Peng Jia

Xiuzhong Hu, Guangming Xiong, Zheng Zang et al.

Reconstructing large-scale 3D scenes is essential for autonomous vehicles, especially when partial sensor data is lost. Although the recently developed neural radiance fields (NeRF) have shown compelling results in implicit representations, the large-scale 3D scene reconstruction using partially lost LiDAR point cloud data still needs to be explored. To bridge this gap, we propose a novel 3D scene reconstruction framework called parent-child neural radiance field (PC-NeRF). The framework comprises two modules, the parent NeRF and the child NeRF, to simultaneously optimize scene-level, segment-level, and point-level scene representations. Sensor data can be utilized more efficiently by leveraging the segment-level representation capabilities of child NeRFs, and an approximate volumetric representation of the scene can be quickly obtained even with limited observations. With extensive experiments, our proposed PC-NeRF is proven to achieve high-precision 3D reconstruction in large-scale scenes. Moreover, PC-NeRF can effectively tackle situations where partial sensor data is lost and has high deployment efficiency with limited training time. Our approach implementation and the pre-trained models will be available at https://github.com/biter0088/pc-nerf.

Peng Jia, Ruiqi Sun, Nan Li et al.

Strong lensing in galaxy clusters probes properties of dense cores of dark matter halos in mass, studies the distant universe at flux levels and spatial resolutions otherwise unavailable, and constrains cosmological models independently. The next-generation large scale sky imaging surveys are expected to discover thousands of cluster-scale strong lenses, which would lead to unprecedented opportunities for applying cluster-scale strong lenses to solve astrophysical and cosmological problems. However, the large dataset challenges astronomers to identify and extract strong lensing signals, particularly strongly lensed arcs, because of their complexity and variety. Hence, we propose a framework to detect cluster-scale strongly lensed arcs, which contains a transformer-based detection algorithm and an image simulation algorithm. We embed prior information of strongly lensed arcs at cluster-scale into the training data through simulation and then train the detection algorithm with simulated images. We use the trained transformer to detect strongly lensed arcs from simulated and real data. Results show that our approach could achieve 99.63 % accuracy rate, 90.32 % recall rate, 85.37 % precision rate and 0.23 % false positive rate in detection of strongly lensed arcs from simulated images and could detect almost all strongly lensed arcs in real observation images. Besides, with an interpretation method, we have shown that our method could identify important information embedded in simulated data. Next step, to test the reliability and usability of our approach, we will apply it to available observations (e.g., DESI Legacy Imaging Surveys) and simulated data of upcoming large-scale sky surveys, such as the Euclid and the CSST.

Junpeng Jiang, Gangyi Hong, Lijun Zhou et al.

Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned problem, i.e. models built on top of Diffusion Transformers (DiT), works are still missing which are targeted on exploring the potential for multi-view videos generation scenarios. Noticeably, we propose the first DiT-based framework specifically designed for generating temporally and multi-view consistent videos which precisely match the given bird's-eye view layouts control. Specifically, the proposed framework leverages a parameter-free spatial view-inflated attention mechanism to guarantee the cross-view consistency, where joint cross-attention modules and ControlNet-Transformer are integrated to further improve the precision of control. To demonstrate our advantages, we extensively investigate the qualitative comparisons on nuScenes dataset, particularly in some most challenging corner cases. In summary, the effectiveness of our proposed method in producing long, controllable, and highly consistent videos under difficult conditions is proven to be effective.

Bu Jin, Yupeng Zheng, Pengfei Li et al.

3D dense captioning stands as a cornerstone in achieving a comprehensive understanding of 3D scenes through natural language. It has recently witnessed remarkable achievements, particularly in indoor settings. However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the domain gap between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the lack of data with comprehensive box-caption pair annotations specifically tailored for outdoor scenes. To this end, we introduce the new task of outdoor 3D dense captioning. As input, we assume a LiDAR point cloud and a set of RGB images captured by the panoramic camera rig. The expected output is a set of object boxes with captions. To tackle this task, we propose the TOD3Cap network, which leverages the BEV representation to generate object box proposals and integrates Relation Q-Former with LLaMA-Adapter to generate rich captions for these objects. We also introduce the TOD3Cap dataset, the largest one to our knowledge for 3D dense captioning in outdoor scenes, which contains 2.3M descriptions of 64.3K outdoor objects from 850 scenes. Notably, our TOD3Cap network can effectively localize and caption 3D objects in outdoor scenes, which outperforms baseline methods by a significant margin (+9.6 CiDEr@0.5IoU). Code, data, and models are publicly available at https://github.com/jxbbb/TOD3Cap.

Yulin Luo, Hao Chen, Zhuangzhe Wu et al.

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately interpreting and integrating visual observations conditioned on language instructions. Although recent works have sought to enhance the visual capabilities of VLA models, most approaches treat the LLM backbone as a black box, providing limited insight into how visual information is grounded into action generation. Therefore, we perform a systematic analysis of multiple VLA models across different action-generation paradigms and observe that sensitivity to visual tokens progressively decreases in deeper layers during action generation. Motivated by this observation, we propose \textbf{DeepVision-VLA}, built on a \textbf{Vision-Language Mixture-of-Transformers (VL-MoT)} framework. This framework enables shared attention between the vision foundation model and the VLA backbone, injecting multi-level visual features from the vision expert into deeper layers of the VLA backbone to enhance visual representations for precise and complex manipulation. In addition, we introduce \textbf{Action-Guided Visual Pruning (AGVP)}, which leverages shallow-layer attention to prune irrelevant visual tokens while preserving task-relevant ones, reinforcing critical visual cues for manipulation with minimal computational overhead. DeepVision-VLA outperforms prior state-of-the-art methods by 9.0\% and 7.5\% on simulated and real-world tasks, respectively, providing new insights for the design of visually enhanced VLA models.

Qinwen Xu, Jiaming Liu, Rui Zhou et al.

Despite strong generalization capabilities, Vision-Language-Action (VLA) models remain constrained by the high cost of expert demonstrations and insufficient real-world interaction. While online reinforcement learning (RL) has shown promise in improving general foundation models, applying RL to VLA manipulation in real-world settings is still hindered by low exploration efficiency and a restricted exploration space. Through systematic real-world experiments, we observe that the effective exploration space of online RL is closely tied to the data distribution of supervised fine-tuning (SFT). Motivated by this observation, we propose TwinRL, a digital twin-real-world collaborative RL framework designed to scale and guide exploration for VLA models. First, a high-fidelity digital twin is efficiently reconstructed from smartphone-captured scenes, enabling realistic bidirectional transfer between real and simulated environments. During the SFT warm-up stage, we introduce an exploration space expansion strategy using digital twins to broaden the support of the data trajectory distribution. Building on this enhanced initialization, we propose a sim-to-real guided exploration strategy to further accelerate online RL. Specifically, TwinRL performs efficient and parallel online RL in the digital twin prior to deployment, effectively bridging the gap between offline and online training stages. Subsequently, we exploit efficient digital twin sampling to identify failure-prone yet informative configurations, which are used to guide targeted human-in-the-loop rollouts on the real robot. In our experiments, TwinRL approaches 100% success in both in-distribution regions covered by real-world demonstrations and out-of-distribution regions, delivering at least a 30% speedup over prior real-world RL methods and requiring only about 20 minutes on average across four tasks.

Peng Jia, Jiameng Lv, Runyu Ning et al.

Large-scale astronomical surveys can capture numerous images of celestial objects, including galaxies and nebulae. Analysing and processing these images can reveal intricate internal structures of these objects, allowing researchers to conduct comprehensive studies on their morphology, evolution, and physical properties. However, varying noise levels and point spread functions can hamper the accuracy and efficiency of information extraction from these images. To mitigate these effects, we propose a novel image restoration algorithm that connects a deep learning-based restoration algorithm with a high-fidelity telescope simulator. During the training stage, the simulator generates images with different levels of blur and noise to train the neural network based on the quality of restored images. After training, the neural network can directly restore images obtained by the telescope, as represented by the simulator. We have tested the algorithm using real and simulated observation data and have found that it effectively enhances fine structures in blurry images and increases the quality of observation images. This algorithm can be applied to large-scale sky survey data, such as data obtained by LSST, Euclid, and CSST, to further improve the accuracy and efficiency of information extraction, promoting advances in the field of astronomical research.

Wenzhao Zheng, Junjie Wu, Yao Zheng et al.

Vision-based autonomous driving shows great potential due to its satisfactory performance and low costs. Most existing methods adopt dense representations (e.g., bird's eye view) or sparse representations (e.g., instance boxes) for decision-making, which suffer from the trade-off between comprehensiveness and efficiency. This paper explores a Gaussian-centric end-to-end autonomous driving (GaussianAD) framework and exploits 3D semantic Gaussians to extensively yet sparsely describe the scene. We initialize the scene with uniform 3D Gaussians and use surrounding-view images to progressively refine them to obtain the 3D Gaussian scene representation. We then use sparse convolutions to efficiently perform 3D perception (e.g., 3D detection, semantic map construction). We predict 3D flows for the Gaussians with dynamic semantics and plan the ego trajectory accordingly with an objective of future scene forecasting. Our GaussianAD can be trained in an end-to-end manner with optional perception labels when available. Extensive experiments on the widely used nuScenes dataset verify the effectiveness of our end-to-end GaussianAD on various tasks including motion planning, 3D occupancy prediction, and 4D occupancy forecasting. Code: https://github.com/wzzheng/GaussianAD.

Peng Jia, Wenbo Liu, Yuan Liu et al.

Lobster eye telescopes are ideal monitors to detect X-ray transients, because they could observe celestial objects over a wide field of view in X-ray band. However, images obtained by lobster eye telescopes are modified by their unique point spread functions, making it hard to design a high efficiency target detection algorithm. In this paper, we integrate several machine learning algorithms to build a target detection framework for data obtained by lobster eye telescopes. Our framework would firstly generate two 2D images with different pixel scales according to positions of photons on the detector. Then an algorithm based on morphological operations and two neural networks would be used to detect candidates of celestial objects with different flux from these 2D images. At last, a random forest algorithm will be used to pick up final detection results from candidates obtained by previous steps. Tested with simulated data of the Wide-field X-ray Telescope onboard the Einstein Probe, our detection framework could achieve over 94% purity and over 90% completeness for targets with flux more than 3 mCrab (9.6 * 10-11 erg/cm2/s) and more than 94% purity and moderate completeness for targets with lower flux at acceptable time cost. The framework proposed in this paper could be used as references for data processing methods developed for other lobster eye X-ray telescopes.

Tao Tang, Enhui Ma, xia zhou et al.

Autonomous driving has seen remarkable advancements, largely driven by extensive real-world data collection. However, acquiring diverse and corner-case data remains costly and inefficient. Generative models have emerged as a promising solution by synthesizing realistic sensor data. However, existing approaches primarily focus on single-modality generation, leading to inefficiencies and misalignment in multimodal sensor data. To address these challenges, we propose OminiGen, which generates aligned multimodal sensor data in a unified framework. Our approach leverages a shared Bird\u2019s Eye View (BEV) space to unify multimodal features and designs a novel generalizable multimodal reconstruction method, UAE, to jointly decode LiDAR and multi-view camera data. UAE achieves multimodal sensor decoding through volume rendering, enabling accurate and flexible reconstruction. Furthermore, we incorporate a Diffusion Transformer (DiT) with a ControlNet branch to enable controllable multimodal sensor generation. Our comprehensive experiments demonstrate that OminiGen achieves desired performances in unified multimodal sensor data generation with multimodal consistency and flexible sensor adjustments.

Yupeng Zheng, Pengxuan Yang, Zebin Xing et al.

End-to-end autonomous driving directly generates planning trajectories from raw sensor data, yet it typically relies on costly perception supervision to extract scene information. A critical research challenge arises: constructing an informative driving world model to enable perception annotation-free, end-to-end planning via self-supervised learning. In this paper, we present World4Drive, an end-to-end autonomous driving framework that employs vision foundation models to build latent world models for generating and evaluating multi-modal planning trajectories. Specifically, World4Drive first extracts scene features, including driving intention and world latent representations enriched with spatial-semantic priors provided by vision foundation models. It then generates multi-modal planning trajectories based on current scene features and driving intentions and predicts multiple intention-driven future states within the latent space. Finally, it introduces a world model selector module to evaluate and select the best trajectory. We achieve perception annotation-free, end-to-end planning through self-supervised alignment between actual future observations and predicted observations reconstructed from the latent space. World4Drive achieves state-of-the-art performance without manual perception annotations on both the open-loop nuScenes and closed-loop NavSim benchmarks, demonstrating an 18.1\% relative reduction in L2 error, 46.7% lower collision rate, and 3.75 faster training convergence. Codes will be accessed at https://github.com/ucaszyp/World4Drive.

Xiuzhong Hu, Guangming Xiong, Zheng Zang et al.

Large-scale 3D scene reconstruction and novel view synthesis are vital for autonomous vehicles, especially utilizing temporally sparse LiDAR frames. However, conventional explicit representations remain a significant bottleneck towards representing the reconstructed and synthetic scenes at unlimited resolution. Although the recently developed neural radiance fields (NeRF) have shown compelling results in implicit representations, the problem of large-scale 3D scene reconstruction and novel view synthesis using sparse LiDAR frames remains unexplored. To bridge this gap, we propose a 3D scene reconstruction and novel view synthesis framework called parent-child neural radiance field (PC-NeRF). Based on its two modules, parent NeRF and child NeRF, the framework implements hierarchical spatial partitioning and multi-level scene representation, including scene, segment, and point levels. The multi-level scene representation enhances the efficient utilization of sparse LiDAR point cloud data and enables the rapid acquisition of an approximate volumetric scene representation. With extensive experiments, PC-NeRF is proven to achieve high-precision novel LiDAR view synthesis and 3D reconstruction in large-scale scenes. Moreover, PC-NeRF can effectively handle situations with sparse LiDAR frames and demonstrate high deployment efficiency with limited training epochs. Our approach implementation and the pre-trained models are available at https://github.com/biter0088/pc-nerf.

Miao Zhang, Peng Jia, Zhengyang Li et al.

Sky survey telescopes play a critical role in modern astronomy, but misalignment of their optical elements can introduce significant variations in point spread functions, leading to reduced data quality. To address this, we need a method to obtain misalignment states, aiding in the reconstruction of accurate point spread functions for data processing methods or facilitating adjustments of optical components for improved image quality. Since sky survey telescopes consist of many optical elements, they result in a vast array of potential misalignment states, some of which are intricately coupled, posing detection challenges. However, by continuously adjusting the misalignment states of optical elements, we can disentangle coupled states. Based on this principle, we propose a deep neural network to extract misalignment states from continuously varying point spread functions in different field of views. To ensure sufficient and diverse training data, we recommend employing a digital twin to obtain data for neural network training. Additionally, we introduce the state graph to store misalignment data and explore complex relationships between misalignment states and corresponding point spread functions, guiding the generation of training data from experiments. Once trained, the neural network estimates misalignment states from observation data, regardless of the impacts caused by atmospheric turbulence, noise, and limited spatial sampling rates in the detector. The method proposed in this paper could be used to provide prior information for the active optics system and the optical system alignment.

Xiaoyu Tian, Junru Gu, Bailin Li et al.

A primary hurdle of autonomous driving in urban environments is understanding complex and long-tail scenarios, such as challenging road conditions and delicate human behaviors. We introduce DriveVLM, an autonomous driving system leveraging Vision-Language Models (VLMs) for enhanced scene understanding and planning capabilities. DriveVLM integrates a unique combination of reasoning modules for scene description, scene analysis, and hierarchical planning. Furthermore, recognizing the limitations of VLMs in spatial reasoning and heavy computational requirements, we propose DriveVLM-Dual, a hybrid system that synergizes the strengths of DriveVLM with the traditional autonomous driving pipeline. Experiments on both the nuScenes dataset and our SUP-AD dataset demonstrate the efficacy of DriveVLM and DriveVLM-Dual in handling complex and unpredictable driving conditions. Finally, we deploy the DriveVLM-Dual on a production vehicle, verifying it is effective in real-world autonomous driving environments.

Jia Hu, Junqi Li, Weimeng Lin et al.

Vehicle Dispatching Systems (VDSs) are critical to the operational efficiency of Automated Container Terminals (ACTs). However, their widespread commercialization is hindered due to their low transferability across diverse terminals. This transferability challenge stems from three limitations: high reliance on port operational specialists, a high demand for terminal-specific data, and time-consuming manual deployment processes. Leveraging the emergence of Large Language Models (LLMs), this paper proposes PortAgent, an LLM-driven vehicle dispatching agent that fully automates the VDS transferring workflow. It bears three features: (1) no need for port operations specialists; (2) low need of data; and (3) fast deployment. Specifically, specialist dependency is eliminated by the Virtual Expert Team (VET). The VET collaborates with four virtual experts, including a Knowledge Retriever, Modeler, Coder, and Debugger, to emulate a human expert team for the VDS transferring workflow. These experts specialize in the domain of terminal VDS via a few-shot example learning approach. Through this approach, the experts are able to learn VDS-domain knowledge from a few VDS examples. These examples are retrieved via a Retrieval-Augmented Generation (RAG) mechanism, mitigating the high demand for terminal-specific data. Furthermore, an automatic VDS design workflow is established among these experts to avoid extra manual interventions. In this workflow, a self-correction loop inspired by the LLM Reflexion framework is created

Xingchen Zhou, Nan Li, Peng Jia et al.

Source extraction is crucial in analyzing data from next-generation, large-scale sky surveys in radio bands, such as the Square Kilometre Array (SKA). Several source extraction programs, including SoFiA and Aegean, have been developed to address this challenge. However, finding optimal parameter configurations when applying these programs to real observations is non-trivial. For example, the outcomes of SoFiA intensely depend on several key parameters across its preconditioning, source-finding, and reliability-filtering modules. To address this issue, we propose a framework to automatically optimize these parameters using an AI agent based on a state-of-the-art reinforcement learning (RL) algorithm, i.e., Soft Actor-Critic (SAC). The SKA Science Data Challenge 2 (SDC2) dataset is utilized to assess the feasibility and reliability of this framework. The AI agent interacts with the environment by adjusting parameters based on the feedback from the SDC2 score defined by the SDC2 Team, progressively learning to select parameter sets that yield improved performance. After sufficient training, the AI agent can automatically identify an optimal parameter configuration that outperform the benchmark set by Team SoFiA within only 100 evaluation steps and with reduced time consumption. Our approach could address similar problems requiring complex parameter tuning, beyond radio band surveys and source extraction. Yet, high-quality training sets containing representative observations and catalogs of ground truth are essential.

Qiuxuan Feng, Jiale Yu, Jiaming Liu et al.

World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: the "Imagine-then-Execute" approach, which uses video prediction to infer actions via inverse dynamics, and the "Joint Modeling" approach, which jointly models actions and video representations. Based on systematic experiments, we observe a fundamental trade-off between these paradigms: the former explicitly leverages world models for generalizable transit but lacks interaction precision, whereas the latter enables fine-grained, temporally coherent action generation but is constrained by the exploration space of the training distribution. Motivated by these findings, we propose HarmoWAM, an end-to-end WAM that fully leverages a world model to unify predictive and reactive control, enabling both generalizable transit and precise manipulation. Specifically, the world model provides spatio-temporal physical priors that condition two complementary action experts: a predictive expert that leverages latent dynamics for iterative action generation, and a reactive expert that directly infers actions from predicted visual evolution. To enable adaptive coordination, a Process-Adaptive Gating Mechanism is proposed to automatically determine the timing and location of switching between them. This allows the world model to drive the reactive expert to expand the exploration space and the predictive expert to perform precise interactions across different stages of a task. For evaluation, we construct three training-unseen test environments across six real-world robotic tasks, covering variations in background, position, and object semantics. Notably, HarmoWAM achieves strong zero-shot generalization across these scenarios, significantly outperforming prior state-of-the-art VLA models and WAMs by margins of 33% and 29%, respectively.

Peng Jia, Zhen Xiao, Jia Li et al.

High-quality, real-time talking head synthesis remains a fundamental challenge in computer vision. Existing reconstruction- and rendering-based methods typically rely on identity-specific models, limiting cross-identity generalization. To address this issue, we propose SDTalk, a one-shot 3D Gaussian Splatting (3DGS)-based framework that generalizes to unseen identities without personalized training or fine-tuning. Our framework comprises two modules with a two-stage training strategy. In the first stage, we incorporate structured facial priors into the reconstruction module and separately predict 3DGS parameters for visible and occluded regions, enabling complete head reconstruction from a single image. In the second stage, we introduce a dual-branch motion field to model coarse and fine facial dynamics, improving detail fidelity and lip synchronization. Experiments demonstrate that SDTalk surpasses existing methods in both visual quality and inference efficiency.

Chaojun Ni, Guosheng Zhao, Xiaofeng Wang et al.

Closed-loop simulation is crucial for end-to-end autonomous driving. Existing sensor simulation methods (e.g., NeRF and 3DGS) reconstruct driving scenes based on conditions that closely mirror training data distributions. However, these methods struggle with rendering novel trajectories, such as lane changes. Recent works have demonstrated that integrating world model knowledge alleviates these issues. Despite their efficiency, these approaches still encounter difficulties in the accurate representation of more complex maneuvers, with multi-lane shifts being a notable example. Therefore, we introduce ReconDreamer, which enhances driving scene reconstruction through incremental integration of world model knowledge. Specifically, DriveRestorer is proposed to mitigate artifacts via online restoration. This is complemented by a progressive data update strategy designed to ensure high-quality rendering for more complex maneuvers. To the best of our knowledge, ReconDreamer is the first method to effectively render in large maneuvers. Experimental results demonstrate that ReconDreamer outperforms Street Gaussians in the NTA-IoU, NTL-IoU, and FID, with relative improvements by 24.87%, 6.72%, and 29.97%. Furthermore, ReconDreamer surpasses DriveDreamer4D with PVG during large maneuver rendering, as verified by a relative improvement of 195.87% in the NTA-IoU metric and a comprehensive user study.

Hao Chen, Jiaming Liu, Zhonghao Yan et al.

Vision-Language-Action (VLA) models have increasingly incorporated reasoning mechanisms for complex robotic manipulation. However, existing approaches share a critical limitation: whether employing explicit linguistic reasoning that suffers from latency and discretization, or utilizing more expressive continuous latent reasoning, they are predominantly confined to static imitation learning that limits adaptability and generalization. While online reinforcement learning (RL) has been introduced to VLAs to enable trial-and-error exploration, current methods exclusively optimize the vanilla action space, bypassing the underlying physical reasoning process. In this paper, we present \textbf{LaST-R1}, a unified VLA framework that integrates latent Chain-of-Thought (CoT) reasoning over physical dynamics prior to action execution, along with a tailored RL post-training paradigm. Specifically, we propose \textbf{Latent-to-Action Policy Optimization (LAPO)}, a novel RL algorithm that jointly optimizes the latent reasoning process and the action generation. By bridging reasoning and control, LAPO improves the representation of physical world modeling and enhances robustness in interactive environments. Furthermore, an \textbf{adaptive latent CoT mechanism} is introduced to allow the policy to dynamically adjust its reasoning horizon based on environment complexity. Extensive experiments show that LaST-R1 achieves a near-perfect 99.8\% average success rate on the LIBERO benchmark with only one-shot supervised warm-up, significantly improving convergence speed and performance over prior state-of-the-art methods. In real-world deployments, LAPO post-training yields up to a 44\% improvement over the initial warm-up policy across four complex tasks, including both single-arm and dual-arm settings. Finally, LaST-R1 demonstrates strong generalization across simulated and real-world environments.

Qiao Sun, Huimin Wang, Jiahao Zhan et al.

Large real-world driving datasets have sparked significant research into various aspects of data-driven motion planners for autonomous driving. These include data augmentation, model architecture, reward design, training strategies, and planner pipelines. These planners promise better generalizations on complicated and few-shot cases than previous methods. However, experiment results show that many of these approaches produce limited generalization abilities in planning performance due to overly complex designs or training paradigms. In this paper, we review and benchmark previous methods focusing on generalizations. The experimental results indicate that as models are appropriately scaled, many design elements become redundant. We introduce StateTransformer-2 (STR2), a scalable, decoder-only motion planner that uses a Vision Transformer (ViT) encoder and a mixture-of-experts (MoE) causal Transformer architecture. The MoE backbone addresses modality collapse and reward balancing by expert routing during training. Extensive experiments on the NuPlan dataset show that our method generalizes better than previous approaches across different test sets and closed-loop simulations. Furthermore, we assess its scalability on billions of real-world urban driving scenarios, demonstrating consistent accuracy improvements as both data and model size grow.

Tao Tang, Dafeng Wei, Zhengyu Jia et al.

The rapid development of the autonomous driving industry has led to a significant accumulation of autonomous driving data. Consequently, there comes a growing demand for retrieving data to provide specialized optimization. However, directly applying previous image retrieval methods faces several challenges, such as the lack of global feature representation and inadequate text retrieval ability for complex driving scenes. To address these issues, firstly, we propose the BEV-TSR framework which leverages descriptive text as an input to retrieve corresponding scenes in the Bird's Eye View (BEV) space. Then to facilitate complex scene retrieval with extensive text descriptions, we employ a large language model (LLM) to extract the semantic features of the text inputs and incorporate knowledge graph embeddings to enhance the semantic richness of the language embedding. To achieve feature alignment between the BEV feature and language embedding, we propose Shared Cross-modal Embedding with a set of shared learnable embeddings to bridge the gap between these two modalities, and employ a caption generation task to further enhance the alignment. Furthermore, there lack of well-formed retrieval datasets for effective evaluation. To this end, we establish a multi-level retrieval dataset, nuScenes-Retrieval, based on the widely adopted nuScenes dataset. Experimental results on the multi-level nuScenes-Retrieval show that BEV-TSR achieves state-of-the-art performance, e.g., 85.78% and 87.66% top-1 accuracy on scene-to-text and text-to-scene retrieval respectively. Codes and datasets will be available.

Derun Li, Changye Li, Yue Wang et al.

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.

Anthony Chen, Wenzhao Zheng, Yida Wang et al.

Recent advancements in world models have revolutionized dynamic environment simulation, allowing systems to foresee future states and assess potential actions. In autonomous driving, these capabilities help vehicles anticipate the behavior of other road users, perform risk-aware planning, accelerate training in simulation, and adapt to novel scenarios, thereby enhancing safety and reliability. Current approaches exhibit deficiencies in maintaining robust 3D geometric consistency or accumulating artifacts during occlusion handling, both critical for reliable safety assessment in autonomous navigation tasks. To address this, we introduce GeoDrive, which explicitly integrates robust 3D geometry conditions into driving world models to enhance spatial understanding and action controllability. Specifically, we first extract a 3D representation from the input frame and then obtain its 2D rendering based on the user-specified ego-car trajectory. To enable dynamic modeling, we propose a dynamic editing module during training to enhance the renderings by editing the positions of the vehicles. Extensive experiments demonstrate that our method significantly outperforms existing models in both action accuracy and 3D spatial awareness, leading to more realistic, adaptable, and reliable scene modeling for safer autonomous driving. Additionally, our model can generalize to novel trajectories and offers interactive scene editing capabilities, such as object editing and object trajectory control.

Jia Li, Yangchen Yu, Yin Chen et al.

Engagement estimation plays a crucial role in understanding human social behaviors, attracting increasing research interests in fields such as affective computing and human-computer interaction. In this paper, we propose a Dialogue-Aware Transformer framework (DAT) with Modality-Group Fusion (MGF), which relies solely on audio-visual input and is language-independent, for estimating human engagement in conversations. Specifically, our method employs a modality-group fusion strategy that independently fuses audio and visual features within each modality for each person before inferring the entire audio-visual content. This strategy significantly enhances the model's performance and robustness. Additionally, to better estimate the target participant's engagement levels, the introduced Dialogue-Aware Transformer considers both the participant's behavior and cues from their conversational partners. Our method was rigorously tested in the Multi-Domain Engagement Estimation Challenge held by MultiMediate'24, demonstrating notable improvements in engagement-level regression precision over the baseline model. Notably, our approach achieves a CCC score of 0.76 on the NoXi Base test set and an average CCC of 0.64 across the NoXi Base, NoXi-Add, and MPIIGI test sets.

Jian Zhu, Zhengyu Jia, Tian Gao et al.

Advanced end-to-end autonomous driving systems predict other vehicles' motions and plan ego vehicle's trajectory. The world model that can foresee the outcome of the trajectory has been used to evaluate the autonomous driving system. However, existing world models predominantly emphasize the trajectory of the ego vehicle and leave other vehicles uncontrollable. This limitation hinders their ability to realistically simulate the interaction between the ego vehicle and the driving scenario. In this paper, we propose a driving World Model named EOT-WM, unifying Ego-Other vehicle Trajectories in videos for driving simulation. Specifically, it remains a challenge to match multiple trajectories in the BEV space with each vehicle in the video to control the video generation. We first project ego-other vehicle trajectories in the BEV space into the image coordinate for vehicle-trajectory match via pixel positions. Then, trajectory videos are encoded by the Spatial-Temporal Variational Auto Encoder to align with driving video latents spatially and temporally in the unified visual space. A trajectory-injected diffusion Transformer is further designed to denoise the noisy video latents for video generation with the guidance of ego-other vehicle trajectories. In addition, we propose a metric based on control latent similarity to evaluate the controllability of trajectories. Extensive experiments are conducted on the nuScenes dataset, and the proposed model outperforms the state-of-the-art method by 30% in FID and 55% in FVD. The model can also predict unseen driving scenes with self-produced trajectories.

Yuchun Wang, Cheng Gong, Jianwei Gong et al.

Driving in an off-road environment is challenging for autonomous vehicles due to the complex and varied terrain. To ensure stable and efficient travel, the vehicle requires consideration and balancing of environmental factors, such as undulations, roughness, and obstacles, to generate optimal trajectories that can adapt to changing scenarios. However, traditional motion planners often utilize a fixed cost function for trajectory optimization, making it difficult to adapt to different driving strategies in challenging irregular terrains and uncommon scenarios. To address these issues, we propose an adaptive motion planner based on human-like cognition and cost evaluation for off-road driving. First, we construct a multi-layer map describing different features of off-road terrains, including terrain elevation, roughness, obstacle, and artificial potential field map. Subsequently, we employ a CNN-LSTM network to learn the trajectories planned by human drivers in various off-road scenarios. Then, based on human-like generated trajectories in different environments, we design a primitive-based trajectory planner that aims to mimic human trajectories and cost weight selection, generating trajectories that are consistent with the dynamics of off-road vehicles. Finally, we compute optimal cost weights and select and extend behavioral primitives to generate highly adaptive, stable, and efficient trajectories. We validate the effectiveness of the proposed method through experiments in a desert off-road environment with complex terrain and varying road conditions. The experimental results show that the proposed human-like motion planner has excellent adaptability to different off-road conditions. It shows real-time operation, greater stability, and more human-like planning ability in diverse and challenging scenarios.

Titong Jiang, Xuefeng Jiang, Yuan Ma et al.

We present LightVLA, a simple yet effective differentiable token pruning framework for vision-language-action (VLA) models. While VLA models have shown impressive capability in executing real-world robotic tasks, their deployment on resource-constrained platforms is often bottlenecked by the heavy attention-based computation over large sets of visual tokens. LightVLA addresses this challenge through adaptive, performance-driven pruning of visual tokens: It generates dynamic queries to evaluate visual token importance, and adopts Gumbel softmax to enable differentiable token selection. Through fine-tuning, LightVLA learns to preserve the most informative visual tokens while pruning tokens which do not contribute to task execution, thereby improving efficiency and performance simultaneously. Notably, LightVLA requires no heuristic magic numbers and introduces no additional trainable parameters, making it compatible with modern inference frameworks. Experimental results demonstrate that LightVLA outperforms different VLA models and existing token pruning methods across diverse tasks on the LIBERO benchmark, achieving higher success rates with substantially reduced computational overhead. Specifically, LightVLA reduces FLOPs and latency by 59.1% and 38.2% respectively, with a 2.6% improvement in task success rate. Meanwhile, we also investigate the learnable query-based token pruning method LightVLA* with additional trainable parameters, which also achieves satisfactory performance. Our work reveals that as VLA pursues optimal performance, LightVLA spontaneously learns to prune tokens from a performance-driven perspective. To the best of our knowledge, LightVLA is the first work to apply adaptive visual token pruning to VLA tasks with the collateral goals of efficiency and performance, marking a significant step toward more efficient, powerful and practical real-time robotic systems.

Mingxiang Fu, Yu Song, Jiameng Lv et al.

The exponential growth of astronomical datasets provides an unprecedented opportunity for humans to gain insight into the Universe. However, effectively analyzing this vast amount of data poses a significant challenge. Astronomers are turning to deep learning techniques to address this, but the methods are limited by their specific training sets, leading to considerable duplicate workloads too. Hence, as an example to present how to overcome the issue, we built a framework for general analysis of galaxy images, based on a large vision model (LVM) plus downstream tasks (DST), including galaxy morphological classification, image restoration, object detection, parameter extraction, and more. Considering the low signal-to-noise ratio of galaxy images and the imbalanced distribution of galaxy categories, we have incorporated a Human-in-the-loop (HITL) module into our large vision model, which leverages human knowledge to enhance the reliability and interpretability of processing galaxy images interactively. The proposed framework exhibits notable few-shot learning capabilities and versatile adaptability to all the abovementioned tasks on galaxy images in the DESI legacy imaging surveys. Expressly, for object detection, trained by 1000 data points, our DST upon the LVM achieves an accuracy of 96.7%, while ResNet50 plus Mask R-CNN gives an accuracy of 93.1%; for morphology classification, to obtain AUC ~0.9, LVM plus DST and HITL only requests 1/50 training sets compared to ResNet18. Expectedly, multimodal data can be integrated similarly, which opens up possibilities for conducting joint analyses with datasets spanning diverse domains in the era of multi-message astronomy.

Xu Li, Ruiqi Sun, Jiameng Lv et al.

Strong gravitational lensing is a powerful tool for investigating dark matter and dark energy properties. With the advent of large-scale sky surveys, we can discover strong lensing systems on an unprecedented scale, which requires efficient tools to extract them from billions of astronomical objects. The existing mainstream lens-finding tools are based on machine learning algorithms and applied to cut-out-centered galaxies. However, according to the design and survey strategy of optical surveys by CSST, preparing cutouts with multiple bands requires considerable efforts. To overcome these challenges, we have developed a framework based on a hierarchical visual Transformer with a sliding window technique to search for strong lensing systems within entire images. Moreover, given that multi-color images of strong lensing systems can provide insights into their physical characteristics, our framework is specifically crafted to identify strong lensing systems in images with any number of channels. As evaluated using CSST mock data based on an Semi-Analytic Model named CosmoDC2, our framework achieves precision and recall rates of 0.98 and 0.90, respectively. To evaluate the effectiveness of our method in real observations, we have applied it to a subset of images from the DESI Legacy Imaging Surveys and media images from Euclid Early Release Observations. 61 new strong lensing system candidates are discovered by our method. However, we also identified false positives arising primarily from the simplified galaxy morphology assumptions within the simulation. This underscores the practical limitations of our approach while simultaneously highlighting potential avenues for future improvements.

Junshan Hu, Jialiang Mao, Zhikang Liu et al.

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary computational overhead in simpler tasks, whereas insufficient tokens compromise fine-grained visual comprehension in more complex contexts. To overcome these limitations, we present TokenFLEX, an innovative and adaptable vision-language framework that encodes images into a variable number of tokens for efficient integration with a Large Language Model (LLM). Our approach is underpinned by two pivotal innovations. Firstly, we present a novel training paradigm that enhances performance across varying numbers of vision tokens by stochastically modulating token counts during training. Secondly, we design a lightweight vision token projector incorporating an adaptive pooling layer and SwiGLU, allowing for flexible downsampling of vision tokens and adaptive selection of features tailored to specific token counts. Comprehensive experiments reveal that TokenFLEX consistently outperforms its fixed-token counterparts, achieving notable performance gains across various token counts enhancements of 1.6%, 1.0%, and 0.4% with 64, 144, and 256 tokens, respectively averaged over eight vision-language benchmarks. These results underscore TokenFLEX's remarkable flexibility while maintaining high-performance vision-language understanding.

Bu Jin, Weize Li, Baihan Yang et al.

Recent advancements in autonomous driving (AD) systems have highlighted the potential of world models in achieving robust and generalizable performance across both ordinary and challenging driving conditions. However, a key challenge remains: precise and flexible camera pose control, which is crucial for accurate viewpoint transformation and realistic simulation of scene dynamics. In this paper, we introduce PosePilot, a lightweight yet powerful framework that significantly enhances camera pose controllability in generative world models. Drawing inspiration from self-supervised depth estimation, PosePilot leverages structure-from-motion principles to establish a tight coupling between camera pose and video generation. Specifically, we incorporate self-supervised depth and pose readouts, allowing the model to infer depth and relative camera motion directly from video sequences. These outputs drive pose-aware frame warping, guided by a photometric warping loss that enforces geometric consistency across synthesized frames. To further refine camera pose estimation, we introduce a reverse warping step and a pose regression loss, improving viewpoint precision and adaptability. Extensive experiments on autonomous driving and general-domain video datasets demonstrate that PosePilot significantly enhances structural understanding and motion reasoning in both diffusion-based and auto-regressive world models. By steering camera pose with self-supervised depth, PosePilot sets a new benchmark for pose controllability, enabling physically consistent, reliable viewpoint synthesis in generative world models.

Yangche Yu, Yin Chen, Jia Li et al.

Accurate engagement estimation is essential for adaptive human-computer interaction systems, yet robust deployment is hindered by poor generalizability across diverse domains and challenges in modeling complex interaction dynamics.To tackle these issues, we propose DAPA (Domain-Adaptive Parallel Attention), a novel framework for generalizable conversational engagement modeling. DAPA introduces a Domain Prompting mechanism by prepending learnable domain-specific vectors to the input, explicitly conditioning the model on the data's origin to facilitate domain-aware adaptation while preserving generalizable engagement representations. To capture interactional synchrony, the framework also incorporates a Parallel Cross-Attention module that explicitly aligns reactive (forward BiLSTM) and anticipatory (backward BiLSTM) states between participants.Extensive experiments demonstrate that DAPA establishes a new state-of-the-art performance on several cross-cultural and cross-linguistic benchmarks, notably achieving an absolute improvement of 0.45 in Concordance Correlation Coefficient (CCC) over a strong baseline on the NoXi-J test set. The superiority of our method was also confirmed by winning the first place in the Multi-Domain Engagement Estimation Challenge at MultiMediate'25.

Xuefeng Jiang, Yuan Ma, Pengxiang Li et al.

In recent years, diffusion models have demonstrated remarkable potential across diverse domains, from vision generation to language modeling. Transferring its generative capabilities to modern end-to-end autonomous driving systems has also emerged as a promising direction. However, existing diffusion-based trajectory generative models often exhibit mode collapse where different random noises converge to similar trajectories after the denoising process.Therefore, state-of-the-art models often rely on anchored trajectories from pre-defined trajectory vocabulary or scene priors in the training set to mitigate collapse and enrich the diversity of generated trajectories, but such inductive bias are not available in real-world deployment, which can be challenged when generalizing to unseen scenarios. In this work, we investigate the possibility of effectively tackling the mode collapse challenge without the assumption of pre-defined trajectory vocabulary or pre-computed scene priors. Specifically, we propose TransDiffuser, an encoder-decoder based generative trajectory planning model, where the encoded scene information and motion states serve as the multi-modal conditional input of the denoising decoder. Different from existing approaches, we exploit a simple yet effective multi-modal representation decorrelation optimization mechanism during the denoising process to enrich the latent representation space which better guides the downstream generation. Without any predefined trajectory anchors or pre-computed scene priors, TransDiffuser achieves the PDMS of 94.85 on the closed-loop planning-oriented benchmark NAVSIM, surpassing previous state-of-the-art methods. Qualitative evaluation further showcases TransDiffuser generates more diverse and plausible trajectories which explore more drivable area.

Peng Jia, Ge Li, Bafeng Cheng et al.

Fast moving celestial objects are characterized by velocities across the celestial sphere that significantly differ from the motions of background stars. In observational images, these objects exhibit distinct shapes, contrasting with the typical appearances of stars. Depending on the observational method employed, these celestial entities may be designated as near-Earth objects or asteroids. Historically, fast moving celestial objects have been observed using ground-based telescopes, where the relative stability of stars and Earth facilitated effective image differencing techniques alongside traditional fast moving celestial object detection and classification algorithms. However, the growing prevalence of space-based telescopes, along with their diverse observational modes, produces images with different properties, rendering conventional methods less effective. This paper presents a novel algorithm for detecting fast moving celestial objects within star fields. Our approach enhances state-of-the-art fast moving celestial object detection neural networks by transforming them into physical-inspired neural networks. These neural networks leverage the point spread function of the telescope and the specific observational mode as prior information; they can directly identify moving fast moving celestial objects within star fields without requiring additional training, thereby addressing the limitations of traditional techniques. Additionally, all neural networks are integrated using the mixture of experts technique, forming a comprehensive fast moving celestial object detection algorithm. We have evaluated our algorithm using simulated observational data that mimics various observations carried out by space based telescope scenarios and real observation images. Results demonstrate that our method effectively detects fast moving celestial objects across different observational modes.

Yuyin Chen, Yida Wang, Xueyang Zhang et al.

Urban scene reconstruction requires modeling both static infrastructure and dynamic elements while supporting diverse environmental conditions. We present \textbf{StyledStreets}, a multi-style street simulator that achieves instruction-driven scene editing with guaranteed spatial and temporal consistency. Building on a state-of-the-art Gaussian Splatting framework for street scenarios enhanced by our proposed pose optimization and multi-view training, our method enables photorealistic style transfers across seasons, weather conditions, and camera setups through three key innovations: First, a hybrid embedding scheme disentangles persistent scene geometry from transient style attributes, allowing realistic environmental edits while preserving structural integrity. Second, uncertainty-aware rendering mitigates supervision noise from diffusion priors, enabling robust training across extreme style variations. Third, a unified parametric model prevents geometric drift through regularized updates, maintaining multi-view consistency across seven vehicle-mounted cameras. Our framework preserves the original scene's motion patterns and geometric relationships. Qualitative results demonstrate plausible transitions between diverse conditions (snow, sandstorm, night), while quantitative evaluations show state-of-the-art geometric accuracy under style transfers. The approach establishes new capabilities for urban simulation, with applications in autonomous vehicle testing and augmented reality systems requiring reliable environmental consistency. Codes will be publicly available upon publication.

Yuru Wang, Pei Liu, Songtao Wang et al.

Open-world 3D scene understanding is a critical challenge that involves recognizing and distinguishing diverse objects and categories from 3D data, such as point clouds, without relying on manual annotations. Traditional methods struggle with this open-world task, especially due to the limitations of constructing extensive point cloud-text pairs and handling multimodal data effectively. In response to these challenges, we present UniPLV, a robust framework that unifies point clouds, images, and text within a single learning paradigm for comprehensive 3D scene understanding. UniPLV leverages images as a bridge to co-embed 3D points with pre-aligned images and text in a shared feature space, eliminating the need for labor-intensive point cloud-text pair crafting. Our framework achieves precise multimodal alignment through two innovative strategies: (i) Logit and feature distillation modules between images and point clouds to enhance feature coherence; (ii) A vision-point matching module that implicitly corrects 3D semantic predictions affected by projection inaccuracies from points to pixels. To further boost performance, we implement four task-specific losses alongside a two-stage training strategy. Extensive experiments demonstrate that UniPLV significantly surpasses state-of-the-art methods, with average improvements of 15.6% and 14.8% in semantic segmentation for Base-Annotated and Annotation-Free tasks, respectively. These results underscore UniPLV's efficacy in pushing the boundaries of open-world 3D scene understanding. We will release the code to support future research and development.

Chengyuan Ma, Peng Jia, Hongyue Guo et al.

Existing generative models for unsupervised anomalous sound detection are limited by their inability to fully capture the complex feature distribution of normal sounds, while the potential of powerful diffusion models in this domain remains largely unexplored. To address this challenge, we propose a novel framework, TLDiffGAN, which consists of two complementary branches. One branch incorporates a latent diffusion model into the GAN generator for adversarial training, thereby making the discriminator's task more challenging and improving the quality of generated samples. The other branch leverages pretrained audio model encoders to extract features directly from raw audio waveforms for auxiliary discrimination. This framework effectively captures feature representations of normal sounds from both raw audio and Mel spectrograms. Moreover, we introduce a TMixup spectrogram augmentation technique to enhance sensitivity to subtle and localized temporal patterns that are often overlooked. Extensive experiments on the DCASE 2020 Challenge Task 2 dataset demonstrate the superior detection performance of TLDiffGAN, as well as its strong capability in anomalous time-frequency localization.

Chengyuan Ma, Peng Jia, Hongyue Guo et al.

The core challenge in industrial equipment anoma lous sound detection (ASD) lies in modeling the time-frequency coupling characteristics of acoustic features. Existing modeling methods are limited by local receptive fields, making it difficult to capture long-range temporal patterns and cross-band dynamic coupling effects in machine acoustic features. In this paper, we propose a novel framework, ESTM, which is based on a dual-path Mamba architecture with time-frequency decoupled modeling and utilizes Selective State-Space Models (SSM) for long-range sequence modeling. ESTM extracts rich feature representations from different time segments and frequency bands by fusing enhanced Mel spectrograms and raw audio features, while further improving sensitivity to anomalous patterns through the TriStat-Gating (TSG) module. Our experiments demonstrate that ESTM improves anomalous detection performance on the DCASE 2020 Task 2 dataset, further validating the effectiveness of the proposed method.

Pei Liu, Qingtian Ning, Xinyan Lu et al.

Recent advances in vision-language models (VLMs) have demonstrated impressive spatial reasoning capabilities for autonomous driving, yet existing methods predominantly focus on static scene understanding while neglecting the essential temporal dimension of real-world driving scenarios. To address this critical limitation, we propose the OmniReason framework, which establishes robust spatiotemporal reasoning by jointly modeling dynamic 3D environments and their underlying decision-making processes. Our work makes two fundamental advances: (1) We introduce OmniReason-Data, two large-scale vision-language-action (VLA) datasets with dense spatiotemporal annotations and natural language explanations, generated through a novel hallucination-mitigated auto-labeling pipeline that ensures both physical plausibility and temporal coherence; (2) We develop the OmniReason-Agent architecture, which integrates a sparse temporal memory module for persistent scene context modeling and an explanation generator that produces human-interpretable decision rationales, facilitated by our spatiotemporal knowledge distillation approach that effectively captures spatiotemporal causal reasoning patterns. Comprehensive experiments demonstrate state-of-the-art performance, where OmniReason-Agent achieves significant improvements in both open-loop planning tasks and visual question answering (VQA) benchmarks, while establishing new capabilities for interpretable, temporally-aware autonomous vehicles operating in complex, dynamic environments.

Xingyue Peng, Yuandong Lyu, Lang Zhang et al.

Road surface reconstruction is essential for autonomous driving, supporting centimeter-accurate lane perception and high-definition mapping in complex urban environments.While recent methods based on mesh rendering or 3D Gaussian splatting (3DGS) achieve promising results under clean and static conditions, they remain vulnerable to occlusions from dynamic agents, visual clutter from static obstacles, and appearance degradation caused by lighting and weather changes. We present a robust reconstruction framework that integrates occlusion-aware 2D Gaussian surfels with semantic-guided color enhancement to recover clean, consistent road surfaces. Our method leverages a planar-adapted Gaussian representation for efficient large-scale modeling, employs segmentation-guided video inpainting to remove both dynamic and static foreground objects, and enhances color coherence via semantic-aware correction in HSV space. Extensive experiments on urban-scale datasets demonstrate that our framework produces visually coherent and geometrically faithful reconstructions, significantly outperforming prior methods under real-world conditions.

Yida Wang, Xueyang Zhang, Kun Zhan et al.

Neural surface reconstruction faces persistent challenges in reconciling geometric fidelity with photometric consistency under complex scene conditions. We present HiNeuS, a unified framework that holistically addresses three core limitations in existing approaches: multi-view radiance inconsistency, missing keypoints in textureless regions, and structural degradation from over-enforced Eikonal constraints during joint optimization. To resolve these issues through a unified pipeline, we introduce: 1) Differential visibility verification through SDF-guided ray tracing, resolving reflection ambiguities via continuous occlusion modeling; 2) Planar-conformal regularization via ray-aligned geometry patches that enforce local surface coherence while preserving sharp edges through adaptive appearance weighting; and 3) Physically-grounded Eikonal relaxation that dynamically modulates geometric constraints based on local radiance gradients, enabling detail preservation without sacrificing global regularity. Unlike prior methods that handle these aspects through sequential optimizations or isolated modules, our approach achieves cohesive integration where appearance-geometry constraints evolve synergistically throughout training. Comprehensive evaluations across synthetic and real-world datasets demonstrate state-of-the-art performance, including a 21.4% reduction in Chamfer distance over reflection-aware baselines and 2.32 dB PSNR improvement against neural rendering counterparts. Qualitative analyses reveal superior capability in recovering specular instruments, urban layouts with centimeter-scale infrastructure, and low-textured surfaces without local patch collapse. The method's generalizability is further validated through successful application to inverse rendering tasks, including material decomposition and view-consistent relighting.

Tao Tang, Likui Zhang, Youpeng Wen et al.

The development of generalist robot manipulation policies has seen significant progress, driven by large-scale demonstration data across diverse environments. However, the high cost and inefficiency of collecting real-world demonstrations hinder the scalability of data acquisition. While existing simulation platforms enable controlled environments for robotic learning, the challenge of bridging the sim-to-real gap remains. To address these challenges, we propose RoboPearls, an editable video simulation framework for robotic manipulation. Built on 3D Gaussian Splatting (3DGS), RoboPearls enables the construction of photo-realistic, view-consistent simulations from demonstration videos, and supports a wide range of simulation operators, including various object manipulations, powered by advanced modules like Incremental Semantic Distillation (ISD) and 3D regularized NNFM Loss (3D-NNFM). Moreover, by incorporating large language models (LLMs), RoboPearls automates the simulation production process in a user-friendly manner through flexible command interpretation and execution. Furthermore, RoboPearls employs a vision-language model (VLM) to analyze robotic learning issues to close the simulation loop for performance enhancement. To demonstrate the effectiveness of RoboPearls, we conduct extensive experiments on multiple datasets and scenes, including RLBench, COLOSSEUM, Ego4D, Open X-Embodiment, and a real-world robot, which demonstrate our satisfactory simulation performance.

Sinchee Chin, Fan Zhang, Xiaochen Yang et al.

Time Series Anomaly Detection (TSAD) is essential for uncovering rare and potentially harmful events in unlabeled time series data. Existing methods are highly dependent on clean, high-quality inputs, making them susceptible to noise and real-world imperfections. Additionally, intricate temporal relationships in time series data are often inadequately captured in traditional 1D representations, leading to suboptimal modeling of dependencies. We introduce VISTA, a training-free, unsupervised TSAD algorithm designed to overcome these challenges. VISTA features three core modules: 1) Time Series Decomposition using Seasonal and Trend Decomposition via Loess (STL) to decompose noisy time series into trend, seasonal, and residual components; 2) Temporal Self-Attention, which transforms 1D time series into 2D temporal correlation matrices for richer dependency modeling and anomaly detection; and 3) Multivariate Temporal Aggregation, which uses a pretrained feature extractor to integrate cross-variable information into a unified, memory-efficient representation. VISTA's training-free approach enables rapid deployment and easy hyperparameter tuning, making it suitable for industrial applications. It achieves state-of-the-art performance on five multivariate TSAD benchmarks.

Tao Tang, Lijun Zhou, Pengkun Hao et al.

3D multiple object tracking (MOT) plays a crucial role in autonomous driving perception. Recent end-to-end query-based trackers simultaneously detect and track objects, which have shown promising potential for the 3D MOT task. However, existing methods are still in the early stages of development and lack systematic improvements, failing to track objects in certain complex scenarios, like occlusions and the small size of target object's situations. In this paper, we first summarize the current end-to-end 3D MOT framework by decomposing it into three constituent parts: query initialization, query propagation, and query matching. Then we propose corresponding improvements, which lead to a strong yet simple tracker: S2-Track. Specifically, for query initialization, we present 2D-Prompted Query Initialization, which leverages predicted 2D object and depth information to prompt an initial estimate of the object's 3D location. For query propagation, we introduce an Uncertainty-aware Probabilistic Decoder to capture the uncertainty of complex environment in object prediction with probabilistic attention. For query matching, we propose a Hierarchical Query Denoising strategy to enhance training robustness and convergence. As a result, our S2-Track achieves state-of-the-art performance on nuScenes benchmark, i.e., 66.3% AMOTA on test split, surpassing the previous best end-to-end solution by a significant margin of 8.9% AMOTA. We achieve 1st place on the nuScenes tracking task leaderboard.

Enhui Ma, Lijun Zhou, Tao Tang et al.

Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail to improve the performance of planning of end-to-end autonomous driving models as the generated videos are usually less than 8 frames and the spatial and temporal inconsistencies are not negligible. To this end, we propose Delphi, a novel diffusion-based long video generation method with a shared noise modeling mechanism across the multi-views to increase spatial consistency, and a feature-aligned module to achieves both precise controllability and temporal consistency. Our method can generate up to 40 frames of video without loss of consistency which is about 5 times longer compared with state-of-the-art methods. Instead of randomly generating new data, we further design a sampling policy to let Delphi generate new data that are similar to those failure cases to improve the sample efficiency. This is achieved by building a failure-case driven framework with the help of pre-trained visual language models. Our extensive experiment demonstrates that our Delphi generates a higher quality of long videos surpassing previous state-of-the-art methods. Consequentially, with only generating 4% of the training dataset size, our framework is able to go beyond perception and prediction tasks, for the first time to the best of our knowledge, boost the planning performance of the end-to-end autonomous driving model by a margin of 25%.

Peng Jia, Yu Song, Jiameng Lv et al.

With the growing amount of astronomical data, there is an increasing need for automated data processing pipelines, which can extract scientific information from observation data without human interventions. A critical aspect of these pipelines is the image quality evaluation and masking algorithm, which evaluates image qualities based on various factors such as cloud coverage, sky brightness, scattering light from the optical system, point spread function size and shape, and read-out noise. Occasionally, the algorithm requires masking of areas severely affected by noise. However, the algorithm often necessitates significant human interventions, reducing data processing efficiency. In this study, we present a deep learning based image quality evaluation algorithm that uses an autoencoder to learn features of high quality astronomical images. The trained autoencoder enables automatic evaluation of image quality and masking of noise affected areas. We have evaluated the performance of our algorithm using two test cases: images with point spread functions of varying full width half magnitude, and images with complex backgrounds. In the first scenario, our algorithm could effectively identify variations of the point spread functions, which can provide valuable reference information for photometry. In the second scenario, our method could successfully mask regions affected by complex regions, which could significantly increase the photometry accuracy. Our algorithm can be employed to automatically evaluate image quality obtained by different sky surveying projects, further increasing the speed and robustness of data processing pipelines.

Peng Jia, Chao Lv, Yushan Li et al.

In recent years, there has been a gradual increase in the performance of Complementary Metal Oxide Semiconductor (CMOS) cameras. These cameras have gained popularity as a viable alternative to charge-coupled device (CCD) cameras in a wide range of applications. One particular application is the CMOS camera installed in small space telescopes. However, the limited power and spatial resources available on satellites present challenges in maintaining ideal observation conditions, including temperature and radiation environment. Consequently, images captured by CMOS cameras are susceptible to issues such as dark current noise and defective pixels. In this paper, we introduce a data-driven framework for mitigating dark current noise and bad pixels for CMOS cameras. Our approach involves two key steps: pixel clustering and function fitting. During pixel clustering step, we identify and group pixels exhibiting similar dark current noise properties. Subsequently, in the function fitting step, we formulate functions that capture the relationship between dark current and temperature, as dictated by the Arrhenius law. Our framework leverages ground-based test data to establish distinct temperature-dark current relations for pixels within different clusters. The cluster results could then be utilized to estimate the dark current noise level and detect bad pixels from real observational data. To assess the effectiveness of our approach, we have conducted tests using real observation data obtained from the Yangwang-1 satellite, equipped with a near-ultraviolet telescope and an optical telescope. The results show a considerable improvement in the detection efficiency of space-based telescopes.

Pengsen Cheng, Jinqiao Dai, Jiamiao Liu et al.

Controlling the generative model to adapt a new domain with limited samples is a difficult challenge and it is receiving increasing attention. Recently, methods based on meta-learning have shown promising results for few-shot domain adaptation. However, meta-learning-based methods usually suffer from the problem of overfitting, which results in a lack of diversity in the generated texts. To avoid this problem, in this study, a novel framework based on reinforcement learning (RL) is proposed. In this framework, to increase the sample utilization of RL and decrease its sample requirement, maximum likelihood estimation learning is incorporated into the RL process. When there are only a few in-domain samples available, experimental results on five target domains in two few-shot configurations show that this framework performs better than baselines.

Rui Sun, Peng Jia, Yongyang Sun et al.

Time domain astronomy has emerged as a vibrant research field in recent years, focusing on celestial objects that exhibit variable magnitudes or positions. Given the urgency of conducting follow-up observations for such objects, the development of an algorithm capable of detecting them and determining their magnitudes and positions has become imperative. Leveraging the advancements in deep neural networks, we present the PNet, an end-to-end framework designed not only to detect celestial objects and extract their magnitudes and positions but also to estimate photometry uncertainty. The PNet comprises two essential steps. Firstly, it detects stars and retrieves their positions, magnitudes, and calibrated magnitudes. Subsequently, in the second phase, the PNet estimates the uncertainty associated with the photometry results, serving as a valuable reference for the light curve classification algorithm. Our algorithm has been tested using both simulated and real observation data, demonstrating the PNet's ability to deliver consistent and reliable outcomes. Integration of the PNet into data processing pipelines for time-domain astronomy holds significant potential for enhancing response speed and improving the detection capabilities for celestial objects with variable positions and magnitudes.