Jia Pan

Fangyuan Wang, Ziyuan Wang, Guorui Pei et al.

Robotic manipulation depends on the ability to anticipate how actions reshape objects, contacts, and scene geometry before execution. Learned world models provide this capability by predicting task-relevant future evolution under robot intervention, yet the term now spans latent dynamics models, action-conditioned video generators, three- and four-dimensional scene predictors, physics-informed simulators, and predictive modules inside vision-language-action systems. This breadth has fragmented the literature and obscured the design choices that matter for manipulation. We survey world models for robotic manipulation through three questions: what future representation is predicted, how prediction is connected to action, and when prediction is used in the robot-learning pipeline. We operationally define a world model as an action-conditioned predictive system and distinguish it from perception modules, inverse models, policies, rewards, and value functions. We then organize existing work into five representation families, develop a functional taxonomy that separates integrated prediction-action models from explicit predictive planners, and characterize infrastructure roles including synthetic experience generation, candidate filtering, search-based evaluation, learned environments, and outcome verification. We further map these roles across pretraining, post-training, and inference adaptation, review 34 manipulation datasets, and synthesize evaluation protocols for predictive fidelity, task performance, and simulator reliability. This survey shows that world models are evolving from task-specific dynamics predictors into predictive infrastructure for robot learning, while exposing open challenges in contact modeling, hallucination control, action alignment, and benchmarking under closed-loop use.

Changhong Fu, Liangliang Yao, Haobo Zuo et al.

Domain adaptation (DA) has demonstrated significant promise for real-time nighttime unmanned aerial vehicle (UAV) tracking. However, the state-of-the-art (SOTA) DA still lacks the potential object with accurate pixel-level location and boundary to generate the high-quality target domain training sample. This key issue constrains the transfer learning of the real-time daytime SOTA trackers for challenging nighttime UAV tracking. Recently, the notable Segment Anything Model (SAM) has achieved a remarkable zero-shot generalization ability to discover abundant potential objects due to its huge data-driven training approach. To solve the aforementioned issue, this work proposes a novel SAM-powered DA framework for real-time nighttime UAV tracking, i.e., SAM-DA. Specifically, an innovative SAM-powered target domain training sample swelling is designed to determine enormous high-quality target domain training samples from every single raw nighttime image. This novel one-to-many generation significantly expands the high-quality target domain training sample for DA. Comprehensive experiments on extensive nighttime UAV videos prove the robustness and domain adaptability of SAM-DA for nighttime UAV tracking. Especially, compared to the SOTA DA, SAM-DA can achieve better performance with fewer raw nighttime images, i.e., the fewer-better training. This economized training approach facilitates the quick validation and deployment of algorithms for UAVs. The code is available at https://github.com/vision4robotics/SAM-DA.

Guangze Zheng, Changhong Fu, Junjie Ye et al.

Although the manipulating of the unmanned aerial manipulator (UAM) has been widely studied, vision-based UAM approaching, which is crucial to the subsequent manipulating, generally lacks effective design. The key to the visual UAM approaching lies in object tracking, while current UAM tracking typically relies on costly model-based methods. Besides, UAM approaching often confronts more severe object scale variation issues, which makes it inappropriate to directly employ state-of-the-art model-free Siamese-based methods from the object tracking field. To address the above problems, this work proposes a novel Siamese network with pairwise scale-channel attention (SiamSA) for vision-based UAM approaching. Specifically, SiamSA consists of a pairwise scale-channel attention network (PSAN) and a scale-aware anchor proposal network (SA-APN). PSAN acquires valuable scale information for feature processing, while SA-APN mainly attaches scale awareness to anchor proposing. Moreover, a new tracking benchmark for UAM approaching, namely UAMT100, is recorded with 35K frames on a flying UAM platform for evaluation. Exhaustive experiments on the benchmarks and real-world tests validate the efficiency and practicality of SiamSA with a promising speed. Both the code and UAMT100 benchmark are now available at https://github.com/vision4robotics/SiamSA.

Weilin Wan, Lei Yang, Lingjie Liu et al.

Understanding human intentions during interactions has been a long-lasting theme, that has applications in human-robot interaction, virtual reality and surveillance. In this study, we focus on full-body human interactions with large-sized daily objects and aim to predict the future states of objects and humans given a sequential observation of human-object interaction. As there is no such dataset dedicated to full-body human interactions with large-sized daily objects, we collected a large-scale dataset containing thousands of interactions for training and evaluation purposes. We also observe that an object's intrinsic physical properties are useful for the object motion prediction, and thus design a set of object dynamic descriptors to encode such intrinsic properties. We treat the object dynamic descriptors as a new modality and propose a graph neural network, HO-GCN, to fuse motion data and dynamic descriptors for the prediction task. We show the proposed network that consumes dynamic descriptors can achieve state-of-the-art prediction results and help the network better generalize to unseen objects. We also demonstrate the predicted results are useful for human-robot collaborations.

Hong-Yu Zhou, Yizhou Yu, Chengdi Wang et al.

During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results. Deep-learning models for aiding diagnosis have yet to meet this requirement. Here we report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model uses embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and bidirectional blocks with intramodal and intermodal attention to learn a holistic representation of radiographs, the unstructured chief complaint and clinical history, structured clinical information such as laboratory-test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases (by 12% and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29% and 7%, respectively). Leveraging unified multimodal Transformer-based models may help streamline triage of patients and facilitate the clinical decision process.

Kun Song, Gaoming Chen, Shentao Ma et al.

One central goal of robotics is to enable robots to interact with the physical world. Traditional manipulation studies primarily focus on single robots and relatively small objects. However, factory and domestic environments often require large-object manipulation, such as moving tables, where multiple robots must work collaboratively. Existing studies still lack a generalizable framework that can handle diverse objects, tasks, and robot team sizes. In this work, we propose CollaBot, a generalist framework for simultaneous collaborative manipulation. First, we use SEEM for scene segmentation and target-object extraction. Then, we propose a collaborative grasping framework that decomposes the task into local grasp pose generation and global coordination. Finally, we design a two-stage planning module to generate collision-free trajectories for task execution. Experimental results across different settings with varying objects, tasks, and numbers of robots indicate that our framework achieves a 72% success rate. This marks a substantial improvement over behavior cloning-based methods, validating the advantages of the proposed framework in complex multi-robot cooperative tasks. Real-world experiments further demonstrate the feasibility of our method in practical applications.

Changhong Fu, Xiang Lei, Haobo Zuo et al.

Visual object tracking has significantly promoted autonomous applications for unmanned aerial vehicles (UAVs). However, learning robust object representations for UAV tracking is especially challenging in complex dynamic environments, when confronted with aspect ratio change and occlusion. These challenges severely alter the original information of the object. To handle the above issues, this work proposes a novel progressive representation learning framework for UAV tracking, i.e., PRL-Track. Specifically, PRL-Track is divided into coarse representation learning and fine representation learning. For coarse representation learning, two innovative regulators, which rely on appearance and semantic information, are designed to mitigate appearance interference and capture semantic information. Furthermore, for fine representation learning, a new hierarchical modeling generator is developed to intertwine coarse object representations. Exhaustive experiments demonstrate that the proposed PRL-Track delivers exceptional performance on three authoritative UAV tracking benchmarks. Real-world tests indicate that the proposed PRL-Track realizes superior tracking performance with 42.6 frames per second on the typical UAV platform equipped with an edge smart camera. The code, model, and demo videos are available at \url{https://github.com/vision4robotics/PRL-Track}.

Yilin Wen, Hao Pan, Lei Yang et al.

Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame pose and object information over a longer time span to recognize the action. Our approach achieves competitive results on two first-person hand action benchmarks, namely FPHA and H2O. Extensive ablation studies verify our design choices.

Changhong Fu, Yiheng Wang, Liangliang Yao et al.

Nighttime UAV tracking under low-illuminated scenarios has achieved great progress by domain adaptation (DA). However, previous DA training-based works are deficient in narrowing the discrepancy of temporal contexts for UAV trackers. To address the issue, this work proposes a prompt-driven temporal domain adaptation training framework to fully utilize temporal contexts for challenging nighttime UAV tracking, i.e., TDA. Specifically, the proposed framework aligns the distribution of temporal contexts from daytime and nighttime domains by training the temporal feature generator against the discriminator. The temporal-consistent discriminator progressively extracts shared domain-specific features to generate coherent domain discrimination results in the time series. Additionally, to obtain high-quality training samples, a prompt-driven object miner is employed to precisely locate objects in unannotated nighttime videos. Moreover, a new benchmark for long-term nighttime UAV tracking is constructed. Exhaustive evaluations on both public and self-constructed nighttime benchmarks demonstrate the remarkable performance of the tracker trained in TDA framework, i.e., TDA-Track. Real-world tests at nighttime also show its practicality. The code and demo videos are available at https://github.com/vision4robotics/TDA-Track.

Dawei Wang, Weizi Li, Lei Zhu et al.

Intersections are essential road infrastructures for traffic in modern metropolises. However, they can also be the bottleneck of traffic flows as a result of traffic incidents or the absence of traffic coordination mechanisms such as traffic lights. Recently, various control and coordination mechanisms that are beyond traditional control methods have been proposed to improve the efficiency of intersection traffic by leveraging the ability of autonomous vehicles. Amongst these methods, the control of foreseeable mixed traffic that consists of human-driven vehicles (HVs) and robot vehicles (RVs) has emerged. We propose a decentralized multi-agent reinforcement learning approach for the control and coordination of mixed traffic by RVs at real-world, complex intersections -- an open challenge to date. We design comprehensive experiments to evaluate the effectiveness, robustness, generalizablility, and adaptability of our approach. In particular, our method can prevent congestion formation via merely 5% RVs under a real-world traffic demand of 700 vehicles per hour. In contrast, without RVs, congestion will form when the traffic demand reaches as low as 200 vehicles per hour. Moreover, when the RV penetration rate exceeds 60%, our method starts to outperform traffic signal control in terms of the average waiting time of all vehicles. Our method is not only robust against blackout events, sudden RV percentage drops, and V2V communication error, but also enjoys excellent generalizablility, evidenced by its successful deployment in five unseen intersections. Lastly, our method performs well under various traffic rules, demonstrating its adaptability to diverse scenarios. Videos and code of our work are available at https://sites.google.com/view/mixedtrafficcontrol

Michael Villarreal, Bibek Poudel, Jia Pan et al.

Traffic congestion is a persistent problem in our society. Previous methods for traffic control have proven futile in alleviating current congestion levels leading researchers to explore ideas with robot vehicles given the increased emergence of vehicles with different levels of autonomy on our roads. This gives rise to mixed traffic control, where robot vehicles regulate human-driven vehicles through reinforcement learning (RL). However, most existing studies use precise observations that require domain expertise and hand engineering for each road network's observation space. Additionally, precise observations use global information, such as environment outflow, and local information, i.e., vehicle positions and velocities. Obtaining this information requires updating existing road infrastructure with vast sensor environments and communication to potentially unwilling human drivers. We consider image observations, a modality that has not been extensively explored for mixed traffic control via RL, as the alternative: 1) images do not require a complete re-imagination of the observation space from environment to environment; 2) images are ubiquitous through satellite imagery, in-car camera systems, and traffic monitoring systems; and 3) images only require communication to equipment. In this work, we show robot vehicles using image observations can achieve competitive performance to using precise information on environments, including ring, figure eight, intersection, merge, and bottleneck. In certain scenarios, our approach even outperforms using precision observations, e.g., up to 8% increase in average vehicle velocity in the merge environment, despite only using local traffic information as opposed to global traffic information.

Yupu Lu, Shijie Lin, Guanqi Chen et al.

Deep learning models are able to approximate one specific dynamical system but struggle at learning generalisable dynamics, where dynamical systems obey the same laws of physics but contain different numbers of elements (e.g., double- and triple-pendulum systems). To relieve this issue, we proposed the Modular Lagrangian Network (ModLaNet), a structural neural network framework with modularity and physical inductive bias. This framework models the energy of each element using modularity and then construct the target dynamical system via Lagrangian mechanics. Modularity is beneficial for reusing trained networks and reducing the scale of networks and datasets. As a result, our framework can learn from the dynamics of simpler systems and extend to more complex ones, which is not feasible using other relevant physics-informed neural networks. We examine our framework for modelling double-pendulum or three-body systems with small training datasets, where our models achieve the best data efficiency and accuracy performance compared with counterparts. We also reorganise our models as extensions to model multi-pendulum and multi-body systems, demonstrating the intriguing reusable feature of our framework.

Haitao Tang, Yu Fu, Lei Sun et al.

Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effective way is to ensure that their hidden and output distributions are consistent, which can be achieved by hierarchical knowledge distillation. However, it is difficult to ensure the distribution consistency simultaneously because the learning of the output distribution depends on the hidden one. In this paper, we propose an adaptive two-stage knowledge distillation method consisting of hidden layer learning and output layer learning. In the former stage, we learn hidden representation with full context by applying mean square error loss function. In the latter stage, we design a power transformation based adaptive smoothness method to learn stable output distribution. It achieved 19\% relative reduction in word error rate, and a faster response for the first token compared with the original streaming model in LibriSpeech corpus.

Shijie Lin, Yinqiang Zhang, Lei Yu et al.

Focus control (FC) is crucial for cameras to capture sharp images in challenging real-world scenarios. The autofocus (AF) facilitates the FC by automatically adjusting the focus settings. However, due to the lack of effective AF methods for the recently introduced event cameras, their FC still relies on naive AF like manual focus adjustments, leading to poor adaptation in challenging real-world conditions. In particular, the inherent differences between event and frame data in terms of sensing modality, noise, temporal resolutions, etc., bring many challenges in designing an effective AF method for event cameras. To address these challenges, we develop a novel event-based autofocus framework consisting of an event-specific focus measure called event rate (ER) and a robust search strategy called event-based golden search (EGS). To verify the performance of our method, we have collected an event-based autofocus dataset (EAD) containing well-synchronized frames, events, and focal positions in a wide variety of challenging scenes with severe lighting and motion conditions. The experiments on this dataset and additional real-world scenarios demonstrated the superiority of our method over state-of-the-art approaches in terms of efficiency and accuracy.

Jing-Xuan Zhang, Gen-Shun Wan, Jia Pan

Lip region-of-interest (ROI) is conventionally used for visual input in the lipreading task. Few works have adopted the entire face as visual input because lip-excluded parts of the face are usually considered to be redundant and irrelevant to visual speech recognition. However, faces contain much more detailed information than lips, such as speakers' head pose, emotion, identity etc. We argue that such information might benefit visual speech recognition if a powerful feature extractor employing the entire face is trained. In this work, we propose to adopt the entire face for lipreading with self-supervised learning. AV-HuBERT, an audio-visual multi-modal self-supervised learning framework, was adopted in our experiments. Our experimental results showed that adopting the entire face achieved 16% relative word error rate (WER) reduction on the lipreading task, compared with the baseline method using lip as visual input. Without self-supervised pretraining, the model with face input achieved a higher WER than that using lip input in the case of limited training data (30 hours), while a slightly lower WER when using large amount of training data (433 hours).

Qi Li, Jiaxin Cai, Yuanlong Yu et al.

Amidst the swift advancements in photography and sensor technologies, high-definition cameras have become commonplace in the deployment of Unmanned Aerial Vehicles (UAVs) for diverse operational purposes. Within the domain of UAV imagery analysis, the segmentation of ultra-high resolution images emerges as a substantial and intricate challenge, especially when grappling with the constraints imposed by GPU memory-restricted computational devices. This paper delves into the intricate problem of achieving efficient and effective segmentation of ultra-high resolution UAV imagery, while operating under stringent GPU memory limitation. The strategy of existing approaches is to downscale the images to achieve computationally efficient segmentation. However, this strategy tends to overlook smaller, thinner, and curvilinear regions. To address this problem, we propose a GPU memory-efficient and effective framework for local inference without accessing the context beyond local patches. In particular, we introduce a novel spatial-guided high-resolution query module, which predicts pixel-wise segmentation results with high quality only by querying nearest latent embeddings with the guidance of high-resolution information. Additionally, we present an efficient memory-based interaction scheme to correct potential semantic bias of the underlying high-resolution information by associating cross-image contextual semantics. For evaluation of our approach, we perform comprehensive experiments over public benchmarks and achieve superior performance under both conditions of small and large GPU memory usage limitations. We will release the model and codes in the future.

Wenxi Liu, Qi Li, Weixiang Yang et al.

HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to expensive sensors and time-consuming computation. Camera-based methods usually need to perform road segmentation and view transformation separately, which often causes distortion and missing content. To push the limits of the technology, we present a novel framework that reconstructs a local map formed by road layout and vehicle occupancy in the bird's-eye view given a front-view monocular image only. We propose a front-to-top view projection (FTVP) module, which takes the constraint of cycle consistency between views into account and makes full use of their correlation to strengthen the view transformation and scene understanding. In addition, we also apply multi-scale FTVP modules to propagate the rich spatial information of low-level features to mitigate spatial deviation of the predicted object location. Experiments on public benchmarks show that our method achieves the state-of-the-art performance in the tasks of road layout estimation, vehicle occupancy estimation, and multi-class semantic estimation. For multi-class semantic estimation, in particular, our model outperforms all competitors by a large margin. Furthermore, our model runs at 25 FPS on a single GPU, which is efficient and applicable for real-time panorama HD map reconstruction.

Fenglin Ding, Genshun Wan, Pengcheng Li et al.

Multilingual end-to-end models have shown great improvement over monolingual systems. With the development of pre-training methods on speech, self-supervised multilingual speech representation learning like XLSR has shown success in improving the performance of multilingual automatic speech recognition (ASR). However, similar to the supervised learning, multilingual pre-training may also suffer from language interference and further affect the application of multilingual system. In this paper, we introduce several techniques for improving self-supervised multilingual pre-training by leveraging auxiliary language information, including the language adversarial training, language embedding and language adaptive training during the pre-training stage. We conduct experiments on a multilingual ASR task consisting of 16 languages. Our experimental results demonstrate 14.3% relative gain over the standard XLSR model, and 19.8% relative gain over the no pre-training multilingual model.

Chengyu Deng, Guanqi Chen, Yizhou Chen et al.

Diffusion-based policies have established a new standard for precise robotic manipulation but face a critical scalability bottleneck: high-performance models are computationally expensive, while lightweight alternatives often fail to generalize across diverse multi-task environments. Mixture-of-Experts (MoE) architectures offer a promising path to efficiency by activating only a subset of parameters. However, existing MoE routing mechanisms typically rely on low-level noise or latent statistics, ignoring the compositional nature of manipulation tasks. This can fragment reusable behaviors across experts, limiting interpretability and transferability. We introduce Semantically Structured Mixture-of-Experts Diffusion Policy (SMoDP) for compositional robotic manipulation, a framework that grounds expert specialization in semantic task structure. SMoDP leverages a lightweight, inference-time skill predictor, supervised by offline annotations from Vision-Language Models (VLMs), to route action chunks to experts specialized for specific behavioral phases. To ensure robust assignment, we propose a dual contrastive alignment strategy that grounds multi-modal observations in language-defined skill semantics (Inter-modal) while enforcing routing consistency across visually distinct but functionally related behaviors (Intra-modal). Our approach outperforms representative diffusion and MoE-based baselines on multi-task benchmarks with significantly improved parameter efficiency and demonstrates effective compositional transfer to novel tasks through parameter-efficient fine-tuning. Project website: https://deng-cy20.github.io/SMoDP/

Chenyu Liu, Jia Pan, Jinshui Hu et al.

Recently, Handwritten Mathematical Expression Recognition (HMER) has gained considerable attention in pattern recognition for its diverse applications in document understanding. Current methods typically approach HMER as an image-to-sequence generation task within an autoregressive (AR) encoder-decoder framework. However, these approaches suffer from several drawbacks: 1) a lack of overall language context, limiting information utilization beyond the current decoding step; 2) error accumulation during AR decoding; and 3) slow decoding speed. To tackle these problems, this paper makes the first attempt to build a novel bottom-up Non-AutoRegressive Modeling approach for HMER, called NAMER. NAMER comprises a Visual Aware Tokenizer (VAT) and a Parallel Graph Decoder (PGD). Initially, the VAT tokenizes visible symbols and local relations at a coarse level. Subsequently, the PGD refines all tokens and establishes connectivities in parallel, leveraging comprehensive visual and linguistic contexts. Experiments on CROHME 2014/2016/2019 and HME100K datasets demonstrate that NAMER not only outperforms the current state-of-the-art (SOTA) methods on ExpRate by 1.93%/2.35%/1.49%/0.62%, but also achieves significant speedups of 13.7x and 6.7x faster in decoding time and overall FPS, proving the effectiveness and efficiency of NAMER.

Tengye Xu, Yangting Sun, Ziju Shen et al.

Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants through different object instances, positions, and camera viewpoints. Recent vision-based reward models tend to memorize specific pixel distributions and fail to generalize beyond their training conditions. To address this, we propose a framework that learns invariant symbolic reward functions from as few as five demonstrations. The insight is to shift from visual feature-fitting to the discovery of behavioral invariants: task-level properties that remain constant across diverse visual instantiations. The framework has two coupled components: a structural reward formulation that encodes task-level strategies and physical constraints while preserving optimal policy invariance, and a hybrid symbolic-numerical procedure that distills these invariants from demonstrations without online interaction. Experiments on eight Meta-World tasks and three Franka manipulation tasks demonstrate that our method achieves stronger process alignment and policy rollout ranking abilities compared to baselines, accelerating downstream policy learning. Three real-world out-of-distribution experiments further show that the same learned reward generalizes zero-shot to position, viewpoint, and object variations, enabling a single reward representation to be reused across diverse task variants in practice.

Dongjie Yu, Kun Lei, Zhennan Jiang et al.

Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore how reinforcement learning (RL) should adapt policies after offline pretraining. Existing lightweight methods commonly apply residual corrections directly in action space, but this often leads to noisy and poorly structured exploration. In this work, we propose Z-Perturbation Reinforcement Learning (ZPRL), an approach that steers pretrained policies through a compact bottleneck latent rather than through policy weights or output actions. During offline training, we augment the policy with a plug-and-play variational information bottleneck (VIB) module to extract a task-relevant latent interface from observation embeddings. During online finetuning, the base policy is frozen and RL learns only a residual perturbation on this latent, whose decoded representation conditions the frozen action generator. We instantiate ZPRL on flow-matching policies and evaluate it on eight simulation tasks and four real-world tasks. Across diverse manipulation settings, ZPRL improves both sample efficiency and final performance over strong post-training baselines. In the real world, ZPRL improves the average success rate on four tasks by 33.7% over imitation base policies while producing smoother exploration behaviors than an action residual counterpart. These results suggest that a compact, task-aligned bottleneck latent provides an effective interface for online RL adaptation. More videos can be found at https://manutdmoon.github.io/ZPRL/.

Yilin Wen, Hao Pan, Takehiko Ohkawa et al.

We present a novel unified framework that concurrently tackles recognition and future prediction for human hand pose and action modeling. Previous works generally provide isolated solutions for either recognition or prediction, which not only increases the complexity of integration in practical applications, but more importantly, cannot exploit the synergy of both sides and suffer suboptimal performances in their respective domains. To address this problem, we propose a generative Transformer VAE architecture to model hand pose and action, where the encoder and decoder capture recognition and prediction respectively, and their connection through the VAE bottleneck mandates the learning of consistent hand motion from the past to the future and vice versa. Furthermore, to faithfully model the semantic dependency and different temporal granularity of hand pose and action, we decompose the framework into two cascaded VAE blocks: the first and latter blocks respectively model the short-span poses and long-span action, and are connected by a mid-level feature representing a sub-second series of hand poses. This decomposition into block cascades facilitates capturing both short-term and long-term temporal regularity in pose and action modeling, and enables training two blocks separately to fully utilize datasets with annotations of different temporal granularities. We train and evaluate our framework across multiple datasets; results show that our joint modeling of recognition and prediction improves over isolated solutions, and that our semantic and temporal hierarchy facilitates long-term pose and action modeling.

Zhengyan Sheng, Yang Ai, Li-Juan Liu et al.

Despite recent advancements in speech generation with text prompt providing control over speech style, voice attributes in synthesized speech remain elusive and challenging to control. This paper introduces a novel task: voice attribute editing with text prompt, with the goal of making relative modifications to voice attributes according to the actions described in the text prompt. To solve this task, VoxEditor, an end-to-end generative model, is proposed. In VoxEditor, addressing the insufficiency of text prompt, a Residual Memory (ResMem) block is designed, that efficiently maps voice attributes and these descriptors into the shared feature space. Additionally, the ResMem block is enhanced with a voice attribute degree prediction (VADP) block to align voice attributes with corresponding descriptors, addressing the imprecision of text prompt caused by non-quantitative descriptions of voice attributes. We also establish the open-source VCTK-RVA dataset, which leads the way in manual annotations detailing voice characteristic differences among different speakers. Extensive experiments demonstrate the effectiveness and generalizability of our proposed method in terms of both objective and subjective metrics. The dataset and audio samples are available on the website.

An Yang, Chenyu Liu, Jun Du et al.

3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation. However, existing 3D-GS-based segmentation methods typically rely on high-dimensional category features, which introduce substantial memory overhead. Moreover, fine-grained segmentation remains challenging due to label space congestion and the lack of stable multi-granularity control mechanisms. To address these limitations, we propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping, drastically reducing memory usage. We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability. Additionally, we fine-tune opacity during segmentation training to address the incompatibility between photometric rendering and semantic segmentation, which often leads to foreground-background confusion. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art segmentation performance while significantly reducing memory consumption and accelerating inference.

Michael Villarreal, Dawei Wang, Jia Pan et al.

Greenhouse gas emissions have dramatically risen since the early 1900s with U.S. transportation generating 28% of U.S. emissions. As such, there is interest in reducing transportation-related emissions. Specifically, sustainability research has sprouted around signalized intersections as intersections allow different streams of traffic to cross and change directions. Recent research has developed mixed traffic control eco-driving strategies at signalized intersections to decrease emissions. However, the inherent structure of a signalized intersection generates increased emissions by creating frequent acceleration/deceleration events, excessive idling from traffic congestion, and stop-and-go waves. Thus, we believe unsignalized intersections hold potential for further sustainability improvements. In this work, we provide an emissions analysis on unsignalized intersections with complex, real-world topologies and traffic demands where mixed traffic control strategies are employed by robot vehicles (RVs) to reduce wait times and congestion. We find with at least 10% RV penetration rate, RVs generate less fuel consumption, CO2 emissions, and NOx emissions than signalized intersections by up to 27%, 27% and 28%, respectively. With at least 30% RVs, CO and HC emissions are reduced by up to 42% and 43%, respectively. Additionally, RVs can reduce network-wide emissions despite only employing their strategies at intersections.

Yuan Zhang, Chenyu Xue, Wenjie Xu et al.

We introduce iFlyBot-VLA, a large-scale Vision-Language-Action (VLA) model trained under a novel framework. The main contributions are listed as follows: (1) a latent action model thoroughly trained on large-scale human and robotic manipulation videos; (2) a dual-level action representation framework that jointly supervises both the Vision-Language Model (VLM) and the action expert during training; (3) a mixed training strategy that combines robot trajectory data with general QA and spatial QA datasets, effectively enhancing the 3D perceptual and reasoning capabilities of the VLM backbone. Specifically, the VLM is trained to predict two complementary forms of actions: latent actions, derived from our latent action model pretrained on cross-embodiment manipulation data, which capture implicit high-level intentions; and structured discrete action tokens, obtained through frequency-domain transformations of continuous control signals, which encode explicit low-level dynamics. This dual supervision aligns the representation spaces of language, vision, and action, enabling the VLM to directly contribute to action generation. Experimental results on the LIBERO Franka benchmark demonstrate the superiority of our frame-work, while real-world evaluations further show that iFlyBot-VLA achieves competitive success rates across diverse and challenging manipulation tasks. Furthermore, we plan to open-source a portion of our self-constructed dataset to support future research in the community

Anirudh Khatry, Robert Zhang, Jia Pan et al.

C-to-Rust transpilation is essential for modernizing legacy C code while enhancing safety and interoperability with modern Rust ecosystems. However, no dataset currently exists for evaluating whether a system can transpile C into safe Rust that passes a set of test cases. We introduce CRUST-Bench, a dataset of 100 C repositories, each paired with manually-written interfaces in safe Rust as well as test cases that can be used to validate correctness of the transpilation. By considering entire repositories rather than isolated functions, CRUST-Bench captures the challenges of translating complex projects with dependencies across multiple files. The provided Rust interfaces provide explicit specifications that ensure adherence to idiomatic, memory-safe Rust patterns, while the accompanying test cases enforce functional correctness. We evaluate state-of-the-art large language models (LLMs) on this task and find that safe and idiomatic Rust generation is still a challenging problem for various state-of-the-art methods and techniques. We also provide insights into the errors LLMs usually make in transpiling code from C to safe Rust. The best performing model, OpenAI o1, is able to solve only 15 tasks in a single-shot setting. Improvements on CRUST-Bench would lead to improved transpilation systems that can reason about complex scenarios and help in migrating legacy codebases from C into languages like Rust that ensure memory safety. You can find the dataset and code at https://github.com/anirudhkhatry/CRUST-bench.

Yuhan Ping, Yuan Liu, Xiaoxiao Long et al.

In this paper, we introduce \textit{DecoRec}, a novel system designed to elevate single-view 2D images to a decomposed 3D scene mesh. Current methods for single-view scene reconstruction typically rely on object retrieval or the regression of coarse 3D voxels or surfaces, leading to inaccuracies in capturing the appearance and geometry of the input image. The lack of high-quality large-scale scene-level datasets further complicates direct 3D scene generation from single-view images. To achieve high-quality 3D scene generation from a single-view image, DecoRec takes advantage of recent diffusion-based single-view object reconstruction methods to reconstruct individual objects separately. Subsequently, a refinement pipeline is proposed to effectively merge these reconstructed objects, enhancing appearance and geometry through a differentiable rendering technique and diffusion-guided refinement. Our results demonstrate that DecoRec facilitates high-quality single-view scene reconstruction in both geometry and novel synthesis, offering significant benefits for downstream applications like room interior design.

Haobo Zuo, Changhong Fu, Guangze Zheng et al.

Domain adaptation is an inspiring solution to the misalignment issue of day/night image features for nighttime UAV tracking. However, the one-step adaptation paradigm is inadequate in addressing the prevalent difficulties posed by low-resolution (LR) objects when viewed from the UAVs at night, owing to the blurry edge contour and limited detail information. Moreover, these approaches struggle to perceive LR objects disturbed by nighttime noise. To address these challenges, this work proposes a novel progressive alignment paradigm, named domain-aware diffusion model (DaDiff), aligning nighttime LR object features to the daytime by virtue of progressive and stable generations. The proposed DaDiff includes an alignment encoder to enhance the detail information of nighttime LR objects, a tracking-oriented layer designed to achieve close collaboration with tracking tasks, and a successive distribution discriminator presented to distinguish different feature distributions at each diffusion timestep successively. Furthermore, an elaborate nighttime UAV tracking benchmark is constructed for LR objects, namely NUT-LR, consisting of 100 annotated sequences. Exhaustive experiments have demonstrated the robustness and feature alignment ability of the proposed DaDiff. The source code and video demo are available at https://github.com/vision4robotics/DaDiff.

Dongjie Yu, Hang Xu, Yizhou Chen et al.

Bimanual manipulation tasks typically involve multiple stages which require efficient interactions between two arms, posing step-wise and stage-wise challenges for imitation learning systems. Specifically, failure and delay of one step will broadcast through time, hinder success and efficiency of each sub-stage task, and thereby overall task performance. Although recent works have made strides in addressing certain challenges, few approaches explicitly consider the multi-stage nature of bimanual tasks while simultaneously emphasizing the importance of inference speed. In this paper, we introduce a novel keypose-conditioned consistency policy tailored for bimanual manipulation. It is a hierarchical imitation learning framework that consists of a high-level keypose predictor and a low-level trajectory generator. The predicted keyposes provide guidance for trajectory generation and also mark the completion of one sub-stage task. The trajectory generator is designed as a consistency model trained from scratch without distillation, which generates action sequences conditioning on current observations and predicted keyposes with fast inference speed. Simulated and real-world experimental results demonstrate that the proposed approach surpasses baseline methods in terms of success rate and operational efficiency. Codes are available at https://github.com/ManUtdMoon/BiKC.

Hanbo Cheng, Limin Lin, Chenyu Liu et al.

Talking head generation intends to produce vivid and realistic talking head videos from a single portrait and speech audio clip. Although significant progress has been made in diffusion-based talking head generation, almost all methods rely on autoregressive strategies, which suffer from limited context utilization beyond the current generation step, error accumulation, and slower generation speed. To address these challenges, we present DAWN (Dynamic frame Avatar With Non-autoregressive diffusion), a framework that enables all-at-once generation of dynamic-length video sequences. Specifically, it consists of two main components: (1) audio-driven holistic facial dynamics generation in the latent motion space, and (2) audio-driven head pose and blink generation. Extensive experiments demonstrate that our method generates authentic and vivid videos with precise lip motions, and natural pose/blink movements. Additionally, with a high generation speed, DAWN possesses strong extrapolation capabilities, ensuring the stable production of high-quality long videos. These results highlight the considerable promise and potential impact of DAWN in the field of talking head video generation. Furthermore, we hope that DAWN sparks further exploration of non-autoregressive approaches in diffusion models. Our code will be publicly available at https://github.com/Hanbo-Cheng/DAWN-pytorch.

Yangyang Xu, Bailin Deng, Junle Wang et al.

We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure attributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark-driven structure transfer latent direction. The disentangled latent code produces rich generative features that incorporate feature blending to produce a plausible swapping result. We further extend our method to video face swapping by enforcing two spatio-temporal constraints on the latent space and the image space. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art image/video face swapping methods in terms of hallucination quality and consistency. Code can be found at: https://github.com/cnnlstm/FSLSD_HiRes.

Dawei Wang, Lingping Gao, Ziquan Lan et al.

Recently, there have been many advances in autonomous driving society, attracting a lot of attention from academia and industry. However, existing works mainly focus on cars, extra development is still required for self-driving truck algorithms and models. In this paper, we introduce an intelligent self-driving truck system. Our presented system consists of three main components, 1) a realistic traffic simulation module for generating realistic traffic flow in testing scenarios, 2) a high-fidelity truck model which is designed and evaluated for mimicking real truck response in real-world deployment, 3) an intelligent planning module with learning-based decision making algorithm and multi-mode trajectory planner, taking into account the truck's constraints, road slope changes, and the surrounding traffic flow. We provide quantitative evaluations for each component individually to demonstrate the fidelity and performance of each part. We also deploy our proposed system on a real truck and conduct real world experiments which shows our system's capacity of mitigating sim-to-real gap. Our code is available at https://github.com/InceptioResearch/IITS

Guanqi Chen, Lei Yang, Guanhua Chen et al.

The ability to navigate robots with natural language instructions in an unknown environment is a crucial step for achieving embodied artificial intelligence (AI). With the improving performance of deep neural models proposed in the field of vision-and-language navigation (VLN), it is equally interesting to know what information the models utilize for their decision-making in the navigation tasks. To understand the inner workings of deep neural models, various explanation methods have been developed for promoting explainable AI (XAI). But they are mostly applied to deep neural models for image or text classification tasks and little work has been done in explaining deep neural models for VLN tasks. In this paper, we address these problems by building quantitative benchmarks to evaluate explanation methods for VLN models in terms of faithfulness. We propose a new erasure-based evaluation pipeline to measure the step-wise textual explanation in the sequential decision-making setting. We evaluate several explanation methods for two representative VLN models on two popular VLN datasets and reveal valuable findings through our experiments.

Yupu Lu, Shijie Lin, Hao Xu et al.

Finding a control Lyapunov function (CLF) in a dynamical system with a controller is an effective way to guarantee stability, which is a crucial issue in safety-concerned applications. Recently, deep learning models representing CLFs have been applied into a learner-verifier framework to identify satisfiable candidates. However, the learner treats Lyapunov conditions as complex constraints for optimisation, which is hard to achieve global convergence. It is also too complicated to implement these Lyapunov conditions for verification. To improve this framework, we treat Lyapunov conditions as inductive biases and design a neural CLF and a CLF-based controller guided by this knowledge. This design enables a stable optimisation process with limited constraints, and allows end-to-end learning of both the CLF and the controller. Our approach achieves a higher convergence rate and larger region of attraction (ROA) in learning the CLF compared to existing methods among abundant experiment cases. We also thoroughly reveal why the success rate decreases with previous methods during learning.

Linfang Zheng, Zikai Ouyang, Chen Wang et al.

Video is a scalable observation of physical dynamics: it captures how objects move, how contact unfolds, and how scenes evolve under interaction -- all without requiring robot action labels. Yet translating this temporal structure into reliable robotic control remains an open challenge, because video lacks action supervision and differs from robot experience in embodiment, viewpoint, and physical constraints. This survey reviews methods that exploit non-action-annotated temporal video to learn control interfaces for robotic manipulation. We introduce an \emph{interface-centric taxonomy} organized by where the video-to-control interface is constructed and what control properties it enables, identifying three families: direct video--action policies, which keep the interface implicit; latent-action methods, which route temporal structure through a compact learned intermediate; and explicit visual interfaces, which predict interpretable targets for downstream control. For each family, we analyze control-integration properties -- how the loop is closed, what can be verified before execution, and where failures enter. A cross-family synthesis reveals that the most pressing open challenges center on the \emph{robotics integration layer} -- the mechanisms that connect video-derived predictions to dependable robot behavior -- and we outline research directions toward closing this gap.

Sihan Chen, Hang Xu, Yupu Lu et al.

Shared autonomy (SA) enables robots to infer human intent and assist in its achievement. While most research focuses on improving intent inference, it overlooks whether humans can understand the robot's intent in return. Without such mutual understanding, collaboration becomes less effective, degrading user experience and task performance. To address this gap, previous studies have explicitly conveyed the robot intent through additional interfaces, which remain unintuitive and limited in expressiveness. Inspired by impedance control, we propose Impedance-Driven Anisotropic Guidance Field Enhanced Shared Autonomy (IAGF-SA), a novel paradigm that extends SA with an embodied, physically-grounded communication channel. This channel adaptively modulates the robot's dynamic response to human input, enabling intuitive, continuous, physically-grounded robot intent communication while naturally guiding human actions. User studies across three scenarios and two teleoperation interfaces indicate that IAGF-SA improves task performance, human-robot agreement, and subjective experience, thus demonstrating its effectiveness in enhancing human-robot communication and collaboration.

Guangze Zheng, Shijie Lin, Haobo Zuo et al.

The complex dynamicity of open-world objects presents non-negligible challenges for multi-object tracking (MOT), often manifested as severe deformations, fast motion, and occlusions. Most methods that solely depend on coarse-grained object cues, such as boxes and the overall appearance of the object, are susceptible to degradation due to distorted internal relationships of dynamic objects. To address this problem, this work proposes NetTrack, an efficient, generic, and affordable tracking framework to introduce fine-grained learning that is robust to dynamicity. Specifically, NetTrack constructs a dynamicity-aware association with a fine-grained Net, leveraging point-level visual cues. Correspondingly, a fine-grained sampler and matching method have been incorporated. Furthermore, NetTrack learns object-text correspondence for fine-grained localization. To evaluate MOT in extremely dynamic open-world scenarios, a bird flock tracking (BFT) dataset is constructed, which exhibits high dynamicity with diverse species and open-world scenarios. Comprehensive evaluation on BFT validates the effectiveness of fine-grained learning on object dynamicity, and thorough transfer experiments on challenging open-world benchmarks, i.e., TAO, TAO-OW, AnimalTrack, and GMOT-40, validate the strong generalization ability of NetTrack even without finetuning. Project page: https://george-zhuang.github.io/nettrack/.

Ruihua Han, Shuai Wang, Shuaijun Wang et al.

Navigating a nonholonomic robot in a cluttered, unknown environment requires accurate perception and precise motion control for real-time collision avoidance. This paper presents NeuPAN: a real-time, highly accurate, map-free, easy-to-deploy, and environment-invariant robot motion planner. Leveraging a tightly coupled perception-to-control framework, NeuPAN has two key innovations compared to existing approaches: 1) it directly maps raw point cloud data to a latent distance feature space for collision-free motion generation, avoiding error propagation from the perception to control pipeline; 2) it is interpretable from an end-to-end model-based learning perspective. The crux of NeuPAN is solving an end-to-end mathematical model with numerous point-level constraints using a plug-and-play (PnP) proximal alternating-minimization network (PAN), incorporating neurons in the loop. This allows NeuPAN to generate real-time, physically interpretable motions. It seamlessly integrates data and knowledge engines, and its network parameters can be fine-tuned via backpropagation. We evaluate NeuPAN on a ground mobile robot, a wheel-legged robot, and an autonomous vehicle, in extensive simulated and real-world environments. Results demonstrate that NeuPAN outperforms existing baselines in terms of accuracy, efficiency, robustness, and generalization capabilities across various environments, including the cluttered sandbox, office, corridor, and parking lot. We show that NeuPAN works well in unknown and unstructured environments with arbitrarily shaped objects, transforming impassable paths into passable ones.

Ke Guo, Zhenwei Miao, Wei Jing et al.

Microscopic traffic simulation plays a crucial role in transportation engineering by providing insights into individual vehicle behavior and overall traffic flow. However, creating a realistic simulator that accurately replicates human driving behaviors in various traffic conditions presents significant challenges. Traditional simulators relying on heuristic models often fail to deliver accurate simulations due to the complexity of real-world traffic environments. Due to the covariate shift issue, existing imitation learning-based simulators often fail to generate stable long-term simulations. In this paper, we propose a novel approach called learner-aware supervised imitation learning to address the covariate shift problem in multi-agent imitation learning. By leveraging a variational autoencoder simultaneously modeling the expert and learner state distribution, our approach augments expert states such that the augmented state is aware of learner state distribution. Our method, applied to urban traffic simulation, demonstrates significant improvements over existing state-of-the-art baselines in both short-term microscopic and long-term macroscopic realism when evaluated on the real-world dataset pNEUMA.

Yuxuan Gao, Yedong Shen, Shiqi Zhang et al.

Although multi-step generative policies achieve strong performance in robotic manipulation by modeling multimodal action distributions, they require multi-step iterative denoising at inference time. Each action therefore needs tens to hundreds of network function evaluations (NFEs), making them costly for high-frequency closed-loop control and online reinforcement learning (RL). To address this limitation, we propose a two-stage framework for native one-step generative policies that shifts refinement from inference to training. First, we introduce the Drift-Based Policy (DBP), which leverages fixed-point drifting objectives to internalize iterative refinement into the model parameters, yielding a one-step generative backbone by design while preserving multimodal action modeling capacity. Second, we develop Drift-Based Policy Optimization (DBPO), an online RL framework that equips the pretrained backbone with a compatible stochastic interface, enabling stable on-policy updates without sacrificing the one-step deployment property. Extensive experiments demonstrate the effectiveness of the proposed framework across offline imitation learning, online fine-tuning, and real-world control scenarios. DBP matches or exceeds the performance of multi-step diffusion policies while achieving up to $100\times$ faster inference. It also consistently outperforms existing one-step baselines on challenging manipulation benchmarks. Moreover, DBPO enables effective and stable policy improvement in online settings. Experiments on a real-world dual-arm robot demonstrate reliable high-frequency control at 105.2 Hz.

Ke Guo, Haochen Liu, Xiaojun Wu et al.

End-to-end (E2E) autonomous driving systems offer a promising alternative to traditional modular pipelines by reducing information loss and error accumulation, with significant potential to enhance both mobility and safety. However, most existing E2E approaches directly generate plans based on dense bird's-eye view (BEV) grid features, leading to inefficiency and limited planning awareness. To address these limitations, we propose iterative Proposal-centric autonomous driving (iPad), a novel framework that places proposals - a set of candidate future plans - at the center of feature extraction and auxiliary tasks. Central to iPad is ProFormer, a BEV encoder that iteratively refines proposals and their associated features through proposal-anchored attention, effectively fusing multi-view image data. Additionally, we introduce two lightweight, proposal-centric auxiliary tasks - mapping and prediction - that improve planning quality with minimal computational overhead. Extensive experiments on the NAVSIM and CARLA Bench2Drive benchmarks demonstrate that iPad achieves state-of-the-art performance while being significantly more efficient than prior leading methods.

Zeqing Zhang, Guangze Zheng, Xuebo Ji et al.

Granular materials (GMs) are ubiquitous in daily life. Understanding their properties is also important, especially in agriculture and industry. However, existing works require dedicated measurement equipment and also need large human efforts to handle a large number of particles. In this paper, we introduce a method for estimating the relative values of particle size and density from the video of the interaction with GMs. It is trained on a visuo-haptic learning framework inspired by a contact model, which reveals the strong correlation between GM properties and the visual-haptic data during the probe-dragging in the GMs. After training, the network can map the visual modality well to the haptic signal and implicitly characterize the relative distribution of particle properties in its latent embeddings, as interpreted in that contact model. Therefore, we can analyze GM properties using the trained encoder, and only visual information is needed without extra sensory modalities and human efforts for labeling. The presented GM property estimator has been extensively validated via comparison and ablation experiments. The generalization capability has also been evaluated and a real-world application on the beach is also demonstrated. Experiment videos are available at \url{https://sites.google.com/view/gmwork/vhlearning} .

Ganlong Zhao, Guanbin Li, Jia Pan et al.

Aerial Vision-and-Language Navigation (Aerial VLN) aims to obtain an unmanned aerial vehicle agent to navigate aerial 3D environments following human instruction. Compared to ground-based VLN, aerial VLN requires the agent to decide the next action in both horizontal and vertical directions based on the first-person view observations. Previous methods struggle to perform well due to the longer navigation path, more complicated 3D scenes, and the neglect of the interplay between vertical and horizontal actions. In this paper, we propose a novel grid-based view selection framework that formulates aerial VLN action prediction as a grid-based view selection task, incorporating vertical action prediction in a manner that accounts for the coupling with horizontal actions, thereby enabling effective altitude adjustments. We further introduce a grid-based bird's eye view map for aerial space to fuse the visual information in the navigation history, provide contextual scene information, and mitigate the impact of obstacles. Finally, a cross-modal transformer is adopted to explicitly align the long navigation history with the instruction. We demonstrate the superiority of our method in extensive experiments.

Shijie Lin, Xiang Zhang, Lei Yang et al.

Bimodal objects, such as the checkerboard pattern used in camera calibration, markers for object tracking, and text on road signs, to name a few, are prevalent in our daily lives and serve as a visual form to embed information that can be easily recognized by vision systems. While binarization from intensity images is crucial for extracting the embedded information in the bimodal objects, few previous works consider the task of binarization of blurry images due to the relative motion between the vision sensor and the environment. The blurry images can result in a loss in the binarization quality and thus degrade the downstream applications where the vision system is in motion. Recently, neuromorphic cameras offer new capabilities for alleviating motion blur, but it is non-trivial to first deblur and then binarize the images in a real-time manner. In this work, we propose an event-based binary reconstruction method that leverages the prior knowledge of the bimodal target's properties to perform inference independently in both event space and image space and merge the results from both domains to generate a sharp binary image. We also develop an efficient integration method to propagate this binary image to high frame rate binary video. Finally, we develop a novel method to naturally fuse events and images for unsupervised threshold identification. The proposed method is evaluated in publicly available and our collected data sequence, and shows the proposed method can outperform the SOTA methods to generate high frame rate binary video in real-time on CPU-only devices.

Yupu Lu, Yuxiang Ma, Jia Pan

This paper presents RichMap, a high-precision reachability map representation designed to balance efficiency and flexibility for versatile robot manipulation tasks. By refining the classic grid-based structure, we propose a streamlined approach that achieves performance close to compact map forms (e.g., RM4D) while maintaining structural flexibility. Our method utilizes theoretical capacity bounds on $\mathbb{S}^2$ (or $SO(3)$) to ensure rigorous coverage and employs an asynchronous pipeline for efficient construction. We validate the map against comprehensive metrics, pursuing high prediction accuracy ($>98\%$), low false positive rates ($1\sim2\%$), and fast large-batch query ($\sim$15 $μ$s/query). We extend the framework applications to quantify robot workspace similarity via maximum mean discrepancy (MMD) metrics and demonstrate energy-based guidance for diffusion policy transfer, achieving up to $26\%$ improvement for cross-embodiment scenarios in the block pushing experiment.

Yuhan Xie, Yixi Cai, Yinqiang Zhang et al.

This research tackles the challenge of real-time active view selection and uncertainty quantification on visual quality for active 3D reconstruction. Visual quality is a critical aspect of 3D reconstruction. Recent advancements such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have notably enhanced the image rendering quality of reconstruction models. Nonetheless, the efficient and effective acquisition of input images for reconstruction-specifically, the selection of the most informative viewpoint-remains an open challenge, which is crucial for active reconstruction. Existing studies have primarily focused on evaluating geometric completeness and exploring unobserved or unknown regions, without direct evaluation of the visual uncertainty within the reconstruction model. To address this gap, this paper introduces a probabilistic model that quantifies visual uncertainty for each Gaussian. Leveraging Shannon Mutual Information, we formulate a criterion, Gaussian Splatting Shannon Mutual Information (GauSS-MI), for real-time assessment of visual mutual information from novel viewpoints, facilitating the selection of next best view. GauSS-MI is implemented within an active reconstruction system integrated with a view and motion planner. Extensive experiments across various simulated and real-world scenes showcase the superior visual quality and reconstruction efficiency performance of the proposed system.

Guangze Zheng, Shijie Lin, Haobo Zuo et al.

This work proposes the Lattice Boltzmann Model (LBM) to learn real-world pixel dynamicity for visual tracking. LBM decomposes visual representations into dynamic pixel lattices and solves pixel motion states through collision-streaming processes. Specifically, the high-dimensional distribution of the target pixels is acquired through a multilayer predict-update network to estimate the pixel positions and visibility. The predict stage formulates lattice collisions among the spatial neighborhood of target pixels and develops lattice streaming within the temporal visual context. The update stage rectifies the pixel distributions with online visual representations. Compared with existing methods, LBM demonstrates practical applicability in an online and real-time manner, which can efficiently adapt to real-world visual tracking tasks. Comprehensive evaluations of real-world point tracking benchmarks such as TAP-Vid and RoboTAP validate LBM's efficiency. A general evaluation of large-scale open-world object tracking benchmarks such as TAO, BFT, and OVT-B further demonstrates LBM's real-world practicality.

Chenyu Liu, Jinshui Hu, Baocai Yin et al.

Online Handwritten Text Recognition (OLHTR) has gained considerable attention for its diverse range of applications. Current approaches usually treat OLHTR as a sequence recognition task, employing either a single trajectory or image encoder, or multi-stream encoders, combined with a CTC or attention-based recognition decoder. However, these approaches face several drawbacks: 1) single encoders typically focus on either local trajectories or visual regions, lacking the ability to dynamically capture relevant global features in challenging cases; 2) multi-stream encoders, while more comprehensive, suffer from complex structures and increased inference costs. To tackle this, we propose a Collaborative learning-based OLHTR framework, called Col-OLHTR, that learns multimodal features during training while maintaining a single-stream inference process. Col-OLHTR consists of a trajectory encoder, a Point-to-Spatial Alignment (P2SA) module, and an attention-based decoder. The P2SA module is designed to learn image-level spatial features through trajectory-encoded features and 2D rotary position embeddings. During training, an additional image-stream encoder-decoder is collaboratively trained to provide supervision for P2SA features. At inference, the extra streams are discarded, and only the P2SA module is used and merged before the decoder, simplifying the process while preserving high performance. Extensive experimental results on several OLHTR benchmarks demonstrate the state-of-the-art (SOTA) performance, proving the effectiveness and robustness of our design.