Pengwei Wang

Lingfeng Zhang, Xiaoshuai Hao, Qinwen Xu et al.

Vision-and-language navigation (VLN) is a key task in Embodied AI, requiring agents to navigate diverse and unseen environments while following natural language instructions. Traditional approaches rely heavily on historical observations as spatio-temporal contexts for decision making, leading to significant storage and computational overhead. In this paper, we introduce MapNav, a novel end-to-end VLN model that leverages Annotated Semantic Map (ASM) to replace historical frames. Specifically, our approach constructs a top-down semantic map at the start of each episode and update it at each timestep, allowing for precise object mapping and structured navigation information. Then, we enhance this map with explicit textual labels for key regions, transforming abstract semantics into clear navigation cues and generate our ASM. MapNav agent using the constructed ASM as input, and use the powerful end-to-end capabilities of VLM to empower VLN. Extensive experiments demonstrate that MapNav achieves state-of-the-art (SOTA) performance in both simulated and real-world environments, validating the effectiveness of our method. Moreover, we will release our ASM generation source code and dataset to ensure reproducibility, contributing valuable resources to the field. We believe that our proposed MapNav can be used as a new memory representation method in VLN, paving the way for future research in this field.

Shihan Wu, Xuecheng Liu, Shaoxuan Xie et al.

Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware heterogeneity across bimanual robotic platforms. To bridge this gap, we introduce RoboCOIN, a large-scale multi-embodiment bimanual manipulation dataset comprising over 180,000 demonstrations collected from 15 distinct robotic platforms. Spanning 16 diverse environments-including residential, commercial, and industrial settings-the dataset features 421 bimanual tasks systematically categorized by 39 bimanual collaboration actions and 432 objects. A key innovation of our work is the hierarchical capability pyramid, which provides granular annotations ranging from trajectory-level concepts to segment-level subtasks and frame-level kinematics. Furthermore, we present CoRobot, an efficient data processing pipeline powered by the Robot Trajectory Markup Language (RTML), designed to facilitate quality assessment, automated annotation, and unified multi-embodiment and data management. Extensive experiments demonstrate the effectiveness of RoboCOIN in enhancing the performance of various bimanual manipulation models across a wide spectrum of robotic embodiments. The entire dataset and codebase are fully open-sourced, providing a valuable resource for advancing research in bimanual and multi-embodiment manipulation.

Shuanghao Bai, Jing Lyu, Wanqi Zhou et al.

Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representations that mismatch continuous perception and control. We propose Latent Reasoning VLA (LaRA-VLA), a unified VLA framework that internalizes multi-modal CoT reasoning into continuous latent representations for embodied action. LaRA-VLA performs unified reasoning and prediction in latent space, eliminating explicit CoT generation at inference time and enabling efficient, action-oriented control. To realize latent embodied reasoning, we introduce a curriculum-based training paradigm that progressively transitions from explicit textual and visual CoT supervision to latent reasoning, and finally adapts latent reasoning dynamics to condition action generation. We construct two structured CoT datasets and evaluate LaRA-VLA on both simulation benchmarks and long-horizon real-robot manipulation tasks. Experimental results show that LaRA-VLA consistently outperforms state-of-the-art VLA methods while reducing inference latency by up to 90\% compared to explicit CoT-based approaches, demonstrating latent reasoning as an effective and efficient paradigm for real-time embodied control. Project Page: https://loveju1y.github.io/Latent-Reasoning-VLA/

Pengwei Wang

Generative Adversarial Networks (GAN) is currently widely used as an unsupervised image generation method. Current state-of-the-art GANs can generate photorealistic images with high resolution. However, a large amount of data is required, or the model would prone to generate images with similar patterns (mode collapse) and bad quality. I proposed an additional structure and loss function for GANs called LFM, trained to maximize the feature diversity between the different dimensions of the latent space to avoid mode collapse without affecting the image quality. Orthogonal latent vector pairs are created, and feature vector pairs extracted by discriminator are examined by dot product, with which discriminator and generator are in a novel adversarial relationship. In experiments, this system has been built upon DCGAN and proved to have improvement on Frechet Inception Distance (FID) training from scratch on CelebA Dataset. This system requires mild extra performance and can work with data augmentation methods. The code is available on github.com/penway/LFM.

Zongzheng Zhang, Jingrui Pang, Zhuo Yang et al.

Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper control or single-arm dexterous hand manipulation. While low-dimensional gripper control can often be handled with simpler methods, high-dimensional dexterous hand control benefits greatly from full end-to-end VLA learning. In this work, we introduce Dexora, the first open-source VLA system that natively targets dual-arm, dual-hand high-DoF manipulation. We design a hybrid teleoperation pipeline that decouples gross arm kinematics (captured with a custom exoskeleton backpack) from fine finger motion (markerless hand tracking via Apple Vision Pro), and that drives both a physical dual-arm dual-hand platform and an identical MuJoCo digital twin. Using that interface, we assemble a large training corpus: an embodiment-matched synthetic corpus (100K simulated trajectories, 6.5M frames) and a real-world dataset of 10K teleoperated episodes (2.92M frames). To mitigate noisy teleoperation demonstrations, we propose a data-quality-aware training recipe: an offline discriminator provides clip-level weights for diffusion-transformer policy training, down-weighting low-quality demonstrations. Empirically, Dexora outperforms competitive VLA baselines on both basic and dexterous benchmarks (e.g., average dexterous success 66.7% vs. 51.7%), attains 90% success on basic tasks, and shows robust out-of-distribution and cross-embodiment generalization. Ablations confirm the importance of real data and the discriminator for dexterity.

Tong Zhang, Yong Liu, Boyang Li et al.

With the evolution of pre-trained language models, current open-domain dialogue systems have achieved great progress in conducting one-session conversations. In contrast, Multi-Session Conversation (MSC), which consists of multiple sessions over a long term with the same user, is under-investigated. In this paper, we propose History-Aware Hierarchical Transformer (HAHT) for multi-session open-domain dialogue. HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses. Specifically, HAHT first encodes history conversation sessions hierarchically into a history memory. Then, HAHT leverages historical information to facilitate the understanding of the current conversation context by encoding the history memory together with the current context with attention-based mechanisms. Finally, to explicitly utilize historical information, HAHT uses a history-aware response generator that switches between a generic vocabulary and a history-aware vocabulary. Experimental results on a large-scale MSC dataset suggest that the proposed HAHT model consistently outperforms baseline models. Human evaluation results support that HAHT generates more human-like, context-relevant and history-relevant responses than baseline models.

Yuheng Ji, Yuyang Liu, Huajie Tan et al.

Current robotic evaluation is still largely dominated by binary success rates, which collapse rich execution processes into a single outcome and obscure critical qualities such as progress, efficiency, and stability. To address this limitation, we propose PRM-as-a-Judge, a dense evaluation paradigm that leverages Process Reward Models (PRMs) to audit policy execution directly from trajectory videos by estimating task progress from observation sequences. Central to this paradigm is the OPD (Outcome-Process-Diagnosis) metric system, which explicitly formalizes execution quality via a task-aligned progress potential. We characterize dense robotic evaluation through two axiomatic properties: macro-consistency, which requires additive and path-consistent aggregation, and micro-resolution, which requires sensitivity to fine-grained physical evolution. Under this formulation, potential-based PRM judges provide a natural instantiation of dense evaluation, with macro-consistency following directly from the induced scalar potential. We empirically validate the micro-resolution property using RoboPulse, a diagnostic benchmark specifically designed for probing micro-scale progress discrimination, where several trajectory-trained PRM judges outperform discriminative similarity-based methods and general-purpose foundation-model judges. Finally, leveraging PRM-as-a-Judge and the OPD metric system, we conduct a structured audit of mainstream policy paradigms across long-horizon tasks, revealing behavioral signatures and failure modes that are invisible to outcome-only metrics.

Mengzhen Liu, Enshen Zhou, Cheng Chi et al.

Active perception and manipulation are crucial for robots to interact with complex scenes. Existing methods struggle to unify semantic-driven active perception with robust, viewpoint-invariant execution. We propose SaPaVe, an end-to-end framework that jointly learns these capabilities in a data-efficient manner. Our approach decouples camera and manipulation actions rather than placing them in a shared action space, and follows a bottom-up training strategy: we first train semantic camera control on a large-scale dataset, then jointly optimize both action types using hybrid data. To support this framework, we introduce ActiveViewPose-200K, a dataset of 200k image-language-camera movement pairs for semantic camera movement learning, and a 3D geometry-aware module that improves execution robustness under dynamic viewpoints. We also present ActiveManip-Bench, the first benchmark for evaluating active manipulation beyond fixed-view settings. Extensive experiments in both simulation and real-world environments show that SaPaVe outperforms recent vision-language-action models such as GR00T N1 and \(π_0\), achieving up to 31.25\% higher success rates in real-world tasks. These results show that tightly coupled perception and execution, when trained with decoupled yet coordinated strategies, enable efficient and generalizable active manipulation. Project page: https://lmzpai.github.io/SaPaVe

Zhe Li, Cheng Chi, Boan Zhu et al.

Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art humanoid locomotion systems rely on either curated motion capture trajectories or sparse text commands, leaving a critical gap between visual understanding and control. Text-to-motion methods suffer from semantic sparsity and staged pipeline errors, while video-based approaches only perform mechanical pose mimicry without genuine visual understanding. We propose RoboMirror, the first retargeting-free video-to-locomotion framework embodying "understand before you imitate". Leveraging VLMs, it distills raw egocentric/third-person videos into visual motion intents, which directly condition a diffusion-based policy to generate physically plausible, semantically aligned locomotion without explicit pose reconstruction or retargeting. Extensive experiments validate the effectiveness of RoboMirror, it enables telepresence via egocentric videos, drastically reduces third-person control latency by 80%, and achieves a 3.7% higher task success rate than baselines. By reframing humanoid control around video understanding, we bridge the visual understanding and action gap.

Weibin Yang, Longwei Xu, Pengwei Wang et al.

U-Net and its variants have been widely used in medical image segmentation. However, most current U-Net variants confine their improvement strategies to building more complex encoder, while leaving the decoder unchanged or adopting a simple symmetric structure. These approaches overlook the true functionality of the decoder: receiving low-resolution feature maps from the encoder and restoring feature map resolution and lost information through upsampling. As a result, the decoder, especially its upsampling component, plays a crucial role in enhancing segmentation outcomes. However, in 3D medical image segmentation, the commonly used transposed convolution can result in visual artifacts. This issue stems from the absence of direct relationship between adjacent pixels in the output feature map. Furthermore, plain encoder has already possessed sufficient feature extraction capability because downsampling operation leads to the gradual expansion of the receptive field, but the loss of information during downsampling process is unignorable. To address the gap in relevant research, we extend our focus beyond the encoder and introduce neU-Net (i.e., not complex encoder U-Net), which incorporates a novel Sub-pixel Convolution for upsampling to construct a powerful decoder. Additionally, we introduce multi-scale wavelet inputs module on the encoder side to provide additional information. Our model design achieves excellent results, surpassing other state-of-the-art methods on both the Synapse and ACDC datasets.

Ao Li, Longwei Xu, Chen Ling et al.

Sentiment and emotion understanding are essential to applications such as human-computer interaction and depression detection. While Multimodal Large Language Models (MLLMs) demonstrate robust general capabilities, they face considerable challenges in the field of affective computing, particularly in detecting subtle facial expressions and handling complex emotion-related tasks, such as emotion reason inference and understanding emotions in long-context scenarios. Furthermore, there is a lack of a unified MLLM that can effectively handle both sentiment and emotion-related tasks. To address these challenges, we explore multi-task training strategies for MLLMs in affective computing and introduce Emotion Universe (EmoVerse), an MLLM designed to handle a broad spectrum of sentiment and emotion-related tasks. In addition, EmoVerse is capable of deeply analyzing the underlying causes of emotional states. We also introduce the Affective Multitask (AMT) Dataset, which supports multimodal sentiment analysis, multimodal emotion recognition, facial expression recognition, emotion reason inference, and emotion cause-pair extraction tasks. Extensive experiments demonstrate that EmoVerse outperforms existing methods, achieving state-of-the-art results in sentiment and emotion-related tasks. The code is available at https://github.com/liaolea/EmoVerse.

Ruoxuan Feng, Yuxuan Zhou, Siyu Mei et al.

Real-world contact-rich manipulation demands robots to perceive temporal tactile feedback, capture subtle surface deformations, and reason about object properties as well as force dynamics. Although optical tactile sensors are uniquely capable of providing such rich information, existing tactile datasets and models remain limited. These resources primarily focus on object-level attributes (e.g., material) while largely overlooking fine-grained tactile temporal dynamics during physical interactions. We consider that advancing dynamic tactile perception requires a systematic hierarchy of dynamic perception capabilities to guide both data collection and model design. To address the lack of tactile data with rich dynamic information, we present ToucHD, a large-scale hierarchical tactile dataset spanning tactile atomic actions, real-world manipulations, and touch-force paired data. Beyond scale, ToucHD establishes a comprehensive tactile dynamic data ecosystem that explicitly supports hierarchical perception capabilities from the data perspective. Building on it, we propose AnyTouch 2, a general tactile representation learning framework for diverse optical tactile sensors that unifies object-level understanding with fine-grained, force-aware dynamic perception. The framework captures both pixel-level and action-specific deformations across frames, while explicitly modeling physical force dynamics, thereby learning multi-level dynamic perception capabilities from the model perspective. We evaluate our model on benchmarks that covers static object properties and dynamic physical attributes, as well as real-world manipulation tasks spanning multiple tiers of dynamic perception capabilities-from basic object-level understanding to force-aware dexterous manipulation. Experimental results demonstrate consistent and strong performance across sensors and tasks.

Yuheng Ji, Huajie Tan, Cheng Chi et al.

We introduce \textsc{MathSticks}, a benchmark for Visual Symbolic Compositional Reasoning (VSCR), which unifies visual perception, symbolic manipulation, and arithmetic consistency. Each task presents an incorrect matchstick equation that must be corrected by moving one or two sticks under strict conservation rules. The benchmark includes both text-guided and purely visual settings, systematically covering digit scale, move complexity, solution multiplicity, and operator variation, with 1.4M generated instances and a curated test set. Evaluations of 14 vision--language models reveal substantial limitations: closed-source models succeed only on simple cases, open-source models fail in the visual regime, while humans exceed 90\% accuracy. These findings establish \textsc{MathSticks} as a rigorous testbed for advancing compositional reasoning across vision and symbols. Our code and dataset are publicly available at https://github.com/Yuheng2000/MathSticks.

Huajie Tan, Yuheng Ji, Xiaoshuai Hao et al.

Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods enhance Vision-Language Models (VLMs) through Chain-of-Thought (CoT) supervised fine-tuning using meticulously annotated data. However, this approach may lead to overfitting and cognitive rigidity, limiting the model's generalization ability under domain shifts and reducing real-world applicability. To overcome these limitations, we propose Reason-RFT, a two-stage reinforcement fine-tuning framework for visual reasoning. First, Supervised Fine-Tuning (SFT) with curated CoT data activates the reasoning potential of VLMs. This is followed by reinforcement learning based on Group Relative Policy Optimization (GRPO), which generates multiple reasoning-response pairs to enhance adaptability to domain shifts. To evaluate Reason-RFT, we reconstructed a comprehensive dataset covering visual counting, structural perception, and spatial transformation, serving as a benchmark for systematic assessment across three key dimensions. Experimental results highlight three advantages: (1) performance enhancement, with Reason-RFT achieving state-of-the-art results and outperforming both open-source and proprietary models; (2) generalization superiority, maintaining robust performance under domain shifts across various tasks; and (3) data efficiency, excelling in few-shot learning scenarios and surpassing full-dataset SFT baselines. Reason-RFT introduces a novel training paradigm for visual reasoning and marks a significant step forward in multimodal research. Project website: https://tanhuajie.github.io/ReasonRFT

Ao Li, Zongfang Liu, Xinhua Li et al.

Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt template design. Although prompt learning methods can address the sensitivity issue by replacing natural language prompts with learnable ones, they are incomprehensible to humans. Ensuring consistent performance across various prompt templates enables models to adapt seamlessly to diverse phrasings, enhancing their ability to handle downstream tasks without requiring extensive prompt engineering. In this work, we introduce the RobustPrompt Benchmark, a systematic benchmark to evaluate robustness to different prompt templates for VLMs. It includes a dataset with hundreds of carefully designed prompt templates, divided into six types, covering a wide variety of commonly used templates. Beside the benchmark, we propose Modeling Variants of Prompts (MVP), a simple yet effective method that mitigates sensitivity by modeling variants of prompt structures. The innovation of MVP lies in decoupling prompts into templates and class names, and using Variational Autoencoders (VAE) to model the distribution of diverse prompt structures. Experiments across 11 datasets demonstrate that MVP can greatly enhance model robustness to variations in input prompts without a drop in performance. The code is available at https://github.com/liaolea/MVP.

Yuheng Ji, Huajie Tan, Jiayu Shi et al.

Recent advancements in Multimodal Large Language Models (MLLMs) have shown remarkable capabilities across various multimodal contexts. However, their application in robotic scenarios, particularly for long-horizon manipulation tasks, reveals significant limitations. These limitations arise from the current MLLMs lacking three essential robotic brain capabilities: Planning Capability, which involves decomposing complex manipulation instructions into manageable sub-tasks; Affordance Perception, the ability to recognize and interpret the affordances of interactive objects; and Trajectory Prediction, the foresight to anticipate the complete manipulation trajectory necessary for successful execution. To enhance the robotic brain's core capabilities from abstract to concrete, we introduce ShareRobot, a high-quality heterogeneous dataset that labels multi-dimensional information such as task planning, object affordance, and end-effector trajectory. ShareRobot's diversity and accuracy have been meticulously refined by three human annotators. Building on this dataset, we developed RoboBrain, an MLLM-based model that combines robotic and general multi-modal data, utilizes a multi-stage training strategy, and incorporates long videos and high-resolution images to improve its robotic manipulation capabilities. Extensive experiments demonstrate that RoboBrain achieves state-of-the-art performance across various robotic tasks, highlighting its potential to advance robotic brain capabilities.

Yueru Jia, Jiaming Liu, Sixiang Chen et al.

3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on the explicit extraction of 3D features, while still facing challenges such as the lack of large-scale robotic 3D data and the potential loss of spatial geometry. To address these limitations, we propose the Lift3D framework, which progressively enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manipulation policy. Specifically, we first design a task-aware masked autoencoder that masks task-relevant affordance patches and reconstructs depth information, enhancing the 2D foundation model's implicit 3D robotic representation. After self-supervised fine-tuning, we introduce a 2D model-lifting strategy that establishes a positional mapping between the input 3D points and the positional embeddings of the 2D model. Based on the mapping, Lift3D utilizes the 2D foundation model to directly encode point cloud data, leveraging large-scale pretrained knowledge to construct explicit 3D robotic representations while minimizing spatial information loss. In experiments, Lift3D consistently outperforms previous state-of-the-art methods across several simulation benchmarks and real-world scenarios.

Yuxiang Duan, Ao Li, Yingqin Li et al.

Multimodal large language models (MLLMs) have shown remarkable capabilities in a wide range of vision-language tasks. However, the large number of visual tokens introduces significant computational overhead. To address this issue, visual token pruning has emerged as a key technique for enhancing the efficiency of MLLMs. In cognitive science, humans tend to first determine which regions of a scene to attend to ("where to look") before deciding which specific elements within those regions to process in detail ("what to select"). This two-stage strategy enables the visual system to efficiently allocate attention at a coarse spatial level before performing fine-grained selection. However, existing pruning methods primarily focus on directly optimizing "what to select", typically using attention scores or similarity metrics. They rarely consider "where to look", which has been shown to lead to inefficient spatial allocation, positional bias, and the retention of irrelevant or redundant tokens. In this paper, we propose GridPrune, a method that replaces the global Top-K mechanism with a "guide-globally, select-locally" zonal selection system. GridPrune splits the pruning process into two steps: first, it uses text-conditional guidance to dynamically allocate a token budget across spatial zones; and then, it performs local selection within each budgeted zone. Experimental results demonstrate that GridPrune achieves superior performance across various MLLM architectures. On LLaVA-NeXT-7B, GridPrune retains 96.98% of the full performance while using 11.1% of the tokens, outperforming the best-performing baseline by 2.34% at the same pruning rate.

Enshen Zhou, Jingkun An, Cheng Chi et al.

Spatial referring is a fundamental capability of embodied robots to interact with the 3D physical world. However, even with the powerful pretrained vision language models (VLMs), recent approaches are still not qualified to accurately understand the complex 3D scenes and dynamically reason about the instruction-indicated locations for interaction. To this end, we propose RoboRefer, a 3D-aware VLM that can first achieve precise spatial understanding by integrating a disentangled but dedicated depth encoder via supervised fine-tuning (SFT). Moreover, RoboRefer advances generalized multi-step spatial reasoning via reinforcement fine-tuning (RFT), with metric-sensitive process reward functions tailored for spatial referring tasks. To support SFT and RFT training, we introduce RefSpatial, a large-scale dataset of 20M QA pairs (2x prior), covering 31 spatial relations (vs. 15 prior) and supporting complex reasoning processes (up to 5 steps). In addition, we introduce RefSpatial-Bench, a challenging benchmark filling the gap in evaluating spatial referring with multi-step reasoning. Experiments show that SFT-trained RoboRefer achieves state-of-the-art spatial understanding, with an average success rate of 89.6%. RFT-trained RoboRefer further outperforms all other baselines by a large margin, even surpassing Gemini-2.5-Pro by 17.4% in average accuracy on RefSpatial-Bench. Notably, RoboRefer can be integrated with various control policies to execute long-horizon, dynamic tasks across diverse robots (e,g., UR5, G1 humanoid) in cluttered real-world scenes. Please see the project page at https://zhoues.github.io/RoboRefer.

Shuyi Zhang, Xiaoshuai Hao, Yingbo Tang et al.

Video content comprehension is essential for various applications, ranging from video analysis to interactive systems. Despite advancements in large-scale vision-language models (VLMs), these models often struggle to capture the nuanced, spatiotemporal details essential for thorough video analysis. To address this gap, we introduce Video-CoT, a groundbreaking dataset designed to enhance spatiotemporal understanding using Chain-of-Thought (CoT) methodologies. Video-CoT contains 192,000 fine-grained spa-tiotemporal question-answer pairs and 23,000 high-quality CoT-annotated samples, providing a solid foundation for evaluating spatiotemporal understanding in video comprehension. Additionally, we provide a comprehensive benchmark for assessing these tasks, with each task featuring 750 images and tailored evaluation metrics. Our extensive experiments reveal that current VLMs face significant challenges in achieving satisfactory performance, high-lighting the difficulties of effective spatiotemporal understanding. Overall, the Video-CoT dataset and benchmark open new avenues for research in multimedia understanding and support future innovations in intelligent systems requiring advanced video analysis capabilities. By making these resources publicly available, we aim to encourage further exploration in this critical area. Project website:https://video-cot.github.io/ .

Xiaoshuai Hao, Lingdong Kong, Rong Yin et al.

Robust high-definition (HD) map construction is vital for autonomous driving, yet existing methods often struggle with incomplete multi-view camera data. This paper presents SafeMap, a novel framework specifically designed to secure accuracy even when certain camera views are missing. SafeMap integrates two key components: the Gaussian-based Perspective View Reconstruction (G-PVR) module and the Distillation-based Bird's-Eye-View (BEV) Correction (D-BEVC) module. G-PVR leverages prior knowledge of view importance to dynamically prioritize the most informative regions based on the relationships among available camera views. Furthermore, D-BEVC utilizes panoramic BEV features to correct the BEV representations derived from incomplete observations. Together, these components facilitate the end-to-end map reconstruction and robust HD map generation. SafeMap is easy to implement and integrates seamlessly into existing systems, offering a plug-and-play solution for enhanced robustness. Experimental results demonstrate that SafeMap significantly outperforms previous methods in both complete and incomplete scenarios, highlighting its superior performance and reliability.

Yunfan Lou, Xiaowei Chi, Xiaojie Zhang et al.

World models derived from large-scale video generative pre-training have emerged as a promising paradigm for generalist robot policy learning. However, standard approaches often focus on high-fidelity RGB video prediction, this can result in overfitting to irrelevant factors, such as dynamic backgrounds and illumination changes. These distractions reduce the model's ability to generalize, ultimately leading to unreliable and fragile control policies. To address this, we introduce the Mask World Model (MWM), which leverages video diffusion architectures to predict the evolution of semantic masks instead of pixels. This shift imposes a geometric information bottleneck, forcing the model to capture essential physical dynamics and contact relations while filtering out visual noise. We seamlessly integrate this mask dynamics backbone with a diffusion-based policy head to enable robust end-to-end control. Extensive evaluations demonstrate the superiority of MWM on the LIBERO and RLBench simulation benchmarks, significantly outperforming the state-of-the-art RGB-based world models. Furthermore, real-world experiments and robustness evaluation (via random token pruning) reveal that MWM exhibits superior generalization capabilities and robust resilience to texture information loss.

Sixiang Chen, Jiaming Liu, Siyuan Qian et al.

Recently, mobile manipulation has attracted increasing attention for enabling language-conditioned robotic control in household tasks. However, existing methods still face challenges in coordinating mobile base and manipulator, primarily due to two limitations. On the one hand, they fail to explicitly model the influence of the mobile base on manipulator control, which easily leads to error accumulation under high degrees of freedom. On the other hand, they treat the entire mobile manipulation process with the same visual observation modality (e.g., either all 2D or all 3D), overlooking the distinct multimodal perception requirements at different stages during mobile manipulation. To address this, we propose the Adaptive Coordination Diffusion Transformer (AC-DiT), which enhances mobile base and manipulator coordination for end-to-end mobile manipulation. First, since the motion of the mobile base directly influences the manipulator's actions, we introduce a mobility-to-body conditioning mechanism that guides the model to first extract base motion representations, which are then used as context prior for predicting whole-body actions. This enables whole-body control that accounts for the potential impact of the mobile base's motion. Second, to meet the perception requirements at different stages of mobile manipulation, we design a perception-aware multimodal conditioning strategy that dynamically adjusts the fusion weights between various 2D visual images and 3D point clouds, yielding visual features tailored to the current perceptual needs. This allows the model to, for example, adaptively rely more on 2D inputs when semantic information is crucial for action prediction, while placing greater emphasis on 3D geometric information when precise spatial understanding is required. We validate AC-DiT through extensive experiments on both simulated and real-world mobile manipulation tasks.

Yi Han, Cheng Chi, Enshen Zhou et al.

Vision-Language Models (VLMs) have shown remarkable capabilities in spatial reasoning, yet they remain fundamentally limited to qualitative precision and lack the computational precision required for real-world robotics. Current approaches fail to leverage metric cues from depth sensors and camera calibration, instead reducing geometric problems to pattern recognition tasks that cannot deliver the centimeter-level accuracy essential for robotic manipulation. We present TIGeR (Tool-Integrated Geometric Reasoning), a novel framework that transforms VLMs from perceptual estimators to geometric computers by enabling them to generate and execute precise geometric computations through external tools. Rather than attempting to internalize complex geometric operations within neural networks, TIGeR empowers models to recognize geometric reasoning requirements, synthesize appropriate computational code, and invoke specialized libraries for exact calculations. To support this paradigm, we introduce TIGeR-300K, a comprehensive tool-invocation-oriented dataset covering point transformations, pose estimation, and spatial compatibility verification, complete with tool invocation sequences and intermediate computations. Through a two-stage training pipeline combining supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT) with our proposed hierarchical reward design, TIGeR achieves SOTA performance on geometric reasoning benchmarks while demonstrating centimeter-level precision in real-world robotic manipulation tasks.

Wee Kiat Chan, PengWei Wang, Raye Chen-Hua Yeow

Soft robotics has emerged as a promising field with the potential to revolutionize industries such as healthcare and manufacturing. However, designing effective soft robots presents challenges, particularly in managing the complex interplay of material properties, structural design, and control strategies. Traditional design methods are often time-consuming and may not yield optimal designs. In this paper, we explore the use of generative AI to create 3D models of soft actuators. We create a dataset of over 70 text-shape pairings of soft pneumatic robot actuator designs, and adapt a latent diffusion model (SDFusion) to learn the data distribution and generate novel designs from it. By employing transfer learning and data augmentation techniques, we significantly improve the performance of the diffusion model. These findings highlight the potential of generative AI in designing complex soft robotic systems, paving the way for future advancements in the field.

Yulin Luo, Chun-Kai Fan, Menghang Dong et al.

Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a core challenge. Recent embodied systems often adopt a dual-system paradigm, where System 2 handles high-level reasoning while System 1 executes low-level control. In this work, we refer to System 2 as the embodied brain, emphasizing its role as the cognitive core for reasoning and decision-making in manipulation tasks. Given this role, systematic evaluation of the embodied brain is essential. Yet existing benchmarks emphasize execution success, or when targeting high-level reasoning, suffer from incomplete dimensions and limited task realism, offering only a partial picture of cognitive capability. To bridge this gap, we introduce RoboBench, a benchmark that systematically evaluates multimodal large language models (MLLMs) as embodied brains. Motivated by the critical roles across the full manipulation pipeline, RoboBench defines five dimensions-instruction comprehension, perception reasoning, generalized planning, affordance prediction, and failure analysis-spanning 14 capabilities, 25 tasks, and 6092 QA pairs. To ensure realism, we curate datasets across diverse embodiments, attribute-rich objects, and multi-view scenes, drawing from large-scale real robotic data. For planning, RoboBench introduces an evaluation framework, MLLM-as-world-simulator. It evaluate embodied feasibility by simulating whether predicted plans can achieve critical object-state changes. Experiments on 14 MLLMs reveal fundamental limitations: difficulties with implicit instruction comprehension, spatiotemporal reasoning, cross-scenario planning, fine-grained affordance understanding, and execution failure diagnosis. RoboBench provides a comprehensive scaffold to quantify high-level cognition, and guide the development of next-generation embodied MLLMs. The project page is in https://robo-bench.github.io.

Zhe Li, Cheng Chi, Yangyang Wei et al.

Natural language offers a natural interface for humanoid robots, but existing language-guided humanoid locomotion pipelines remain cumbersome and untrustworthy. They typically decode human motion, retarget it to robot morphology, and then track it with a physics-based controller. However, this multi-stage process is prone to cumulative errors, introduces high latency, and yields weak coupling between semantics and control. These limitations call for a more direct pathway from language to action, one that eliminates fragile intermediate stages. Therefore, we present RoboGhost, a retargeting-free framework that directly conditions humanoid policies on language-grounded motion latents. By bypassing explicit motion decoding and retargeting, RoboGhost enables a diffusion-based policy to denoise executable actions directly from noise, preserving semantic intent and supporting fast, reactive control. A hybrid causal transformer-diffusion motion generator further ensures long-horizon consistency while maintaining stability and diversity, yielding rich latent representations for precise humanoid behavior. Extensive experiments demonstrate that RoboGhost substantially reduces deployment latency, improves success rates and tracking precision, and produces smooth, semantically aligned locomotion on real humanoids. Beyond text, the framework naturally extends to other modalities such as images, audio, and music, providing a universal foundation for vision-language-action humanoid systems.

Huaihai Lyu, Chaofan Chen, Senwei Xie et al.

Existing Vision-Language-Action (VLA) models can be broadly categorized into diffusion-based and auto-regressive (AR) approaches: diffusion models capture continuous action distributions but rely on computationally heavy iterative denoising. In contrast, AR models enable efficient optimization and flexible sequence construction, making them better suited for large-scale pretraining. To further improve AR efficiency, particularly when action chunks induce extended and high-dimensional sequences, prior work applies entropy-guided and token-frequency techniques to shorten the sequence length. However, such compression struggled with \textit{poor reconstruction or inefficient compression}. Motivated by this, we introduce an Omni Swift Action Tokenizer, which learns a compact, transferable action representation. Specifically, we first normalize value ranges and temporal horizons to obtain a consistent representation with B-Spline encoding. Then, we apply multi-stage residual quantization to the position, rotation, and gripper subspaces, producing compressed discrete tokens with coarse-to-fine granularity for each part. After pre-training on the large-scale dataset Droid, the resulting discrete tokenization shortens the training sequence by 6.8$\times$, and lowers the target entropy. To further explore the potential of OmniSAT, we develop a cross-embodiment learning strategy that builds on the unified action-pattern space and jointly leverages robot and human demonstrations. It enables scalable auxiliary supervision from heterogeneous egocentric videos. Across diverse real-robot and simulation experiments, OmniSAT encompasses higher compression while preserving reconstruction quality, enabling faster AR training convergence and model performance.

Enshen Zhou, Cheng Chi, Yibo Li et al.

Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spatial referring and real-world metric measurement. However, existing methods struggle with this compositional task. To this end, we propose RoboTracer, a 3D-aware VLM that first achieves both 3D spatial referring and measuring via a universal spatial encoder and a regression-supervised decoder to enhance scale awareness during supervised fine-tuning (SFT). Moreover, RoboTracer advances multi-step metric-grounded reasoning via reinforcement fine-tuning (RFT) with metric-sensitive process rewards, supervising key intermediate perceptual cues to accurately generate spatial traces. To support SFT and RFT training, we introduce TraceSpatial, a large-scale dataset of 30M QA pairs, spanning outdoor/indoor/tabletop scenes and supporting complex reasoning processes (up to 9 steps). We further present TraceSpatial-Bench, a challenging benchmark filling the gap to evaluate spatial tracing. Experimental results show that RoboTracer surpasses baselines in spatial understanding, measuring, and referring, with an average success rate of 79.1%, and also achieves SOTA performance on TraceSpatial-Bench by a large margin, exceeding Gemini-2.5-Pro by 36% accuracy. Notably, RoboTracer can be integrated with various control policies to execute long-horizon, dynamic tasks across diverse robots (UR5, G1 humanoid) in cluttered real-world scenes. See the project page at https://zhoues.github.io/RoboTracer.

Cheng Peng, Zhenzhe Zhang, Cheng Chi et al.

Navigating to a specified object in an unknown environment is a fundamental yet challenging capability of embodied intelligence. However, current methods struggle to balance decision frequency with intelligence, resulting in decisions lacking foresight or discontinuous actions. In this work, we propose PIGEON: Point of Interest Guided Exploration for Object Navigation with VLM, maintaining a lightweight and semantically aligned snapshot memory during exploration as semantic input for the exploration strategy. We use a large Visual-Language Model (VLM), named PIGEON-VL, to select Points of Interest (PoI) formed during exploration and then employ a lower-level planner for action output, increasing the decision frequency. Additionally, this PoI-based decision-making enables the generation of Reinforcement Learning with Verifiable Reward (RLVR) data suitable for simulators. Experiments on classic object navigation benchmarks demonstrate that our zero-shot transfer method achieves state-of-the-art performance, while RLVR further enhances the model's semantic guidance capabilities, enabling deep reasoning during real-time navigation.

Yankai Fu, Ning Chen, Junkai Zhao et al.

Building a generalist robot that can perceive, reason, and act across diverse tasks remains an open challenge, especially for dexterous manipulation. A major bottleneck lies in the scarcity of large-scale, action-annotated data for dexterous skills, as teleoperation is difficult and costly. Human data, with its vast scale and diverse manipulation behaviors, provides rich priors for learning robotic actions. While prior works have explored leveraging human demonstrations, they are often constrained by limited scenarios and a large visual gap between human and robots. To eliminate these limitations, we propose METIS, a vision-language-action (VLA) model for dexterous manipulation pretrained on multi-source egocentric datasets. We first construct EgoAtlas, which integrates large-scale human and robotic data from multiple sources, all unified under a consistent action space. We further extract motion-aware dynamics, a compact and discretized motion representation, which provides efficient and expressive supervision for VLA training. Built upon them, METIS integrates reasoning and acting into a unified framework, enabling effective deployment to downstream dexterous manipulation tasks. Our method demonstrates exceptional dexterous manipulation capabilities, achieving highest average success rate in six real-world tasks. Experimental results also highlight the superior generalization and robustness to out-of-distribution scenarios. These findings emphasize METIS as a promising step toward a generalist model for dexterous manipulation.

Pengwei Wang

Advances in treatment technology now allow for the use of customizable 3D-printed hydrogel wound dressings for patients with osteoradionecrosis (ORN) of the jaw (ONJ). Meanwhile, deep learning has enabled precise segmentation of 3D medical images using tools like nnUNet. However, the scarcity of labeled data in ONJ imaging makes supervised training impractical. This study aims to develop an unsupervised training approach for automatically identifying anomalies in imaging scans. We propose a novel two-stage training pipeline. In the first stage, a VQ-GAN is trained to accurately reconstruct normal subjects. In the second stage, random cube masking and ONJ-specific masking are applied to train a new encoder capable of recovering the data. The proposed method achieves successful segmentation on both simulated and real patient data. This approach provides a fast initial segmentation solution, reducing the burden of manual labeling. Additionally, it has the potential to be directly used for 3D printing when combined with hand-tuned post-processing.

Junhe Zhang, Wanli Ni, Pengwei Wang et al.

With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption and latency. In this letter, we propose a task-oriented multimodal token transmission scheme for efficient multimodal information fusion and utilization. To improve the efficiency of token transmission, we design a two-stage training algotithm, including cross-modal alignment and task-oriented fine-tuning, for large model-based token communication. Meanwhile, token compression is performed using a sliding window pooling operation to save communication resources. To balance the trade-off between latency and model performance caused by compression, we formulate a weighted-sum optimization problem over latency and validation loss. We jointly optimizes bandwidth, power allocation, and token length across users by using an alternating optimization method. Simulation results demonstrate that the proposed algorithm outperforms the baseline under different bandwidth and power budgets. Moreover, the two-stage training algorithm achieves higher accuracy across various signal-to-noise ratios than the method without cross-modal alignment.

Pengwei Wang, Xin Ye, Xiaohuan Zhou et al.

In contrast to conventional pipeline Spoken Language Understanding (SLU) which consists of automatic speech recognition (ASR) and natural language understanding (NLU), end-to-end SLU infers the semantic meaning directly from speech and overcomes the error propagation caused by ASR. End-to-end slot filling (SF) from speech is an essential component of end-to-end SLU, and is usually regarded as a sequence-to-sequence generation problem, heavily relied on the performance of language model of ASR. However, it is hard to generate a correct slot when the slot is out-of-vovabulary (OOV) in training data, especially when a slot is an anti-linguistic entity without grammatical rule. Inspired by object detection in computer vision that is to detect the object from an image, we consider SF as the task of slot detection from speech. In this paper, we formulate the SF task as a matching task and propose an end-to-end knowledge-based SF model, named Speech-to-Slot (Speech2Slot), to leverage knowledge to detect the boundary of a slot from the speech. We also release a large-scale dataset of Chinese speech for slot filling, containing more than 830,000 samples. The experiments show that our approach is markedly superior to the conventional pipeline SLU approach, and outperforms the state-of-the-art end-to-end SF approach with 12.51% accuracy improvement.

Zekun Wang, Pengwei Wang, Peter C. Louis et al.

The COVID-19 epidemic has been a significant healthcare challenge in the United States. According to the Centers for Disease Control and Prevention (CDC), COVID-19 infection is transmitted predominately by respiratory droplets generated when people breathe, talk, cough, or sneeze. Wearing a mask is the primary, effective, and convenient method of blocking 80% of all respiratory infections. Therefore, many face mask detection and monitoring systems have been developed to provide effective supervision for hospitals, airports, publication transportation, sports venues, and retail locations. However, the current commercial face mask detection systems are typically bundled with specific software or hardware, impeding public accessibility. In this paper, we propose an in-browser serverless edge-computing based face mask detection solution, called Web-based efficient AI recognition of masks (WearMask), which can be deployed on any common devices (e.g., cell phones, tablets, computers) that have internet connections using web browsers, without installing any software. The serverless edge-computing design minimizes the extra hardware costs (e.g., specific devices or cloud computing servers). The contribution of the proposed method is to provide a holistic edge-computing framework of integrating (1) deep learning models (YOLO), (2) high-performance neural network inference computing framework (NCNN), and (3) a stack-based virtual machine (WebAssembly). For end-users, our web-based solution has advantages of (1) serverless edge-computing design with minimal device limitation and privacy risk, (2) installation free deployment, (3) low computing requirements, and (4) high detection speed. Our WearMask application has been launched with public access at facemask-detection.com.

Pengwei Wang, Liangchen Wei, Yong Cao et al.

End-to-end Spoken Language Understanding (SLU) is proposed to infer the semantic meaning directly from audio features without intermediate text representation. Although the acoustic model component of an end-to-end SLU system can be pre-trained with Automatic Speech Recognition (ASR) targets, the SLU component can only learn semantic features from limited task-specific training data. In this paper, for the first time we propose to do large-scale unsupervised pre-training for the SLU component of an end-to-end SLU system, so that the SLU component may preserve semantic features from massive unlabeled audio data. As the output of the acoustic model component, i.e. phoneme posterior sequences, has much different characteristic from text sequences, we propose a novel pre-training model called BERT-PLM, which stands for Bidirectional Encoder Representations from Transformers through Permutation Language Modeling. BERT-PLM trains the SLU component on unlabeled data through a regression objective equivalent to the partial permutation language modeling objective, while leverages full bi-directional context information with BERT networks. The experiment results show that our approach out-perform the state-of-the-art end-to-end systems with over 12.5% error reduction.

Pengwei Wang, Dejing Dou, Fangzhao Wu et al.

Large scale knowledge graph embedding has attracted much attention from both academia and industry in the field of Artificial Intelligence. However, most existing methods concentrate solely on fact triples contained in the given knowledge graph. Inspired by the fact that logic rules can provide a flexible and declarative language for expressing rich background knowledge, it is natural to integrate logic rules into knowledge graph embedding, to transfer human knowledge to entity and relation embedding, and strengthen the learning process. In this paper, we propose a novel logic rule-enhanced method which can be easily integrated with any translation based knowledge graph embedding model, such as TransE . We first introduce a method to automatically mine the logic rules and corresponding confidences from the triples. And then, to put both triples and mined logic rules within the same semantic space, all triples in the knowledge graph are represented as first-order logic. Finally, we define several operations on the first-order logic and minimize a global loss over both of the mined logic rules and the transformed first-order logics. We conduct extensive experiments for link prediction and triple classification on three datasets: WN18, FB166, and FB15K. Experiments show that the rule-enhanced method can significantly improve the performance of several baselines. The highlight of our model is that the filtered Hits@1, which is a pivotal evaluation in the knowledge inference task, has a significant improvement (up to 700% improvement).

Reihaneh Safavi-Naini, Pengwei Wang

Key agreement is a fundamental cryptographic primitive. It has been proved that key agreement protocols with security against computationally unbounded adversaries cannot exist in a setting where Alice and Bob do not have dependent variables and communication between them is fully public, or fully controlled by the adversary. In this paper we consider this problem when the adversary can "partially" control the channel. We motivate these adversaries by considering adversarial corruptions at the physical layer of communication, give a definition of adversaries that can "partially" eavesdrop and "partially" corrupt the communication. We formalize security and reliability of key agreement protocols, derive bounds on the rate of key agreement, and give constructions that achieve the bound. Our results show that it is possible to have secret key agreement as long as some of the communicated symbols remain private and unchanged by the adversary. We relate our results to the previous known results, and discuss future work.

Pengwei Wang, Reihaneh Safavi-Naini

Wyner's elegant model of wiretap channel exploits noise in the communication channel to provide perfect secrecy against a computationally unlimited eavesdropper without requiring a shared key. We consider an adversarial model of wiretap channel proposed in [18,19] where the adversary is active: it selects a fraction $ρ_r$ of the transmitted codeword to eavesdrop and a fraction $ρ_w$ of the codeword to corrupt by "adding" adversarial error. It was shown that this model also captures network adversaries in the setting of 1-round Secure Message Transmission [8]. It was proved that secure communication (1-round) is possible if and only if $ρ_r + ρ_w <1$. In this paper we show that by allowing communicants to have access to a public discussion channel (authentic communication without secrecy) secure communication becomes possible even if $ρ_r + ρ_w >1$. We formalize the model of \awtppd protocol and for two efficiency measures, {\em information rate } and {\em message round complexity} derive tight bounds. We also construct a rate optimal protocol family with minimum number of message rounds. We show application of these results to Secure Message Transmission with Public Discussion (SMT-PD), and in particular show a new lower bound on transmission rate of these protocols together with a new construction of an optimal SMT-PD protocol.

Pengwei Wang, Reihaneh Safavi-Naini

In wiretap model of secure communication the goal is to provide (asymptotic) perfect secrecy and reliable communication over a noisy channel that is eavesdropped by an adversary with unlimited computational power. This goal is achieved by taking advantage of the channel noise and without requiring a shared key. The model has attracted attention in recent years because it captures eavesdropping attack in wireless communication. The wiretap adversary is a passive eavesdropping adversary at the physical layer of communication. In this paper we propose a model for adversarial wiretap (AWTP) channel that models active adversaries at this layer. We consider a $(ρ_r, ρ_w)$ wiretap adversary who can see a fraction $ρ_r$, and modify a fraction $ρ_w$, of the sent codeword. The code components that are read and/or modified can be chosen adaptively, and the subsets of read and modified components in general, can be different. AWTP codes provide secrecy and reliability for communication over these channels. We give security and reliability definitions and measures for these codes, and define secrecy capacity of an AWTP channel that represents the secrecy potential of the channel. The paper has two main contributions. First, we prove a tight upper bound on the rate of AWTP codes with perfect secrecy for $(ρ_r, ρ_w)$-AWTP channels, and use the bound to derive the secrecy capacity of the channel. We prove a similar bound for $ε$-secure codes also, but in this case the bound is not tight. Second, we give an explicit construction for a capacity achieving AWTP code family, and prove its security and efficiency properties. We show that AWTP model is a natural generalization of Wyner's wiretap models and somewhat surprisingly, also provides a direct generalization for a seemingly unrelated cryptographic primitive, Secure Message Transmission (SMT).