both efficiency and stability. As a training-free framework, supported by KV Cache, Swordsman demonstrates state-of-the-art performance across extensive evaluations.

cs.CL↗

arXiv2026

SOP: A Scalable Online Post-Training System for Vision-Language-Action Models

Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality. Existing post-training approaches for VLA models are typically offline, single-robot, or task-specific, limiting effective on-policy adaptation and scalable learning from real-world interaction. We introduce a Scalable Online Post-training (SOP) system that enables online, distributed, multi-task post-training of generalist VLA models directly in the physical world. SOP tightly couples execution and learning through a closed-loop architecture in which a fleet of robots continuously streams on-policy experience and human intervention signals to a centralized cloud learner, and asynchronously receives updated policies. This design supports prompt on-policy correction, scales experience collection through parallel deployment, and preserves generality during adaptation. SOP is agnostic to the choice of post-training algorithm; we instantiate it with both interactive imitation learning (HG-DAgger) and reinforcement learning (RECAP). Across a range of real-world manipulation tasks including cloth folding, box assembly, and grocery restocking, we show that SOP substantially improves the performance of large pretrained VLA models while maintaining a single shared policy across tasks. Effective post-training can be achieved within hours of real-world interaction, and performance scales near-linearly with the number of robots in the fleet. These results suggest that tightly coupling online learning with fleet-scale deployment is instrumental to enabling efficient, reliable, and scalable post-training of generalist robot policies in the physical world.

cs.RO↗

arXiv2025

Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning

Current text-to-image diffusion generation typically employs complete-text conditioning. Due to the intricate syntax, diffusion transformers (DiTs) inherently suffer from a comprehension defect of complete-text captions. One-fly complete-text input either overlooks critical semantic details or causes semantic confusion by simultaneously modeling diverse semantic primitive types. To mitigate this defect of DiTs, we propose a novel split-text conditioning framework named DiT-ST. This framework converts a complete-text caption into a split-text caption, a collection of simplified sentences, to explicitly express various semantic primitives and their interconnections. The split-text caption is then injected into different denoising stages of DiT-ST in a hierarchical and incremental manner. Specifically, DiT-ST leverages Large Language Models to parse captions, extracting diverse primitives and hierarchically sorting out and constructing these primitives into a split-text input. Moreover, we partition the diffusion denoising process according to its differential sensitivities to diverse semantic primitive types and determine the appropriate timesteps to incrementally inject tokens of diverse semantic primitive types into input tokens via cross-attention. In this way, DiT-ST enhances the representation learning of specific semantic primitive types across different stages. Extensive experiments validate the effectiveness of our proposed DiT-ST in mitigating the complete-text comprehension defect.

cs.CV↗

arXiv2025

MuonSLab: A plastic scintillator based detector for muon measurement in the deep ocean

Atmospheric muons are important probes for studying primary cosmic rays and extensive air showers. Additionally, they constitute a significant background for many underground and deep-sea neutrino experiments, such as TRopIcal DEep-sea Neutrino Telescope (TRIDENT). Understanding the muon flux at various depths in the deep sea is essential for validating TRIDENT simulations and guiding the development of optimized trigger strategies. This paper introduces a novel device based on plastic scintillalors and silicon photomultipliers (SiPMs) named MuonSLab, which is designed to measure muon flux in the deep sea and has the potential to be extended to other atmospheric muon property measurements. We discuss the design and instrumentation of MuonSLab and present results from several muon flux measurements, demonstrating its sensitivity to muon detection and its stability during operations across multiple locations.

hep-ex↗

arXiv2023

Pre-Deployment Testing of Low Speed, Urban Road Autonomous Driving in a Simulated Environment

Low speed autonomous shuttles emulating SAE Level L4 automated driving using human driver assisted autonomy have been operating in geo-fenced areas in several cities in the US and the rest of the world. These autonomous vehicles (AV) are operated by small to mid-sized technology companies that do not have the resources of automotive OEMs for carrying out exhaustive, comprehensive testing of their AV technology solutions before public road deployment. Due to the low speed of operation and hence not operating on roads containing highways, the base vehicles of these AV shuttles are not required to go through rigorous certification tests. The way the driver assisted AV technology is tested and allowed for public road deployment is continuously evolving but is not standardized and shows differences between the different states where these vehicles operate. Currently, AVs and AV shuttles deployed on public roads are using these deployments for testing and improving their technology. However, this is not the right approach. Safe and extensive testing in a lab and controlled test environment including Model-in-the-Loop (MiL), Hardware-in-the-Loop (HiL) and Autonomous-Vehicle-in-the-Loop (AViL) testing should be the prerequisite to such public road deployments. This paper presents three dimensional virtual modeling of an AV shuttle deployment site and simulation testing in this virtual environment. We have two deployment sites in Columbus of these AV shuttles through the Department of Transportation funded Smart City Challenge project named Smart Columbus. The Linden residential area AV shuttle deployment site of Smart Columbus is used as the specific example for illustrating the AV testing method proposed in this paper.

cs.RO↗

arXiv2023

Decision Making for Autonomous Vehicles

This paper is on decision making of autonomous vehicles for handling roundabouts. The round intersection is introduced first followed by the Markov Decision Processes (MDP), the Partially Observable Markov Decision Processes (POMDP) and the Object Oriented Partially Observable Markov Decision Process (OOPOMDP). The Partially Observable Monte-Carlo Planning algorihtm (POMCP) algorithm is introduced and OOPOMDP is applied to decision making for autonomous vehicles in round intersections. Decision making is formulated as a POMDP problem and the penalty function is formulated and set followed by improvement of decision making with policy prediction. The augmented objective state and policy based state transition is introduced simulations are used to demonstrate the effectiveness of the proposed method.

eess.SY↗

arXiv2023

Vehicle State Estimation and Prediction

This paper presents methods for vehicle state estimation and prediction for autonomous driving. A roundabout is chosen to apply the methods and illustrate the results as autonomous vehicles have difficulty in handling roundabouts. State estimation based on the unscented Kalman filter (UKF) is introduced first with application to a roundabout. The microscopic traffic simulator SUMO is used to generate realistic traffic in the roundabout for the simulation experiments. Change point detection based driving behavior prediction using a multi policy approach is then introduced and evaluated for the round intersection example. Finally, these methods are combined for vehicle trajectory estimation based on UKF and policy prediction and demonstrated using the roundabout example.

eess.SY↗

arXiv2023

TrajMatch: Towards Automatic Spatio-temporal Calibration for Roadside LiDARs through Trajectory Matching

Recently, it has become popular to deploy sensors such as LiDARs on the roadside to monitor the passing traffic and assist autonomous vehicle perception. Unlike autonomous vehicle systems, roadside sensors are usually affiliated with different subsystems and lack synchronization both in time and space. Calibration is a key technology which allows the central server to fuse the data generated by different location infrastructures, which can deliver improve the sensing range and detection robustness. Unfortunately, existing calibration algorithms often assume that the LiDARs are significantly overlapped or that the temporal calibration is already achieved. Since these assumptions do not always hold in the real world, the calibration results from the existing algorithms are often unsatisfactory and always need human involvement, which brings high labor costs. In this paper, we propose TrajMatch -- the first system that can automatically calibrate for roadside LiDARs in both time and space. The main idea is to automatically calibrate the sensors based on the result of the detection/tracking task instead of extracting special features. More deeply, we propose a mechanism for evaluating calibration parameters that is consistent with our algorithm, and we demonstrate the effectiveness of this scheme experimentally, which can also be used to guide parameter iterations for multiple calibration. Finally, to evaluate the performance of TrajMatch , we collect two dataset, one simulated dataset LiDARnet-sim 1.0 and a real-world dataset. Experiment results show that TrajMatch can achieve a spatial calibration error of less than 10cm and a temporal calibration error of less than 1.5ms.

cs.RO↗

arXiv2020

Simulation Environment for Safety Assessment of CEAV Deployment in Linden

This report presents a simulation environment for pre-deployment testing of the autonomous shuttles that will operate in the Linden Residential Area. An autonomous shuttle deployment was already successfully launched and operated in the city of Columbus and ended recently. This report focuses on the second autonomous shuttle deployment planned to start in December, 2019, using a route that will help to solve first-mile / last-mile mobility challenges in the Linden neighborhood of Columbus by providing free rides between St. Stephens Community House, Douglas Community Recreation Center, Rosewind Resident Council and Linden Transit Center. This document presents simulation testing environments in two open source simulators and a commercial simulator for this residential area route and how they can be used for model-in-the-loop and hardware-in-the-loop simulation testing of autonomous shuttle operation before the actual deployment.

cs.RO↗