arXiv subjects

Zhao Jin

Publications and source records attributed to Zhao Jin.

35 records · Page 2Linked to original sources

arXiv2025

RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation

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/.

cs.RO↗

arXiv2025

MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval

Existing Zero-Shot Composed Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens, which are concatenated with the modifying text and processed by frozen text encoders in pretrained VLMs or LLMs. While this design leverages the strengths of large pretrained models, it only supervises the adapter to produce encoder-compatible tokens that loosely preserve visual semantics. Crucially, it does not directly optimize the composed query representation to capture the full intent of the composition or to align with the target semantics, thereby limiting retrieval performance, particularly in cases involving fine-grained or complex visual transformations. To address this problem, we propose MLLM-Guided VLM Fine-Tuning with Joint Inference (MVFT-JI), a novel approach that leverages a pretrained multimodal large language model (MLLM) to construct two complementary training tasks using only unlabeled images: target text retrieval taskand text-to-image retrieval task. By jointly optimizing these tasks, our method enables the VLM to inherently acquire robust compositional retrieval capabilities, supported by the provided theoretical justifications and empirical validation. Furthermore, during inference, we further prompt the MLLM to generate target texts from composed queries and compute retrieval scores by integrating similarities between (i) the composed query and candidate images, and (ii) the MLLM-generated target text and candidate images. This strategy effectively combines the VLM's semantic alignment strengths with the MLLM's reasoning capabilities.

cs.CV↗

arXiv2025

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration

Diffusion Transformers (DiTs) have proven effective in generating high-quality videos but are hindered by high computational costs. Existing video DiT sampling acceleration methods often rely on costly fine-tuning or exhibit limited generalization capabilities. We propose Asymmetric Reduction and Restoration (AsymRnR), a training-free and model-agnostic method to accelerate video DiTs. It builds on the observation that redundancies of feature tokens in DiTs vary significantly across different model blocks, denoising steps, and feature types. Our AsymRnR asymmetrically reduces redundant tokens in the attention operation, achieving acceleration with negligible degradation in output quality and, in some cases, even improving it. We also tailored a reduction schedule to distribute the reduction across components adaptively. To further accelerate this process, we introduce a matching cache for more efficient reduction. Backed by theoretical foundations and extensive experimental validation, AsymRnR integrates into state-of-the-art video DiTs and offers substantial speedup.

cs.CV↗

arXiv2025

Where is this coming from? Making groundedness count in the evaluation of Document VQA models

Document Visual Question Answering (VQA) models have evolved at an impressive rate over the past few years, coming close to or matching human performance on some benchmarks. We argue that common evaluation metrics used by popular benchmarks do not account for the semantic and multimodal groundedness of a model's outputs. As a result, hallucinations and major semantic errors are treated the same way as well-grounded outputs, and the evaluation scores do not reflect the reasoning capabilities of the model. In response, we propose a new evaluation methodology that accounts for the groundedness of predictions with regard to the semantic characteristics of the output as well as the multimodal placement of the output within the input document. Our proposed methodology is parameterized in such a way that users can configure the score according to their preferences. We validate our scoring methodology using human judgment and show its potential impact on existing popular leaderboards. Through extensive analyses, we demonstrate that our proposed method produces scores that are a better indicator of a model's robustness and tends to give higher rewards to better-calibrated answers.

cs.CL↗

arXiv2025

Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration

Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design. We propose correctness learning (CL) to enhance human-AI collaboration integrating deductive verification methods and insights from historical high-quality schemes. The typical pattern hidden in historical high-quality schemes, such as change of task priorities in shared resources, provides critical guidance for intelligent agents in learning and decision-making. By utilizing deductive verification methods, we proposed patten-driven correctness learning (PDCL), formally modeling and reasoning the adaptive behaviors-or 'correctness pattern'-of system agents based on historical high-quality schemes, capturing the logical relationships embedded within these schemes. Using this logical information as guidance, we establish a correctness judgment and feedback mechanism to steer the intelligent decision model toward the 'correctness pattern' reflected in historical high-quality schemes. Extensive experiments across multiple working conditions and core parameters validate the framework's components and demonstrate its effectiveness in improving decision-making and resource optimization.

cs.AI↗

arXiv2024

SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing

While open-source video generation and editing models have made significant progress, individual models are typically limited to specific tasks, failing to meet the diverse needs of users. Effectively coordinating these models can unlock a wide range of video generation and editing capabilities. However, manual coordination is complex and time-consuming, requiring users to deeply understand task requirements and possess comprehensive knowledge of each model's performance, applicability, and limitations, thereby increasing the barrier to entry. To address these challenges, we propose a novel video generation and editing system powered by our Semantic Planning Agent (SPAgent). SPAgent bridges the gap between diverse user intents and the effective utilization of existing generative models, enhancing the adaptability, efficiency, and overall quality of video generation and editing. Specifically, the SPAgent assembles a tool library integrating state-of-the-art open-source image and video generation and editing models as tools. After fine-tuning on our manually annotated dataset, SPAgent can automatically coordinate the tools for video generation and editing, through our novelly designed three-step framework: (1) decoupled intent recognition, (2) principle-guided route planning, and (3) capability-based execution model selection. Additionally, we enhance the SPAgent's video quality evaluation capability, enabling it to autonomously assess and incorporate new video generation and editing models into its tool library without human intervention. Experimental results demonstrate that the SPAgent effectively coordinates models to generate or edit videos, highlighting its versatility and adaptability across various video tasks.

cs.CV↗

arXiv2024

SM$^3$: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects

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.

cs.CV↗

arXiv2023

ESimCSE Unsupervised Contrastive Learning Jointly with UDA Semi-Supervised Learning for Large Label System Text Classification Mode

The challenges faced by text classification with large tag systems in natural language processing tasks include multiple tag systems, uneven data distribution, and high noise. To address these problems, the ESimCSE unsupervised comparative learning and UDA semi-supervised comparative learning models are combined through the use of joint training techniques in the models.The ESimCSE model efficiently learns text vector representations using unlabeled data to achieve better classification results, while UDA is trained using unlabeled data through semi-supervised learning methods to improve the prediction performance of the models and stability, and further improve the generalization ability of the model. In addition, adversarial training techniques FGM and PGD are used in the model training process to improve the robustness and reliability of the model. The experimental results show that there is an 8% and 10% accuracy improvement relative to Baseline on the public dataset Ruesters as well as on the operational dataset, respectively, and a 15% improvement in manual validation accuracy can be achieved on the operational dataset, indicating that the method is effective.

cs.LG↗

arXiv2023

A separation logic for sequences in pointer programs and its decidability

Separation logic and its variants can describe various properties on pointer programs. However, when it comes to properties on sequences, one may find it hard to formalize. To deal with properties on variable-length sequences and multilevel data structures, we propose sequence-heap separation logic which integrates sequences into logical reasoning on heap-manipulated programs. Quantifiers over sequence variables and singleton heap storing sequence (sequence singleton heap) are new members in our logic. Further, we study the satisfiability problem of two fragments. The propositional fragment of sequence-heap separation logic is decidable, and the fragment with 2 alternations on program variables and 1 alternation on sequence variables is undecidable. In addition, we explore boundaries between decidable and undecidable fragments of the logic with prenex normal form.

cs.LO↗

arXiv2022

Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real scenes. However, large disparities between existing synthetic datasets and real scenes lead to poor model transfer. We make two major contributions to address that. First, we develop a point cloud collector and scene flow annotator for GTA-V engine to automatically obtain diverse realistic training samples without human intervention. With that, we develop a large-scale synthetic scene flow dataset GTA-SF. Second, we propose a mean-teacher-based domain adaptation framework that leverages self-generated pseudo-labels of the target domain. It also explicitly incorporates shape deformation regularization and surface correspondence refinement to address distortions and misalignments in domain transfer. Through extensive experiments, we show that our GTA-SF dataset leads to a consistent boost in model generalization to three real datasets (i.e., Waymo, Lyft and KITTI) as compared to the most widely used FT3D dataset. Moreover, our framework achieves superior adaptation performance on six source-target dataset pairs, remarkably closing the average domain gap by 60%. Data and codes are available at https://github.com/leolyj/DCA-SRSFE

cs.CV↗

arXiv2021

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

Physical measurements constitute a large portion of numbers in academic papers, engineering reports, and web tables. Current benchmarks fall short of properly evaluating numeracy of pretrained language models on measurements, hindering research on developing new methods and applying them to numerical tasks. To that end, we introduce a novel task, Masked Measurement Prediction (MMP), where a model learns to reconstruct a number together with its associated unit given masked text. MMP is useful for both training new numerically informed models as well as evaluating numeracy of existing systems. In order to address this task, we introduce a new Generative Masked Measurement (GeMM) model that jointly learns to predict numbers along with their units. We perform fine-grained analyses comparing our model with various ablations and baselines. We use linear probing of traditional pretrained transformer models (RoBERTa) to show that they significantly underperform jointly trained number-unit models, highlighting the difficulty of this new task and the benefits of our proposed pretraining approach. We hope this framework accelerates the progress towards building more robust numerical reasoning systems in the future.

cs.CL↗

arXiv2020

Mission-Aware Spatio-Temporal Deep Learning Model for UAS Instantaneous Density Prediction

The number of daily sUAS operations in uncontrolled low altitude airspace is expected to reach into the millions in a few years. Therefore, UAS density prediction has become an emerging and challenging problem. In this paper, a deep learning-based UAS instantaneous density prediction model is presented. The model takes two types of data as input: 1) the historical density generated from the historical data, and 2) the future sUAS mission information. The architecture of our model contains four components: Historical Density Formulation module, UAS Mission Translation module, Mission Feature Extraction module, and Density Map Projection module. The training and testing data are generated by a python based simulator which is inspired by the multi-agent air traffic resource usage simulator (MATRUS) framework. The quality of prediction is measured by the correlation score and the Area Under the Receiver Operating Characteristics (AUROC) between the predicted value and simulated value. The experimental results demonstrate outstanding performance of the deep learning-based UAS density predictor. Compared to the baseline models, for simplified traffic scenario where no-fly zones and safe distance among sUASs are not considered, our model improves the prediction accuracy by more than 15.2% and its correlation score reaches 0.947. In a more realistic scenario, where the no-fly zone avoidance and the safe distance among sUASs are maintained using A* routing algorithm, our model can still achieve 0.823 correlation score. Meanwhile, the AUROC can reach 0.951 for the hot spot prediction.

cs.CV↗

arXiv2020

GISNet: Graph-Based Information Sharing Network For Vehicle Trajectory Prediction

The trajectory prediction is a critical and challenging problem in the design of an autonomous driving system. Many AI-oriented companies, such as Google Waymo, Uber and DiDi, are investigating more accurate vehicle trajectory prediction algorithms. However, the prediction performance is governed by lots of entangled factors, such as the stochastic behaviors of surrounding vehicles, historical information of self-trajectory, and relative positions of neighbors, etc. In this paper, we propose a novel graph-based information sharing network (GISNet) that allows the information sharing between the target vehicle and its surrounding vehicles. Meanwhile, the model encodes the historical trajectory information of all the vehicles in the scene. Experiments are carried out on the public NGSIM US-101 and I-80 Dataset and the prediction performance is measured by the Root Mean Square Error (RMSE). The quantitative and qualitative experimental results show that our model significantly improves the trajectory prediction accuracy, by up to 50.00%, compared to existing models.

cs.RO↗

arXiv2020

Simulation of Real-time Routing for UAS traffic Management with Communication and Airspace Safety Considerations

Small Unmanned Aircraft Systems (sUAS) will be an important component of the smart city and intelligent transportation environments of the near future. The demand for sUAS related applications, such as commercial delivery and land surveying, is expected to grow rapidly in next few years. In general, sUAS traffic routing and management functions are needed to coordinate the launching of sUAS from different launch sites and determine their trajectories to avoid conflict while considering several other constraints such as expected arrival time, minimum flight energy, and availability of communication resources. However, as the airborne sUAS density grows in a certain area, it is difficult to foresee the potential airspace and communications resource conflicts and make immediate decisions to avoid them. To address this challenge, we present a temporal and spatial routing algorithm and simulation platform for sUAS trajectory management in a high density urban area that plans sUAS movements in a spatial and temporal maze taking into account obstacles that are either static or dynamic in time. The routing allows the sUAS to avoid static no-fly areas (i.e. static obstacles) or other in-flight sUAS and areas that have congested communication resources (i.e. dynamic obstacles). The algorithm is evaluated using an agent-based simulation platform. The simulation results show that the proposed algorithm outperforms other route management algorithms in many areas, especially in processing speed and memory efficiency. Detailed comparisons are provided for the sUAS flight time, the overall throughput, conflict rate and communication resource utilization. The results demonstrate that our proposed algorithm can be used to address the airspace and communication resource utilization needs for a next generation smart city and smart transportation.

cs.MA↗

arXiv2019

Reasoning about Block-based Cloud Storage Systems

Owing to the massive growth in the storage demands of big data, Cloud Storage Systems (CSSs) have been put forward to improve the storage capacity. Compared with traditional storage systems, CSSs have lots of advantages, such as higher capacity, lower cost, and easier scalability. But they are also with higher complexity. In order to ensure CSSs to be reliable, it is necessary to prove the correctness of CSSs management programs. In fact, we are going to verify Block-based Cloud Storage Systems (BCSSs), since BCSSs are the most popular CSSs. In this paper, the correctness of management programs in BCSSs have been proven, and a verification framework based on separation logic is proposed to finish the proven process. The main contributions are as follows. (1) A novel framework with two-tier heap structure is constructed to reflect the characteristics of BCSSs, and a modeling language is defined based on it. (2) Assertions based on separation logic is constructed to describe the properties of BCSSs. (3) The Hoare-style specifications are proposed to reason about the BCSSs. The results demonstrate that the correctness and reliability of BCSSs can be verified by the above proposed methods. Furthermore, the proposed specifications is sound in the application of reasoning about BCSSs.

cs.LO↗

arXiv2017

Temperature and Angular Dependence of the Upper Critical Field in K$_{2}$Cr$_{3}$As$_{3}$

We report measurements of the upper critical field $H_{\mathrm{c2}}$ as functions of temperature $T$, polar angle $θ$ (of the field direction with respect to the crystallographic $c$ axis), and azimuthal angle $ϕ$ (of the field direction relative to the $a$ axis within the $ab$ plane) for the Cr-based superconductor K$_{2}$Cr$_{3}$As$_{3}$ with a quasi-one-dimensional and non-centrosymmetric crystal structure. We confirm that the anisotropy in $H_{\mathrm{c2}}(T)$ becomes inverse with decreasing temperature. At low temperatures, $H_{\mathrm{c2}}(θ)$ data are featured by two maxima at $θ$ = 0 ($\mathbf{H}\parallel c$) and $π/2$ ($\mathbf{H}\bot c$), which can be quantitatively understood only if uniaxial effective-mass anisotropy and absence of Pauli paramagnetic effect for $\mathbf{H}\bot c$ are taken simultaneously into consideration. The in-plane $H_{\mathrm{c2}}(ϕ)$ profile shows a unique threefold modulation especially at low temperatures. Overall, the characteristic of the $H_{\mathrm{c2}}(θ, ϕ, T)$ data mostly resemble those of the heavy-fermion superconductor UPt$_3$, and we argue in favor of a dominant spin-triplet superconductivity with odd parity in K$_{2}$Cr$_{3}$As$_{3}$.

cond-mat.supr-con↗

arXiv2015

Landau level splitting in Cd3As2 under high magnetic fields

Three-dimensional topological Dirac semimetals (TDSs) are a new kind of Dirac materials that exhibit linear energy dispersion in the bulk and can be viewed as three-dimensional graphene. It has been proposed that TDSs can be driven to other exotic phases like Weyl semimetals, topological insulators and topological superconductors by breaking certain symmetries. Here we report the first transport experiment on Landau level splitting in TDS Cd3As2 single crystals under high magnetic fields, suggesting the removal of spin degeneracy by breaking time reversal symmetry. The detected Berry phase develops an evident angular dependence and possesses a crossover from nontrivial to trivial state under high magnetic fields, a strong hint for a fierce competition between the orbit-coupled field strength and the field-generated mass term. Our results unveil the important role of symmetry breaking in TDSs and further demonstrate a feasible path to generate a Weyl semimetal phase by breaking time reversal symmetry.

cond-mat.mtrl-sci↗