arXiv subjects

Yanqing Shen

Publications and source records attributed to Yanqing Shen.

14 recordsLinked to original sources

arXiv2026

PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessment

Fine-grained robotic evaluation matters for understanding embodied models, going beyond binary success rates and rule-based process scores. We present PRM-as-a-Judge 1.5, a toolkit for robot process assessment that turns rollout videos into dense progress curves and derives multiple fine metrics. PRM-as-a-Judge 1.5 introduces three metrics, building on version 1.0, that characterize failure-side progress, post-drawdown recovery, and success-side execution quality, helping users understand embodied model capability. Based on the rollout videos from benchmarks, we perform a comprehensive assessment of the embodied models, providing some fine-grained metric results and key findings. We further introduce RoboPulse++ to evaluate the reliability of process reward models (PRM), providing evaluators with a more accurate testing platform. Moreover, we release a user-friendly assessment suite, including the benchmark, metric implementation, and visualization tools, to support reproducible manipulation process evaluation. We call on the community to rethink how robots are evaluated and establish transparent, procedural, and reproducible assessment as a foundation for the next generation of embodied intelligence.

cs.RO↗

arXiv2026

Orca: The World is in Your Mind

We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward understanding, predicting, and acting upon the world. Orca learns through two complementary paradigms: unconscious learning captures dense natural state transitions from continuous videos, and conscious learning models sparse meaningful state transitions by language-described events and VQA supervision. For pre-training, we construct a large-scale world-learning inventory data, including 125K hours of video data and 160M event annotations. After pre-training, Orca learns a unified world latent space. To examine whether the learned latent supports downstream, we evaluate it by three representative downstream readouts: text generation, image prediction, and embodied action generation. Orca's backbone is frozen, and only the lightweight modality-specific decoders are trainable. Experiments show the scalability of the proposed paradigm and verify that stronger world latent enables stronger downstream readouts. Orca outperforms similar-sized specialized baselines. These results show that Orca, as a general world foundation model, presents a promising approach to understanding, predicting, and acting upon the world. Finally, we discuss the current limitations, aiming to provide useful insights and inspiration for the community.

cs.CV↗

arXiv2026

InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation

Prevalent Vision-Language-Action (VLA) models are typically built upon Multimodal Large Language Models (MLLMs) and demonstrate exceptional proficiency in semantic understanding, but they inherently lack the capability to deduce physical world dynamics. Consequently, recent approaches have shifted toward World Models, typically formulated via video prediction; however, these methods often suffer from a lack of semantic grounding and exhibit brittleness in the presence of video prediction errors. To synergize semantic understanding with dynamic predictive capabilities, we present InternVLA-A1. This model employs a unified Mixture-of-Transformers architecture, coordinating three experts for scene understanding, visual foresight generation, and action execution. These components interact seamlessly through a unified masked self attention mechanism. Building upon InternVL3 and Qwen3-VL, we instantiate InternVLA-A1 at 2B and 3B parameter scales. We pre-train these models on heterogeneous data sources over real-world robot data, synthetic simulation data, and human videos, covering over 692M frames. This hybrid training strategy effectively harnesses the diversity of synthetic simulation data while minimizing the sim-to-real gap. We evaluated InternVLA-A1 on 12 real-world robotic tasks and a simulation benchmark. The results show that InternVLA-A1 consistently outperforms prior leading models: compared with pi0.5, it achieves +4.4\% on static manipulation tasks and +2.6\% on the RoboTwin 2.0 simulation benchmark, and delivers a +26.7\% boost on dynamic manipulation tasks.

cs.RO↗

arXiv2025

Guest metal-driven quantum anharmonic effects on stability and two-gap superconductivity in carbon-boron clathrates

Traditionally, strong quantum anharmonic effects have been considered a characteristic of hydrogen-rich compounds. Here we propose that these effects also play a decisive role in boron-carbon clathrates. The stability and superconducting transition temperature (Tc) of carbon-boron clathrates XYB6C6, whose metal atoms have an average oxidation state of +1.5, have long remained under debate. At this oxidation state, some combinations (e.g., RbSrB6C6) are dynamically stable, whereas others (e.g., RbPbB6C6) are not. Using the stochastic self-consistent harmonic approximation combined with machine learning, we find that the anharmonicity originates primarily from guest metal atoms. For comparison, we find that quantum fluctuations have negligible influence on SrB3C3, but remove the lattice instability of RbPbB6C6. The predicted Tc of RbPbB6C6 (88 K) is nearly twice that of SrB3C3. Moreover, RbPbB6C6 exhibits two-gap superconductivity due to the higher C/B ratio in the density of states at the Fermi level compared to SrB3C3, weakening the sp3 hybridization. These findings demonstrate that quantum anharmonicity crucially governs the stability and superconductivity of XYB6C6 clathrates.

cond-mat.supr-con↗

arXiv2025

StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition

Visual place recognition is a challenging task for autonomous driving and robotics, which is usually considered as an image retrieval problem. A commonly used two-stage strategy involves global retrieval followed by re-ranking using patch-level descriptors. Most deep learning-based methods in an end-to-end manner cannot extract global features with sufficient semantic information from RGB images. In contrast, re-ranking can utilize more explicit structural and semantic information in one-to-one matching process, but it is time-consuming. To bridge the gap between global retrieval and re-ranking and achieve a good trade-off between accuracy and efficiency, we propose StructVPR++, a framework that embeds structural and semantic knowledge into RGB global representations via segmentation-guided distillation. Our key innovation lies in decoupling label-specific features from global descriptors, enabling explicit semantic alignment between image pairs without requiring segmentation during deployment. Furthermore, we introduce a sample-wise weighted distillation strategy that prioritizes reliable training pairs while suppressing noisy ones. Experiments on four benchmarks demonstrate that StructVPR++ surpasses state-of-the-art global methods by 5-23% in Recall@1 and even outperforms many two-stage approaches, achieving real-time efficiency with a single RGB input.

cs.CV↗

arXiv2025

ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images

Place recognition is essential to maintain global consistency in large-scale localization systems. While research in urban environments has progressed significantly using LiDARs or cameras, applications in natural forest-like environments remain largely under-explored. Furthermore, forests present particular challenges due to high self-similarity and substantial variations in vegetation growth over time. In this work, we propose a robust LiDAR-based place recognition method for natural forests, ForestLPR. We hypothesize that a set of cross-sectional images of the forest's geometry at different heights contains the information needed to recognize revisiting a place. The cross-sectional images are represented by \ac{bev} density images of horizontal slices of the point cloud at different heights. Our approach utilizes a visual transformer as the shared backbone to produce sets of local descriptors and introduces a multi-BEV interaction module to attend to information at different heights adaptively. It is followed by an aggregation layer that produces a rotation-invariant place descriptor. We evaluated the efficacy of our method extensively on real-world data from public benchmarks as well as robotic datasets and compared it against the state-of-the-art (SOTA) methods. The results indicate that ForestLPR has consistently good performance on all evaluations and achieves an average increase of 7.38\% and 9.11\% on Recall@1 over the closest competitor on intra-sequence loop closure detection and inter-sequence re-localization, respectively, validating our hypothesis

cs.CV↗

arXiv2024

Complementing Onboard Sensors with Satellite Map: A New Perspective for HD Map Construction

High-definition (HD) maps play a crucial role in autonomous driving systems. Recent methods have attempted to construct HD maps in real-time using vehicle onboard sensors. Due to the inherent limitations of onboard sensors, which include sensitivity to detection range and susceptibility to occlusion by nearby vehicles, the performance of these methods significantly declines in complex scenarios and long-range detection tasks. In this paper, we explore a new perspective that boosts HD map construction through the use of satellite maps to complement onboard sensors. We initially generate the satellite map tiles for each sample in nuScenes and release a complementary dataset for further research. To enable better integration of satellite maps with existing methods, we propose a hierarchical fusion module, which includes feature-level fusion and BEV-level fusion. The feature-level fusion, composed of a mask generator and a masked cross-attention mechanism, is used to refine the features from onboard sensors. The BEV-level fusion mitigates the coordinate differences between features obtained from onboard sensors and satellite maps through an alignment module. The experimental results on the augmented nuScenes showcase the seamless integration of our module into three existing HD map construction methods. The satellite maps and our proposed module notably enhance their performance in both HD map semantic segmentation and instance detection tasks.

cs.CV↗

arXiv2023

InteractionNet: Joint Planning and Prediction for Autonomous Driving with Transformers

Planning and prediction are two important modules of autonomous driving and have experienced tremendous advancement recently. Nevertheless, most existing methods regard planning and prediction as independent and ignore the correlation between them, leading to the lack of consideration for interaction and dynamic changes of traffic scenarios. To address this challenge, we propose InteractionNet, which leverages transformer to share global contextual reasoning among all traffic participants to capture interaction and interconnect planning and prediction to achieve joint. Besides, InteractionNet deploys another transformer to help the model pay extra attention to the perceived region containing critical or unseen vehicles. InteractionNet outperforms other baselines in several benchmarks, especially in terms of safety, which benefits from the joint consideration of planning and forecasting. The code will be available at https://github.com/fujiawei0724/InteractionNet.

cs.RO↗

arXiv2023

MLF-DET: Multi-Level Fusion for Cross-Modal 3D Object Detection

In this paper, we propose a novel and effective Multi-Level Fusion network, named as MLF-DET, for high-performance cross-modal 3D object DETection, which integrates both the feature-level fusion and decision-level fusion to fully utilize the information in the image. For the feature-level fusion, we present the Multi-scale Voxel Image fusion (MVI) module, which densely aligns multi-scale voxel features with image features. For the decision-level fusion, we propose the lightweight Feature-cued Confidence Rectification (FCR) module which further exploits image semantics to rectify the confidence of detection candidates. Besides, we design an effective data augmentation strategy termed Occlusion-aware GT Sampling (OGS) to reserve more sampled objects in the training scenes, so as to reduce overfitting. Extensive experiments on the KITTI dataset demonstrate the effectiveness of our method. Notably, on the extremely competitive KITTI car 3D object detection benchmark, our method reaches 82.89% moderate AP and achieves state-of-the-art performance without bells and whistles.

cs.CV↗

arXiv2023

StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition

Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a more definitive source of structural knowledge input into a CNN network and applies knowledge distillation to avoid online segmentation and inference of seg-branch in testing. Considering that not all samples contain high-quality and helpful knowledge, and some even hurt the performance of distillation, we partition samples and weigh each sample's distillation loss to enhance the expected knowledge precisely. Finally, StructVPR achieves impressive performance on several benchmarks using only global retrieval and even outperforms many two-stage approaches by a large margin. After adding additional re-ranking, ours achieves state-of-the-art performance while maintaining a low computational cost.

cs.CV↗

arXiv2022

TransVPR: Transformer-based place recognition with multi-level attention aggregation

Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scenes often lead to deviations in the perception of visual place. To address this problem, it is crucial to integrate information from only task-relevant regions into image representations. In this paper, we introduce a novel holistic place recognition model, TransVPR, based on vision Transformers. It benefits from the desirable property of the self-attention operation in Transformers which can naturally aggregate task-relevant features. Attentions from multiple levels of the Transformer, which focus on different regions of interest, are further combined to generate a global image representation. In addition, the output tokens from Transformer layers filtered by the fused attention mask are considered as key-patch descriptors, which are used to perform spatial matching to re-rank the candidates retrieved by the global image features. The whole model allows end-to-end training with a single objective and image-level supervision. TransVPR achieves state-of-the-art performance on several real-world benchmarks while maintaining low computational time and storage requirements.

cs.CV↗

arXiv2021

Developing Dipole-scheme Heterojunction Photocatalysts

The high recombination rate of photogenerated carriers is the bottleneck of photocatalysis, severely limiting the photocatalytic efficiency. Here, we develop a dipole-scheme (D-scheme for short) photocatalytic model and materials realization. The D-scheme heterojunction not only can effectively separate electrons and holes by a large polarization field, but also boosts photocatalytic redox reactions with large driving photovoltages and without any carrier loss. By means of first-principles and GW calculations, we propose a D-scheme heterojunction prototype with two real polar materials, PtSeTe/LiGaS2. This D-scheme photocatalyst exhibits a high capability of the photogenerated carrier separation and near-infrared light absorption. Moreover, our calculations of the Gibbs free energy imply a high ability of the hydrogen and oxygen evolution reaction by a large driving force. The proposed D-scheme photocatalytic model is generalized and paves a valuable route of significantly improving the photocatalytic efficiency.

cond-mat.mtrl-sci↗

arXiv2019

Novel two-dimensional photocatalyst SnN3 for overall water splitting with enhanced visible-light absorption

We propose a novel excellent two-dimensional photocatalyst SnN3 monolayer using first-principles calculations. The stability of SnN3 monolayer have been examined via formation energy, phonon spectrum and ab initio molecular dynamics calculations. Large optical absorption capacity plays significant role in the enhancement of photocatalytic splitting of water. The SnN3 monolayer have ultra-high optical absorption capacity in visible region, which is as three and four times as that of SnP3 and MoS2 monolayer, respectively. Available potential and appropriate band positions indicating the ability of overall water splitting even in a wide strain range. Electronic properties of SnN3 monolayer can also be engineered effectively via the external strain, such as the conversion from in-direct band gap to direct band gap. The applied electric field splits the energy levels due to Stark effect, resulting in states accumulation and smaller gap width

cond-mat.mtrl-sci↗

arXiv2015

Novel lithium-nitrogen compounds at ambient and high pressures

Using ab initio evolutionary simulations, we predict the existence of five novel stable Li-N compounds at pressures from 0 to 100 GPa (Li13N, Li5N, Li3N2, LiN2, and LiN5). Structures of these compounds contain of isolated N ions, N2 dimers, polyacetylene-like N chains and N5 rings, respectively. The structure of Li13N consists of Li atoms and Li12N icosahedra (with N atom in the center of the Li12 icosahedron) such icosahedra are notdescribed by Wade-Jemmis electron counting rules and are unique. Electronic structure of Li-N compounds is found to dramatically depend on composition and pressure, making this system ideal for studying metal-insulator transitions. For example, LiN3 undergoes a sequence of pressure-induced transitions: metal-insulator-metal-insulator. This work resolves the previous controversies of theory and experiment on Li2N2.

cond-mat.mtrl-sci↗