Zhengping Che

Shichao Fan, Kun Wu, Zhengping Che et al.

Recent progress in large-scale robotic datasets and vision-language models (VLMs) has advanced research on vision-language-action (VLA) models. However, existing VLA models still face two fundamental challenges: (i) producing precise low-level actions from high-dimensional observations, (ii) bridging domain gaps across heterogeneous data sources, including diverse robot embodiments and human demonstrations. Existing methods often encode latent variables from either visual dynamics or robotic actions to guide policy learning, but they fail to fully exploit the complementary multi-modal knowledge present in large-scale, heterogeneous datasets. In this work, we present X Robotic Model 1 (XR-1), a novel framework for versatile and scalable VLA learning across diverse robots, tasks, and environments. XR-1 introduces the \emph{Unified Vision-Motion Codes (UVMC)}, a discrete latent representation learned via a dual-branch VQ-VAE that jointly encodes visual dynamics and robotic motion. UVMC addresses these challenges by (i) serving as an intermediate representation between the observations and actions, and (ii) aligning multimodal dynamic information from heterogeneous data sources to capture complementary knowledge. To effectively exploit UVMC, we propose a three-stage training paradigm: (i) self-supervised UVMC learning, (ii) UVMC-guided pretraining on large-scale cross-embodiment robotic datasets, and (iii) task-specific post-training. We validate XR-1 through extensive real-world experiments with more than 14,000 rollouts on six different robot embodiments, spanning over 120 diverse manipulation tasks. XR-1 consistently outperforms state-of-the-art baselines such as $π_{0.5}$, $π_0$, RDT, UniVLA, and GR00T-N1.5 while demonstrating strong generalization to novel objects, background variations, distractors, and illumination changes. Our project is at https://xr-1-vla.github.io/.

Haowen Wang, Mingyuan Wang, Zhengping Che et al.

The raw depth image captured by the indoor depth sensor usually has an extensive range of missing depth values due to inherent limitations such as the inability to perceive transparent objects and limited distance range. The incomplete depth map burdens many downstream vision tasks, and a rising number of depth completion methods have been proposed to alleviate this issue. While most existing methods can generate accurate dense depth maps from sparse and uniformly sampled depth maps, they are not suitable for complementing the large contiguous regions of missing depth values, which is common and critical. In this paper, we design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map. The first branch employs an encoder-decoder structure to regress the local dense depth values from the raw depth map, with the help of local guidance information extracted from the RGB image. In the other branch, we propose an RGB-depth fusion GAN to transfer the RGB image to the fine-grained textured depth map. We adopt adaptive fusion modules named W-AdaIN to propagate the features across the two branches, and we append a confidence fusion head to fuse the two outputs of the branches for the final depth map. Extensive experiments on NYU-Depth V2 and SUN RGB-D demonstrate that our proposed method clearly improves the depth completion performance, especially in a more realistic setting of indoor environments with the help of the pseudo depth map.

Yaomin Huang, Ning Liu, Zhengping Che et al.

Channel pruning can effectively reduce both computational cost and memory footprint of the original network while keeping a comparable accuracy performance. Though great success has been achieved in channel pruning for 2D image-based convolutional networks (CNNs), existing works seldom extend the channel pruning methods to 3D point-based neural networks (PNNs). Directly implementing the 2D CNN channel pruning methods to PNNs undermine the performance of PNNs because of the different representations of 2D images and 3D point clouds as well as the network architecture disparity. In this paper, we proposed CP$^3$, which is a Channel Pruning Plug-in for Point-based network. CP$^3$ is elaborately designed to leverage the characteristics of point clouds and PNNs in order to enable 2D channel pruning methods for PNNs. Specifically, it presents a coordinate-enhanced channel importance metric to reflect the correlation between dimensional information and individual channel features, and it recycles the discarded points in PNN's sampling process and reconsiders their potentially-exclusive information to enhance the robustness of channel pruning. Experiments on various PNN architectures show that CP$^3$ constantly improves state-of-the-art 2D CNN pruning approaches on different point cloud tasks. For instance, our compressed PointNeXt-S on ScanObjectNN achieves an accuracy of 88.52% with a pruning rate of 57.8%, outperforming the baseline pruning methods with an accuracy gain of 1.94%.

Yaomin Huang, Xinmei Liu, Yichen Zhu et al.

Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently. In this paper, we propose a Label-Guided auxiliary training method for 3D object detection (LG3D), which serves as an auxiliary network to enhance the feature learning of existing 3D object detectors. Specifically, we propose two novel modules: a Label-Annotation-Inducer that maps annotations and point clouds in bounding boxes to task-specific representations and a Label-Knowledge-Mapper that assists the original features to obtain detection-critical representations. The proposed auxiliary network is discarded in inference and thus has no extra computational cost at test time. We conduct extensive experiments on both indoor and outdoor datasets to verify the effectiveness of our approach. For example, our proposed LG3D improves VoteNet by 2.5% and 3.1% mAP on the SUN RGB-D and ScanNetV2 datasets, respectively.

Zhuoyang Liu, Jiaming Liu, Jiadong Xu et al.

Vision-language-action models (VLAs) have shown generalization capabilities in robotic manipulation tasks by inheriting from vision-language models (VLMs) and learning action generation. Most VLA models focus on interpreting vision and language to generate actions, whereas robots must perceive and interact within the spatial-physical world. This gap highlights the need for a comprehensive understanding of robotic-specific multisensory information, which is crucial for achieving complex and contact-rich control. To this end, we introduce a multisensory language-action (MLA) model that collaboratively perceives heterogeneous sensory modalities and predicts future multisensory objectives to facilitate physical world modeling. Specifically, to enhance perceptual representations, we propose an encoder-free multimodal alignment scheme that innovatively repurposes the large language model itself as a perception module, directly interpreting multimodal cues by aligning 2D images, 3D point clouds, and tactile tokens through positional correspondence. To further enhance MLA's understanding of physical dynamics, we design a future multisensory generation post-training strategy that enables MLA to reason about semantic, geometric, and interaction information, providing more robust conditions for action generation. For evaluation, the MLA model outperforms the previous state-of-the-art 2D and 3D VLA methods by 12% and 24% in complex, contact-rich real-world tasks, respectively, while also demonstrating improved generalization to unseen configurations.

Zhuoyang Liu, Jiaming Liu, Hao Chen et al.

Vision-Language-Action (VLA) models have recently shown strong generalization, with some approaches seeking to explicitly generate linguistic reasoning traces or predict future observations prior to execution. However, explicit reasoning typically incurs non-negligible inference latency, which constrains the temporal resolution required for robotic manipulation. Moreover, such reasoning is confined to the linguistic space, imposing a representational bottleneck that struggles to faithfully capture ineffable physical attributes. To mitigate these limitations, we propose LaST$_0$, a framework that enables efficient reasoning before acting through a Latent Spatio-Temporal Chain-of-Thought (CoT), capturing fine-grained physical and robotic dynamics that are often difficult to verbalize. Specifically, we introduce a token-efficient latent CoT space that models future visual dynamics, 3D structural information, and robot proprioceptive states, and further extends these representations across time to enable temporally consistent implicit reasoning trajectories. Furthermore, LaST$_0$ adopts a dual-system architecture implemented via a Mixture-of-Transformers design, where a reasoning expert conducts low-frequency latent inference and an acting expert generates high-frequency actions conditioned on robotics-oriented latent representations. To facilitate coordination, LaST$_0$ is trained with heterogeneous operation frequencies, enabling adaptive switching during deployment. Across 10 real-world tasks spanning tabletop, mobile, and dexterous hand manipulation, LaST$_0$ improves mean success rates by 13%, 14% and 14% over prior SOTA VLA methods, respectively.

Haowen Wang, Zhengping Che, Yufan Yang et al.

Raw depth images captured in indoor scenarios frequently exhibit extensive missing values due to the inherent limitations of the sensors and environments. For example, transparent materials frequently elude detection by depth sensors; surfaces may introduce measurement inaccuracies due to their polished textures, extended distances, and oblique incidence angles from the sensor. The presence of incomplete depth maps imposes significant challenges for subsequent vision applications, prompting the development of numerous depth completion techniques to mitigate this problem. Numerous methods excel at reconstructing dense depth maps from sparse samples, but they often falter when faced with extensive contiguous regions of missing depth values, a prevalent and critical challenge in indoor environments. To overcome these challenges, we design a novel two-branch end-to-end fusion network named RDFC-GAN, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map. The first branch employs an encoder-decoder structure, by adhering to the Manhattan world assumption and utilizing normal maps from RGB-D information as guidance, to regress the local dense depth values from the raw depth map. The other branch applies an RGB-depth fusion CycleGAN, adept at translating RGB imagery into detailed, textured depth maps while ensuring high fidelity through cycle consistency. We fuse the two branches via adaptive fusion modules named W-AdaIN and train the model with the help of pseudo depth maps. Comprehensive evaluations on NYU-Depth V2 and SUN RGB-D datasets show that our method significantly enhances depth completion performance particularly in realistic indoor settings.

Shuanghao Bai, Meng Li, Xinyuan Lv et al.

Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making high-DoF humanoid control challenging and often unstable. We present HEX, a state-centric framework for coordinated manipulation on full-sized bipedal humanoid robots. HEX introduces a humanoid-aligned universal state representation for scalable learning across heterogeneous embodiments, and incorporates a Mixture-of-Experts Unified Proprioceptive Predictor to model whole-body coordination and temporal motion dynamics from large-scale multi-embodiment trajectory data. To efficiently capture temporal visual context, HEX uses lightweight history tokens to summarize past observations, avoiding repeated encoding of historical images during inference. It further employs a residual-gated fusion mechanism with a flow-matching action head to adaptively integrate visual-language cues with proprioceptive dynamics for action generation. Experiments on real-world humanoid manipulation tasks show that HEX achieves state-of-the-art performance in task success rate and generalization, particularly in fast-reaction and long-horizon scenarios.

Haowen Wang, Zhipeng Fan, Zhen Zhao et al.

Estimating 6D poses and reconstructing 3D shapes of objects in open-world scenes from RGB-depth image pairs is challenging. Many existing methods rely on learning geometric features that correspond to specific templates while disregarding shape variations and pose differences among objects in the same category. As a result, these methods underperform when handling unseen object instances in complex environments. In contrast, other approaches aim to achieve category-level estimation and reconstruction by leveraging normalized geometric structure priors, but the static prior-based reconstruction struggles with substantial intra-class variations. To solve these problems, we propose the DTF-Net, a novel framework for pose estimation and shape reconstruction based on implicit neural fields of object categories. In DTF-Net, we design a deformable template field to represent the general category-wise shape latent features and intra-category geometric deformation features. The field establishes continuous shape correspondences, deforming the category template into arbitrary observed instances to accomplish shape reconstruction. We introduce a pose regression module that shares the deformation features and template codes from the fields to estimate the accurate 6D pose of each object in the scene. We integrate a multi-modal representation extraction module to extract object features and semantic masks, enabling end-to-end inference. Moreover, during training, we implement a shape-invariant training strategy and a viewpoint sampling method to further enhance the model's capability to extract object pose features. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superiority of DTF-Net in both synthetic and real scenes. Furthermore, we show that DTF-Net effectively supports grasping tasks with a real robot arm.

Mingze Wei, Yaomin Huang, Zhiyuan Xu et al.

In this paper, we propose a novel representation for grasping using contacts between multi-finger robotic hands and objects to be manipulated. This representation significantly reduces the prediction dimensions and accelerates the learning process. We present an effective end-to-end network, CMG-Net, for grasping unknown objects in a cluttered environment by efficiently predicting multi-finger grasp poses and hand configurations from a single-shot point cloud. Moreover, we create a synthetic grasp dataset that consists of five thousand cluttered scenes, 80 object categories, and 20 million annotations. We perform a comprehensive empirical study and demonstrate the effectiveness of our grasping representation and CMG-Net. Our work significantly outperforms the state-of-the-art for three-finger robotic hands. We also demonstrate that the model trained using synthetic data performs very well for real robots.

Yixue Zhang, Kun Wu, Zhi Gao et al.

The pursuit of general-purpose robotic manipulation is hindered by the scarcity of diverse, real-world interaction data. Unlike data collection from web in vision or language, robotic data collection is an active process incurring prohibitive physical costs. Consequently, automated task curation to maximize data value remains a critical yet under-explored challenge. Existing manual methods are unscalable and biased toward common tasks, while off-the-shelf foundation models often hallucinate physically infeasible instructions. To address this, we introduce RoboGene, an agentic framework designed to automate the generation of diverse, physically plausible manipulation tasks across single-arm, dual-arm, and mobile robots. RoboGene integrates three core components: diversity-driven sampling for broad task coverage, self-reflection mechanisms to enforce physical constraints, and human-in-the-loop refinement for continuous improvement. We conduct extensive quantitative analysis and large-scale real-world experiments, collecting datasets of 18k trajectories and introducing novel metrics to assess task quality, feasibility, and diversity. Results demonstrate that RoboGene significantly outperforms state-of-the-art foundation models (e.g., GPT-4o, Gemini 2.5 Pro). Furthermore, real-world experiments show that VLA models pre-trained with RoboGene achieve higher success rates and superior generalization, underscoring the importance of high-quality task generation. Our project is available at https://robogene-boost-vla.github.io.

Jingyang He, Guangrun Li, Jieyu Zhang et al.

Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations come from humans or robots with different morphology, kinematics, or action spaces, this action-centric view requires shared action spaces, heuristic retargeting, or large-scale multi-embodiment co-training. We instead view demonstrations as implicit specifications of future goals: the target agent should infer what state the demonstrator is trying to realize, rather than how the demonstrator executes it. We propose Demo-JEPA, a cross-embodiment imitation framework that decouples demonstration intent from embodiment-specific execution. Built on a JEPA-based world model, Demo-JEPA translates source visual demonstrations into target-compatible future latent trajectories in a shared predictive representation space. The target agent then uses these latent trajectories as subgoals and realizes them through planning under its own learned forward dynamics. Because Demo-JEPA avoids action-level correspondence and requires only visual demonstrations plus the target agent's own interaction experience, it supports flexible imitation across heterogeneous embodiments. Experiments on RLBench and real-world manipulation tasks show that Demo-JEPA matches specialized in-domain planners and generalizes to unseen tasks and embodiment configurations where prior methods fail.

Kun Wu, Chengkai Hou, Jiaming Liu et al.

In this paper, we introduce RoboMIND (Multi-embodiment Intelligence Normative Data for Robot Manipulation), a dataset containing 107k demonstration trajectories across 479 diverse tasks involving 96 object classes. RoboMIND is collected through human teleoperation and encompasses comprehensive robotic-related information, including multi-view observations, proprioceptive robot state information, and linguistic task descriptions. To ensure data consistency and reliability for imitation learning, RoboMIND is built on a unified data collection platform and a standardized protocol, covering four distinct robotic embodiments: the Franka Emika Panda, the UR5e, the AgileX dual-arm robot, and a humanoid robot with dual dexterous hands. Our dataset also includes 5k real-world failure demonstrations, each accompanied by detailed causes, enabling failure reflection and correction during policy learning. Additionally, we created a digital twin environment in the Isaac Sim simulator, replicating the real-world tasks and assets, which facilitates the low-cost collection of additional training data and enables efficient evaluation. To demonstrate the quality and diversity of our dataset, we conducted extensive experiments using various imitation learning methods for single-task settings and state-of-the-art Vision-Language-Action (VLA) models for multi-task scenarios. By leveraging RoboMIND, the VLA models achieved high manipulation success rates and demonstrated strong generalization capabilities. To the best of our knowledge, RoboMIND is the largest multi-embodiment teleoperation dataset collected on a unified platform, providing large-scale and high-quality robotic training data. Our project is at https://x-humanoid-robomind.github.io/.

Zhiyuan Xu, Kun Wu, Junjie Wen et al.

While the exploration for embodied AI has spanned multiple decades, it remains a persistent challenge to endow agents with human-level intelligence, including perception, learning, reasoning, decision-making, control, and generalization capabilities, so that they can perform general-purpose tasks in open, unstructured, and dynamic environments. Recent advances in computer vision, natural language processing, and multi-modality learning have shown that the foundation models have superhuman capabilities for specific tasks. They not only provide a solid cornerstone for integrating basic modules into embodied AI systems but also shed light on how to scale up robot learning from a methodological perspective. This survey aims to provide a comprehensive and up-to-date overview of foundation models in robotics, focusing on autonomous manipulation and encompassing high-level planning and low-level control. Moreover, we showcase their commonly used datasets, simulators, and benchmarks. Importantly, we emphasize the critical challenges intrinsic to this field and delineate potential avenues for future research, contributing to advancing the frontier of academic and industrial discourse.

Minjie Zhu, Yichen Zhu, Jinming Li et al.

The language-conditioned robotic manipulation aims to transfer natural language instructions into executable actions, from simple pick-and-place to tasks requiring intent recognition and visual reasoning. Inspired by the dual process theory in cognitive science, which suggests two parallel systems of fast and slow thinking in human decision-making, we introduce Robotics with Fast and Slow Thinking (RFST), a framework that mimics human cognitive architecture to classify tasks and makes decisions on two systems based on instruction types. Our RFST consists of two key components: 1) an instruction discriminator to determine which system should be activated based on the current user instruction, and 2) a slow-thinking system that is comprised of a fine-tuned vision language model aligned with the policy networks, which allows the robot to recognize user intention or perform reasoning tasks. To assess our methodology, we built a dataset featuring real-world trajectories, capturing actions ranging from spontaneous impulses to tasks requiring deliberate contemplation. Our results, both in simulation and real-world scenarios, confirm that our approach adeptly manages intricate tasks that demand intent recognition and reasoning. The project is available at https://jlm-z.github.io/RSFT/

Junjie Wen, Yichen Zhu, Minjie Zhu et al.

Humans interpret scenes by recognizing both the identities and positions of objects in their observations. For a robot to perform tasks such as \enquote{pick and place}, understanding both what the objects are and where they are located is crucial. While the former has been extensively discussed in the literature that uses the large language model to enrich the text descriptions, the latter remains underexplored. In this work, we introduce the \textit{Object-Centric Instruction Augmentation (OCI)} framework to augment highly semantic and information-dense language instruction with position cues. We utilize a Multi-modal Large Language Model (MLLM) to weave knowledge of object locations into natural language instruction, thus aiding the policy network in mastering actions for versatile manipulation. Additionally, we present a feature reuse mechanism to integrate the vision-language features from off-the-shelf pre-trained MLLM into policy networks. Through a series of simulated and real-world robotic tasks, we demonstrate that robotic manipulator imitation policies trained with our enhanced instructions outperform those relying solely on traditional language instructions.

Dong Chen, Ning Liu, Yichen Zhu et al.

Neural network compression techniques, such as knowledge distillation (KD) and network pruning, have received increasing attention. Recent work `Prune, then Distill' reveals that a pruned student-friendly teacher network can benefit the performance of KD. However, the conventional teacher-student pipeline, which entails cumbersome pre-training of the teacher and complicated compression steps, makes pruning with KD less efficient. In addition to compressing models, recent compression techniques also emphasize the aspect of efficiency. Early pruning demands significantly less computational cost in comparison to the conventional pruning methods as it does not require a large pre-trained model. Likewise, a special case of KD, known as self-distillation (SD), is more efficient since it requires no pre-training or student-teacher pair selection. This inspires us to collaborate early pruning with SD for efficient model compression. In this work, we propose the framework named Early Pruning with Self-Distillation (EPSD), which identifies and preserves distillable weights in early pruning for a given SD task. EPSD efficiently combines early pruning and self-distillation in a two-step process, maintaining the pruned network's trainability for compression. Instead of a simple combination of pruning and SD, EPSD enables the pruned network to favor SD by keeping more distillable weights before training to ensure better distillation of the pruned network. We demonstrated that EPSD improves the training of pruned networks, supported by visual and quantitative analyses. Our evaluation covered diverse benchmarks (CIFAR-10/100, Tiny-ImageNet, full ImageNet, CUB-200-2011, and Pascal VOC), with EPSD outperforming advanced pruning and SD techniques.

Kun Wu, Yinuo Zhao, Zhiyuan Xu et al.

Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods typically learn a conservative policy to mitigate the problem of Q-value overestimation, but it is prone to overdo it, leading to an overly conservative policy. Moreover, they optimize all samples equally with fixed constraints, lacking the nuanced ability to control conservative levels in a fine-grained manner. Consequently, this limitation results in a performance decline. To address the above two challenges in a united way, we propose a framework, Adaptive Conservative Level in Q-Learning (ACL-QL), which limits the Q-values in a mild range and enables adaptive control on the conservative level over each state-action pair, i.e., lifting the Q-values more for good transitions and less for bad transitions. We theoretically analyze the conditions under which the conservative level of the learned Q-function can be limited in a mild range and how to optimize each transition adaptively. Motivated by the theoretical analysis, we propose a novel algorithm, ACL-QL, which uses two learnable adaptive weight functions to control the conservative level over each transition. Subsequently, we design a monotonicity loss and surrogate losses to train the adaptive weight functions, Q-function, and policy network alternatively. We evaluate ACL-QL on the commonly used D4RL benchmark and conduct extensive ablation studies to illustrate the effectiveness and state-of-the-art performance compared to existing offline DRL baselines.

Haowen Wang, Zhen Zhao, Zhao Jin et al.

Reconstructing real-world objects and estimating their movable joint structures are pivotal technologies within the field of robotics. Previous research has predominantly focused on supervised approaches, relying on extensively annotated datasets to model articulated objects within limited categories. However, this approach falls short of effectively addressing the diversity present in the real world. To tackle this issue, we propose a self-supervised interaction perception method, referred to as SM$^3$, which leverages multi-view RGB images captured before and after interaction to model articulated objects, identify the movable parts, and infer the parameters of their rotating joints. By constructing 3D geometries and textures from the captured 2D images, SM$^3$ achieves integrated optimization of movable part and joint parameters during the reconstruction process, obviating the need for annotations. Furthermore, we introduce the MMArt dataset, an extension of PartNet-Mobility, encompassing multi-view and multi-modal data of articulated objects spanning diverse categories. Evaluations demonstrate that SM$^3$ surpasses existing benchmarks across various categories and objects, while its adaptability in real-world scenarios has been thoroughly validated.

Haowen Wang, Xiaoping Yuan, Zhao Jin et al.

Articulated objects are ubiquitous in everyday life, and accurate 3D representations of their geometry and motion are critical for numerous applications. However, in the absence of human annotation, existing approaches still struggle to build a unified representation for objects that contain multiple movable parts. We introduce DeGSS, a unified framework that encodes articulated objects as deformable 3D Gaussian fields, embedding geometry, appearance, and motion in one compact representation. Each interaction state is modeled as a smooth deformation of a shared field, and the resulting deformation trajectories guide a progressive coarse-to-fine part segmentation that identifies distinct rigid components, all in an unsupervised manner. The refined field provides a spatially continuous, fully decoupled description of every part, supporting part-level reconstruction and precise modeling of their kinematic relationships. To evaluate generalization and realism, we enlarge the synthetic PartNet-Mobility benchmark and release RS-Art, a real-to-sim dataset that pairs RGB captures with accurately reverse-engineered 3D models. Extensive experiments demonstrate that our method outperforms existing methods in both accuracy and stability.

Yifei Su, Ning Liu, Dong Chen et al.

Generative modeling-based visuomotor policies have been widely adopted in robotic manipulation attributed to their ability to model multimodal action distributions. However, the high inference cost of multi-step sampling limits their applicability in real-time robotic systems. To address this issue, existing approaches accelerate the sampling process in generative modeling-based visuomotor policies by adapting acceleration techniques originally developed for image generation. Despite this progress, a major distinction remains: image generation typically involves producing independent samples without temporal dependencies, whereas robotic manipulation involves generating time-series action trajectories that require continuity and temporal coherence. To effectively exploit temporal information in robotic manipulation, we propose FreqPolicy, a novel approach that first imposes frequency consistency constraints on flow-based visuomotor policies. Our work enables the action model to capture temporal structure effectively while supporting efficient, high-quality one-step action generation. We introduce a frequency consistency constraint that enforces alignment of frequency-domain action features across different timesteps along the flow, thereby promoting convergence of one-step action generation toward the target distribution. In addition, we design an adaptive consistency loss to capture structural temporal variations inherent in robotic manipulation tasks. We assess FreqPolicy on 53 tasks across 3 simulation benchmarks, proving its superiority over existing one-step action generators. We further integrate FreqPolicy into the vision-language-action (VLA) model and achieve acceleration without performance degradation on the 40 tasks of Libero. Besides, we show efficiency and effectiveness in real-world robotic scenarios with an inference frequency 93.5Hz. The code will be publicly available.

Zhang Zhang, Qiang Zhang, Wei Cui et al.

Understanding and forecasting the scene evolutions deeply affect the exploration and decision of embodied agents. While traditional methods simulate scene evolutions through trajectory prediction of potential instances, current works use the occupancy world model as a generative framework for describing fine-grained overall scene dynamics. However, existing methods cluster on the outdoor structured road scenes, while ignoring the exploration of forecasting 3D occupancy scene evolutions for robots in indoor scenes. In this work, we explore a new framework for learning the scene evolutions of observed fine-grained occupancy and propose an occupancy world model based on the combined spatio-temporal receptive field and guided autoregressive transformer to forecast the scene evolutions, called RoboOccWorld. We propose the Conditional Causal State Attention (CCSA), which utilizes camera poses of next state as conditions to guide the autoregressive transformer to adapt and understand the indoor robotics scenarios. In order to effectively exploit the spatio-temporal cues from historical observations, Hybrid Spatio-Temporal Aggregation (HSTA) is proposed to obtain the combined spatio-temporal receptive field based on multi-scale spatio-temporal windows. In addition, we restructure the OccWorld-ScanNet benchmark based on local annotations to facilitate the evaluation of the indoor 3D occupancy scene evolution prediction task. Experimental results demonstrate that our RoboOccWorld outperforms state-of-the-art methods in indoor 3D occupancy scene evolution prediction task. The code will be released soon.

Yinuo Zhao, Kun Wu, Tianjiao Yi et al.

Improving generalization is one key challenge in embodied AI, where obtaining large-scale datasets across diverse scenarios is costly. Traditional weak augmentations, such as cropping and flipping, are insufficient for improving a model's performance in new environments. Existing data augmentation methods often disrupt task-relevant information in images, potentially degrading performance. To overcome these challenges, we introduce EAGLE, an efficient training framework for generalizable visuomotor policies that improves upon existing methods by (1) enhancing generalization by applying augmentation only to control-related regions identified through a self-supervised control-aware mask and (2) improving training stability and efficiency by distilling knowledge from an expert to a visuomotor student policy, which is then deployed to unseen environments without further fine-tuning. Comprehensive experiments on three domains, including the DMControl Generalization Benchmark, the enhanced Robot Manipulation Distraction Benchmark, and a long-sequential drawer-opening task, validate the effectiveness of our method.

Leo Chen, Benjamin Boardley, Ping Hu et al.

This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC). Since 2015, LPCVC has been an international competition devoted to tackling the challenge of computer vision (CV) on edge devices. Most CV researchers focus on improving accuracy, at the expense of ever-growing sizes of machine models. LPCVC balances accuracy with resource requirements. Winners must achieve high accuracy with short execution time when their CV solutions run on an embedded device, such as Raspberry PI or Nvidia Jetson Nano. The vision problem for 2023 LPCVC is segmentation of images acquired by Unmanned Aerial Vehicles (UAVs, also called drones) after disasters. The 2023 LPCVC attracted 60 international teams that submitted 676 solutions during the submission window of one month. This article explains the setup of the competition and highlights the winners' methods that improve accuracy and shorten execution time.

Kun Wu, Ning Liu, Zhen Zhao et al.

Improving data utilization, especially for imperfect data from task failures, is crucial for robotic manipulation due to the challenging, time-consuming, and expensive data collection process in the real world. Current imitation learning (IL) typically discards imperfect data, focusing solely on successful expert data. While reinforcement learning (RL) can learn from explorations and failures, the sim2real gap and its reliance on dense reward and online exploration make it difficult to apply effectively in real-world scenarios. In this work, we aim to conquer the challenge of leveraging imperfect data without the need for reward information to improve the model performance for robotic manipulation in an offline manner. Specifically, we introduce a Self-Supervised Data Filtering framework (SSDF) that combines expert and imperfect data to compute quality scores for failed trajectory segments. High-quality segments from the failed data are used to expand the training dataset. Then, the enhanced dataset can be used with any downstream policy learning method for robotic manipulation tasks. Extensive experiments on the ManiSkill2 benchmark built on the high-fidelity Sapien simulator and real-world robotic manipulation tasks using the Franka robot arm demonstrated that the SSDF can accurately expand the training dataset with high-quality imperfect data and improve the success rates for all robotic manipulation tasks.

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.

Zhiyuan Xu, Yinuo Zhao, Kun Wu et al.

Teleoperation is essential for autonomous robot learning, especially in manipulation tasks that require human demonstrations or corrections. However, most existing systems only offer unilateral robot control and lack the ability to synchronize the robot's status with the teleoperation hardware, preventing real-time, flexible intervention. In this work, we introduce HACTS (Human-As-Copilot Teleoperation System), a novel system that establishes bilateral, real-time joint synchronization between a robot arm and teleoperation hardware. This simple yet effective feedback mechanism, akin to a steering wheel in autonomous vehicles, enables the human copilot to intervene seamlessly while collecting action-correction data for future learning. Implemented using 3D-printed components and low-cost, off-the-shelf motors, HACTS is both accessible and scalable. Our experiments show that HACTS significantly enhances performance in imitation learning (IL) and reinforcement learning (RL) tasks, boosting IL recovery capabilities and data efficiency, and facilitating human-in-the-loop RL. HACTS paves the way for more effective and interactive human-robot collaboration and data-collection, advancing the capabilities of robot manipulation.

Chengxiang Yin, Zhengping Che, Kun Wu et al.

Visual Question Answering (VQA) has emerged as one of the most challenging tasks in artificial intelligence due to its multi-modal nature. However, most existing VQA methods are incapable of handling Knowledge-based Visual Question Answering (KB-VQA), which requires external knowledge beyond visible contents to answer questions about a given image. To address this issue, we propose a novel framework that endows the model with capabilities of answering more general questions, and achieves a better exploitation of external knowledge through generating Multiple Clues for Reasoning with Memory Neural Networks (MCR-MemNN). Specifically, a well-defined detector is adopted to predict image-question related relation phrases, each of which delivers two complementary clues to retrieve the supporting facts from external knowledge base (KB), which are further encoded into a continuous embedding space using a content-addressable memory. Afterwards, mutual interactions between visual-semantic representation and the supporting facts stored in memory are captured to distill the most relevant information in three modalities (i.e., image, question, and KB). Finally, the optimal answer is predicted by choosing the supporting fact with the highest score. We conduct extensive experiments on two widely-used benchmarks. The experimental results well justify the effectiveness of MCR-MemNN, as well as its superiority over other KB-VQA methods.

Chengxiang Yin, Zhengping Che, Kun Wu et al.

Video Question Answering (VideoQA) is a very attractive and challenging research direction aiming to understand complex semantics of heterogeneous data from two domains, i.e., the spatio-temporal video content and the word sequence in question. Although various attention mechanisms have been utilized to manage contextualized representations by modeling intra- and inter-modal relationships of the two modalities, one limitation of the predominant VideoQA methods is the lack of reasoning with event correlation, that is, sensing and analyzing relationships among abundant and informative events contained in the video. In this paper, we introduce the dense caption modality as a new auxiliary and distill event-correlated information from it to infer the correct answer. To this end, we propose a novel end-to-end trainable model, Event-Correlated Graph Neural Networks (EC-GNNs), to perform cross-modal reasoning over information from the three modalities (i.e., caption, video, and question). Besides the exploitation of a brand new modality, we employ cross-modal reasoning modules for explicitly modeling inter-modal relationships and aggregating relevant information across different modalities, and we propose a question-guided self-adaptive multi-modal fusion module to collect the question-oriented and event-correlated evidence through multi-step reasoning. We evaluate our model on two widely-used benchmark datasets and conduct an ablation study to justify the effectiveness of each proposed component.

Yinuo Zhao, Kun Wu, Zhiyuan Xu et al.

Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors. Widely-applied methods either heavily rely on hand-crafted rules or learn from limited human experience, which makes them hard to generalize to rare but critical scenarios. In this paper, we present a novel CAscade Deep REinforcement learning framework, CADRE, to achieve model-free vision-based autonomous urban driving. In CADRE, to derive representative latent features from raw observations, we first offline train a Co-attention Perception Module (CoPM) that leverages the co-attention mechanism to learn the inter-relationships between the visual and control information from a pre-collected driving dataset. Cascaded by the frozen CoPM, we then present an efficient distributed proximal policy optimization framework to online learn the driving policy under the guidance of particularly designed reward functions. We perform a comprehensive empirical study with the CARLA NoCrash benchmark as well as specific obstacle avoidance scenarios in autonomous urban driving tasks. The experimental results well justify the effectiveness of CADRE and its superiority over the state-of-the-art by a wide margin.

Wenzheng Hu, Zhengping Che, Ning Liu et al.

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks. However, most existing pruning approaches are driven by empirical heuristic and rarely consider the joint impact of channels, leading to unguaranteed and suboptimal performance. In this paper, we propose a novel channel pruning method via Class-Aware Trace Ratio Optimization (CATRO) to reduce the computational burden and accelerate the model inference. Utilizing class information from a few samples, CATRO measures the joint impact of multiple channels by feature space discriminations and consolidates the layer-wise impact of preserved channels. By formulating channel pruning as a submodular set function maximization problem, CATRO solves it efficiently via a two-stage greedy iterative optimization procedure. More importantly, we present theoretical justifications on convergence of CATRO and performance of pruned networks. Experimental results demonstrate that CATRO achieves higher accuracy with similar computation cost or lower computation cost with similar accuracy than other state-of-the-art channel pruning algorithms. In addition, because of its class-aware property, CATRO is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.

Kun Wu, Chengxiang Yin, Zhengping Che et al.

Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others. Though many different methods have been proposed to generate images with high visual fidelity, the main challenge remains and comes from two fundamental issues: pose ambiguity and appearance inconsistency. To alleviate the current limitations and improve the quality of the synthesized images, we propose a pose transfer network with augmented Disentangled Feature Consistency (DFC-Net) to facilitate human pose transfer. Given a pair of images containing the source and target person, DFC-Net extracts pose and static information from the source and target respectively, then synthesizes an image of the target person with the desired pose from the source. Moreover, DFC-Net leverages disentangled feature consistency losses in the adversarial training to strengthen the transfer coherence and integrates a keypoint amplifier to enhance the pose feature extraction. With the help of the disentangled feature consistency losses, we further propose a novel data augmentation scheme that introduces unpaired support data with the augmented consistency constraints to improve the generality and robustness of DFC-Net. Extensive experimental results on Mixamo-Pose and EDN-10k have demonstrated DFC-Net achieves state-of-the-art performance on pose transfer.

Ning Liu, Geng Yuan, Zhengping Che et al.

In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i.e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance than the original dense network. However, it is not easy to observe such winning property in many scenarios, where for example, a relatively large learning rate is used even if it benefits training the original dense model. In this work, we investigate the underlying condition and rationale behind the winning property, and find that the underlying reason is largely attributed to the correlation between initialized weights and final-trained weights when the learning rate is not sufficiently large. Thus, the existence of winning property is correlated with an insufficient DNN pretraining, and is unlikely to occur for a well-trained DNN. To overcome this limitation, we propose the "pruning & fine-tuning" method that consistently outperforms lottery ticket sparse training under the same pruning algorithm and the same total training epochs. Extensive experiments over multiple deep models (VGG, ResNet, MobileNet-v2) on different datasets have been conducted to justify our proposals.

Yue Shi, Bo Jiang, Zhengping Che et al.

Scale variance is one of the crucial challenges in multi-scale object detection. Early approaches address this problem by exploiting the image and feature pyramid, which raises suboptimal results with computation burden and constrains from inherent network structures. Pioneering works also propose multi-scale (i.e., multi-level and multi-branch) feature fusions to remedy the issue and have achieved encouraging progress. However, existing fusions still have certain limitations such as feature scale inconsistency, ignorance of level-wise semantic transformation, and coarse granularity. In this work, we present a novel module, the Fluff block, to alleviate drawbacks of current multi-scale fusion methods and facilitate multi-scale object detection. Specifically, Fluff leverages both multi-level and multi-branch schemes with dilated convolutions to have rapid, effective and finer-grained feature fusions. Furthermore, we integrate Fluff to SSD as FluffNet, a powerful real-time single-stage detector for multi-scale object detection. Empirical results on MS COCO and PASCAL VOC have demonstrated that FluffNet obtains remarkable efficiency with state-of-the-art accuracy. Additionally, we indicate the great generality of the Fluff block by showing how to embed it to other widely-used detectors as well.

Xuanzhao Wang, Zhengping Che, Bo Jiang et al.

Video anomaly detection is commonly used in many applications such as security surveillance and is very challenging.A majority of recent video anomaly detection approaches utilize deep reconstruction models, but their performance is often suboptimal because of insufficient reconstruction error differences between normal and abnormal video frames in practice. Meanwhile, frame prediction-based anomaly detection methods have shown promising performance. In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos. The proposed method is equipped with a multi-path ConvGRU-based frame prediction network that can better handle semantically informative objects and areas of different scales and capture spatial-temporal dependencies in normal videos. A noise tolerance loss is introduced during training to mitigate the interference caused by background noise. Extensive experiments have been conducted on the CUHK Avenue, ShanghaiTech Campus, and UCSD Pedestrian datasets, and the results show that our proposed method outperforms existing state-of-the-art approaches. Remarkably, our proposed method obtains the frame-level AUROC score of 88.3% on the CUHK Avenue dataset.

Yushuo Guan, Ning Liu, Pengyu Zhao et al.

The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure, such that the pruned network can be easily deployed in practice. However, existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space. In this paper, we introduce Differentiable Annealing Indicator Search (DAIS) that leverages the strength of neural architecture search in the channel pruning and automatically searches for the effective pruned model with given constraints on computation overhead. Specifically, DAIS relaxes the binarized channel indicators to be continuous and then jointly learns both indicators and model parameters via bi-level optimization. To bridge the non-negligible discrepancy between the continuous model and the target binarized model, DAIS proposes an annealing-based procedure to steer the indicator convergence towards binarized states. Moreover, DAIS designs various regularizations based on a priori structural knowledge to control the pruning sparsity and to improve model performance. Experimental results show that DAIS outperforms state-of-the-art pruning methods on CIFAR-10, CIFAR-100, and ImageNet.

Zhiyuan Xu, Kun Wu, Zhengping Che et al.

While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks. In this paper, we present a Knowledge Transfer based Multi-task Deep Reinforcement Learning framework (KTM-DRL) for continuous control, which enables a single DRL agent to achieve expert-level performance in multiple different tasks by learning from task-specific teachers. In KTM-DRL, the multi-task agent first leverages an offline knowledge transfer algorithm designed particularly for the actor-critic architecture to quickly learn a control policy from the experience of task-specific teachers, and then it employs an online learning algorithm to further improve itself by learning from new online transition samples under the guidance of those teachers. We perform a comprehensive empirical study with two commonly-used benchmarks in the MuJoCo continuous control task suite. The experimental results well justify the effectiveness of KTM-DRL and its knowledge transfer and online learning algorithms, as well as its superiority over the state-of-the-art by a large margin.

Zhengping Che, Guangyu Li, Tracy Li et al.

Driving datasets accelerate the development of intelligent driving and related computer vision technologies, while substantial and detailed annotations serve as fuels and powers to boost the efficacy of such datasets to improve learning-based models. We propose D$^2$-City, a large-scale comprehensive collection of dashcam videos collected by vehicles on DiDi's platform. D$^2$-City contains more than 10000 video clips which deeply reflect the diversity and complexity of real-world traffic scenarios in China. We also provide bounding boxes and tracking annotations of 12 classes of objects in all frames of 1000 videos and detection annotations on keyframes for the remainder of the videos. Compared with existing datasets, D$^2$-City features data in varying weather, road, and traffic conditions and a huge amount of elaborate detection and tracking annotations. By bringing a diverse set of challenging cases to the community, we expect the D$^2$-City dataset will advance the perception and related areas of intelligent driving.

Sanjay Purushotham, Chuizheng Meng, Zhengping Che et al.

Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications. However, few works exist which have benchmarked the performance of the deep learning models with respect to the state-of-the-art machine learning models and prognostic scoring systems on publicly available healthcare datasets. In this paper, we present the benchmarking results for several clinical prediction tasks such as mortality prediction, length of stay prediction, and ICD-9 code group prediction using Deep Learning models, ensemble of machine learning models (Super Learner algorithm), SAPS II and SOFA scores. We used the Medical Information Mart for Intensive Care III (MIMIC-III) (v1.4) publicly available dataset, which includes all patients admitted to an ICU at the Beth Israel Deaconess Medical Center from 2001 to 2012, for the benchmarking tasks. Our results show that deep learning models consistently outperform all the other approaches especially when the `raw' clinical time series data is used as input features to the models.

Zhengping Che, Yu Cheng, Shuangfei Zhai et al.

The rapid growth of Electronic Health Records (EHRs), as well as the accompanied opportunities in Data-Driven Healthcare (DDH), has been attracting widespread interests and attentions. Recent progress in the design and applications of deep learning methods has shown promising results and is forcing massive changes in healthcare academia and industry, but most of these methods rely on massive labeled data. In this work, we propose a general deep learning framework which is able to boost risk prediction performance with limited EHR data. Our model takes a modified generative adversarial network namely ehrGAN, which can provide plausible labeled EHR data by mimicking real patient records, to augment the training dataset in a semi-supervised learning manner. We use this generative model together with a convolutional neural network (CNN) based prediction model to improve the onset prediction performance. Experiments on two real healthcare datasets demonstrate that our proposed framework produces realistic data samples and achieves significant improvements on classification tasks with the generated data over several stat-of-the-art baselines.

Zhengping Che, Yu Cheng, Zhaonan Sun et al.

The widespread availability of electronic health records (EHRs) promises to usher in the era of personalized medicine. However, the problem of extracting useful clinical representations from longitudinal EHR data remains challenging. In this paper, we explore deep neural network models with learned medical feature embedding to deal with the problems of high dimensionality and temporality. Specifically, we use a multi-layer convolutional neural network (CNN) to parameterize the model and is thus able to capture complex non-linear longitudinal evolution of EHRs. Our model can effectively capture local/short temporal dependency in EHRs, which is beneficial for risk prediction. To account for high dimensionality, we use the embedding medical features in the CNN model which hold the natural medical concepts. Our initial experiments produce promising results and demonstrate the effectiveness of both the medical feature embedding and the proposed convolutional neural network in risk prediction on cohorts of congestive heart failure and diabetes patients compared with several strong baselines.

Zhengping Che, Sanjay Purushotham, Kyunghyun Cho et al.

Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values. In time series prediction and other related tasks, it has been noted that missing values and their missing patterns are often correlated with the target labels, a.k.a., informative missingness. There is very limited work on exploiting the missing patterns for effective imputation and improving prediction performance. In this paper, we develop novel deep learning models, namely GRU-D, as one of the early attempts. GRU-D is based on Gated Recurrent Unit (GRU), a state-of-the-art recurrent neural network. It takes two representations of missing patterns, i.e., masking and time interval, and effectively incorporates them into a deep model architecture so that it not only captures the long-term temporal dependencies in time series, but also utilizes the missing patterns to achieve better prediction results. Experiments of time series classification tasks on real-world clinical datasets (MIMIC-III, PhysioNet) and synthetic datasets demonstrate that our models achieve state-of-the-art performance and provides useful insights for better understanding and utilization of missing values in time series analysis.

Zhengping Che, Sanjay Purushotham, Robinder Khemani et al.

Exponential growth in Electronic Healthcare Records (EHR) has resulted in new opportunities and urgent needs for discovery of meaningful data-driven representations and patterns of diseases in Computational Phenotyping research. Deep Learning models have shown superior performance for robust prediction in computational phenotyping tasks, but suffer from the issue of model interpretability which is crucial for clinicians involved in decision-making. In this paper, we introduce a novel knowledge-distillation approach called Interpretable Mimic Learning, to learn interpretable phenotype features for making robust prediction while mimicking the performance of deep learning models. Our framework uses Gradient Boosting Trees to learn interpretable features from deep learning models such as Stacked Denoising Autoencoder and Long Short-Term Memory. Exhaustive experiments on a real-world clinical time-series dataset show that our method obtains similar or better performance than the deep learning models, and it provides interpretable phenotypes for clinical decision making.