arXiv subjects

Dong Zhou

Publications and source records attributed to Dong Zhou.

At least 19 recordsLinked to original sources

arXiv2026

L-SDPPO: Policy Optimization of Spiking Diffusion Policy for Intra-vehicular Robotic Manipulation

Intra-vehicular robots in spacecraft help reduce astronaut workload and improve mission efficiency. Recent research focuses on using deep learning methods to achieve the acute control required for operations in these complex environments. However, objects exhibit unpredictable, unconstrained drift without gravitational damping. These factors demand robustness against complex multimodal action distributions. Diffusion policies (DP) can model these complex actions, but their iterative sampling process consumes too much energy for the limited power budgets of spacecraft. We therefore propose a low-energy intra-vehicular robotic manipulation framework, L-SDPPO, in which the Spiking Diffusion Policy (SDP) is optimized with a reinforcement learning (RL) algorithm. Furthermore, to address the insufficient perception of dynamic spatiotemporal features in microgravity, we propose the statedependent latency injection (SDLI) mechanism, which mimics biological neural delays to dynamically regulate the timing of input information. Evaluation on five representative intra-vehicular daily tasks (e.g., hatch opening and precision container capping) shows that our method consistently achieves higher success rates and lower energy consumption, compared to the state-of-the-art robotic manipulation methods. These results demonstrate our method is a viable intra-vehicular robotic manipulation method.

cs.RO↗

arXiv2026

Prior Policy Guided Dual-Agent Coordinated Manipulation Planning of Spacecraft-Manipulator System

The strong dynamic coupling between the manipulator and the base poses a significant challenge to maintaining spacecraft attitude stability, potentially compromising mission safety. In this paper, we propose a Dual-Agent Coordinated Manipulation Planning (DACMP) framework that simultaneously achieves high-precision end-effector pose reaching for a 6-DoF space manipulator and attitude stabilization of the base spacecraft. To enhance learning efficiency, we present a prior policy-guided Deep Reinforcement Learning algorithm incorporating the Timestep-level Expert Switching Guidance (TESG) mechanism, thereby promoting global convergence and improving task success rates. Extensive experiments demonstrate that DACMP significantly outperforms baseline DRL algorithms in terms of task success rate and control precision. Furthermore, the robustness of DACMP is validated under various challenging scenarios, including system constraints, environmental disturbances, and perception uncertainties. The code and simulation configurations are available on GitHub: https://github.com/HIT-YuhuiHu/DACMP.

cs.RO↗

arXiv2026

Disorder-induced crossover from phase-averaging to mode-mixing regimes in magnetic domain walls of a second-order topological insulator

We investigate electronic transport across a magnetic domain wall (DW) in a three-dimensional (3D) second-order topological insulator subject to Anderson disorder. In the clean limit, the DW hosts two co-propagating one-dimensional (1D) topological edge states that act as the two arms of an effective Aharonov-Bohm (AB) interferometer, inducing a sinusoidal conductance oscillation. Upon the introduction of disorder, the AB oscillations are suppressed, while a half-quantized plateau of $0.5 e^2/h$ for the ensemble-averaged conductance emerges. Notably, within this plateau, the conductance fluctuation exhibits a distinctive two-step plateau structure, with values of $\sim 0.35 e^2/h$ at moderate disorder, followed by a second plateau at $\sim0.29 e^2/h$ under strong disorder. By developing theoretical frameworks that account for the random-phase interference and inter-mode mixing of the two arms, we identify the first fluctuation plateau as a signature of the phase-averaging regime (PAR) and the second as a signature of the mode-mixing regime (MMR). Furthermore, we show that, in the PAR the conductance follows a U-shaped beta distribution, while it evolves into a uniform distribution in the MMR. The Fano factor associated with shot noise is also computed, which exhibits a similar two-step plateau structure at $1/4$ and $1/3$, corresponding to the PAR and MMR, respectively. Our work provides a clear demonstration of the disorder-induced crossover from PAR to MMR, and highlights the crucial role of second-order conductance cumulants in identifying these transport regimes. The results suggest disorder-engineering as a powerful route for controlling electronic transport across DW-based devices.

cond-mat.mes-hall↗

arXiv2026

Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos

Understanding physical transformation processes is crucial for both human cognition and artificial intelligence systems, particularly from an egocentric perspective, which serves as a key bridge between humans and machines in action modeling. We define this modeling process as Egocentric Instructed Visual State Transition (EIVST), which involves generating intermediate frames that depict object transformations between initial and target states under a brief action instruction. EIVST poses two challenges for current generative models: (1) understanding the visual scenes of the initial and target states and reasoning about transformation steps from an egocentric view, and (2) generating a consistent intermediate transition that follows the given instruction while preserving object appearance across the two visual states. To address these challenges, we propose the EgoIn framework. It first infers the multi-step transition process between two given states using TransitionVLM, fine-tuned on our curated dataset to better adapt to this task and reduce hallucinated information. It then generates a sequence of frames based on transition conditions produced by the proposed Transition Conditioning module. Additionally, we introduce Object-aware Auxiliary Supervision to preserve consistent object appearance throughout the transition. Extensive experiments on human-object and robot-object interaction datasets demonstrate EgoIn's superior performance in generating semantically meaningful and visually coherent transformation sequences.

cs.CV↗

arXiv2026

Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models

Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to sensitive attributes such as gender, race, and religion. In this paper, we introduce a comprehensive multilingual debiasing method named Multiple-Debias to address these issues across multiple languages. By incorporating multilingual counterfactual data augmentation and multilingual Self-Debias across both pre-processing and post-processing stages, alongside parameter-efficient fine-tuning, we significantly reduced biases in MPLMs across three sensitive attributes in four languages. We also extended CrowS-Pairs to German, Spanish, Chinese, and Japanese, validating our full-process multilingual debiasing method for gender, racial, and religious bias. Our experiments show that (i) multilingual debiasing methods surpass monolingual approaches in effectively mitigating biases, and (ii) integrating debiasing information from different languages notably improves the fairness of MPLMs.

cs.CL↗

arXiv2026

NutVLM: A Self-Adaptive Defense Framework against Full-Dimension Attacks for Vision Language Models in Autonomous Driving

Vision Language Models (VLMs) have advanced perception in autonomous driving (AD), but they remain vulnerable to adversarial threats. These risks range from localized physical patches to imperceptible global perturbations. Existing defense methods for VLMs remain limited and often fail to reconcile robustness with clean-sample performance. To bridge these gaps, we propose NutVLM, a comprehensive self-adaptive defense framework designed to secure the entire perception-decision lifecycle. Specifically, we first employ NutNet++ as a sentinel, which is a unified detection-purification mechanism. It identifies benign samples, local patches, and global perturbations through three-way classification. Subsequently, localized threats are purified via efficient grayscale masking, while global perturbations trigger Expert-guided Adversarial Prompt Tuning (EAPT). Instead of the costly parameter updates of full-model fine-tuning, EAPT generates "corrective driving prompts" via gradient-based latent optimization and discrete projection. These prompts refocus the VLM's attention without requiring exhaustive full-model retraining. Evaluated on the Dolphins benchmark, our NutVLM yields a 4.89% improvement in overall metrics (e.g., Accuracy, Language Score, and GPT Score). These results validate NutVLM as a scalable security solution for intelligent transportation. Our code is available at https://github.com/PXX/NutVLM.

cs.CV↗

arXiv2026

Imitation learning-based spacecraft rendezvous and docking method with Expert Demonstration

Existing spacecraft rendezvous and docking control methods largely rely on predefined dynamic models and often exhibit limited robustness in realistic on-orbit environments. To address this issue, this paper proposes an Imitation Learning-based spacecraft rendezvous and docking control framework (IL-SRD) that directly learns control policies from expert demonstrations, thereby reducing dependence on accurate modeling. We propose an anchored decoder target mechanism, which conditions the decoder queries on state-related anchors to explicitly constrain the control generation process. This mechanism enforces physically consistent control evolution and effectively suppresses implausible action deviations in sequential prediction, enabling reliable six-degree-of-freedom (6-DOF) rendezvous and docking control. To further enhance stability, a temporal aggregation mechanism is incorporated to mitigate error accumulation caused by the sequential prediction nature of Transformer-based models, where small inaccuracies at each time step can propagate and amplify over long horizons. Extensive simulation results demonstrate that the proposed IL-SRD framework achieves accurate and energy-efficient model-free rendezvous and docking control. Robustness evaluations further confirm its capability to maintain competitive performance under significant unknown disturbances. The source code is available at https://github.com/Dongzhou-1996/IL-SRD.

cs.RO↗

arXiv2025

E-MMDiT: Revisiting Multimodal Diffusion Transformer Design for Fast Image Synthesis under Limited Resources

Diffusion models have shown strong capabilities in generating high-quality images from text prompts. However, these models often require large-scale training data and significant computational resources to train, or suffer from heavy structure with high latency. To this end, we propose Efficient Multimodal Diffusion Transformer (E-MMDiT), an efficient and lightweight multimodal diffusion model with only 304M parameters for fast image synthesis requiring low training resources. We provide an easily reproducible baseline with competitive results. Our model for 512px generation, trained with only 25M public data in 1.5 days on a single node of 8 AMD MI300X GPUs, achieves 0.66 on GenEval and easily reaches to 0.72 with some post-training techniques such as GRPO. Our design philosophy centers on token reduction as the computational cost scales significantly with the token count. We adopt a highly compressive visual tokenizer to produce a more compact representation and propose a novel multi-path compression module for further compression of tokens. To enhance our design, we introduce Position Reinforcement, which strengthens positional information to maintain spatial coherence, and Alternating Subregion Attention (ASA), which performs attention within subregions to further reduce computational cost. In addition, we propose AdaLN-affine, an efficient lightweight module for computing modulation parameters in transformer blocks. Our code is available at https://github.com/AMD-AGI/Nitro-E and we hope E-MMDiT serves as a strong and practical baseline for future research and contributes to democratization of generative AI models.

cs.CV↗

arXiv2025

ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts

Mixture-of-Experts (MoE) architectures have emerged as a promising approach to scale Large Language Models (LLMs). MoE boosts the efficiency by activating a subset of experts per token. Recent works show that fine-grained experts substantially enriches the combinatorial flexibility of active experts and enhances model expressiveness. However, such a design is fundamentally limited by the layer-local routing mechanism: each layer is restricted to its own expert pool. This requires a careful trade-off between expert dimensionality and routing diversity given fixed parameter budgets. We describe ReXMoE, a novel MoE architecture that improves routing beyond the existing layer-local approaches by allowing routers to reuse experts across adjacent layers. ReXMoE decouples expert dimensionality from per-layer budgets, enabling richer expert combinations without sacrificing individual expert capacity or inflating overall parameters. To this end, we propose a new progressive scaling routing (PSR) strategy to gradually increase the candidate expert pool during training. As a result, ReXMoE improves both language modeling and downstream task performance. Extensive experiments on models ranging from 0.5B to 7B parameters across different architectures demonstrate that ReXMoE consistently improves performance under fixed architectural dimensions, confirming ReXMoE as new design paradigm for parameter-efficient and scalable MoE-based LLMs.

cs.CL↗

arXiv2025

Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking

Although autoregressive (AR) models have demonstrated remarkable success in image generation, extending these models to layout-conditioned generation remains challenging due to the sparse nature of layout conditions and the risk of feature entanglement. We present \textbf{S}tructured \textbf{M}asking for \textbf{AR}-based \textbf{L}ayout-to-\textbf{I}mage (SMARLI), a novel framework that effectively integrates spatial layout constraints into the AR generation process. To equip AR models with layout control, a structured masking strategy is applied to the attention computation to govern the interaction among the global prompt, layout, and image tokens. This design prevents the misassociation of different regions with their corresponding descriptions while enabling the sufficient injection of layout constraints into the generation process. To alleviate the exposure bias of AR models and further enhance generation quality and layout accuracy, we incorporate a Group Relative Policy Optimization (GRPO) post-training scheme. We adapt it to the next-set-based paradigm and introduce a specifically designed layout reward, which is coordinated with an image quality reward to guide policy optimization in a balanced manner. Experimental results demonstrate that SMARLI seamlessly integrates layout tokens with text and image tokens without compromising generation quality, and the proposed masking strategy and post-training scheme can also be transferred to standard next-token-based AR models. The proposed framework achieves superior layout control while maintaining the structural simplicity and generation efficiency of AR models.

cs.CV↗

arXiv2025

Light-Weight Cross-Modal Enhancement Method with Benchmark Construction for UAV-based Open-Vocabulary Object Detection

Open-Vocabulary Object Detection (OVD) faces severe performance degradation when applied to UAV imagery due to the domain gap from ground-level datasets. To address this challenge, we propose a complete UAV-oriented solution that combines both dataset construction and model innovation. First, we design a refined UAV-Label Engine, which efficiently resolves annotation redundancy, inconsistency, and ambiguity, enabling the generation of largescale UAV datasets. Based on this engine, we construct two new benchmarks: UAVDE-2M, with over 2.4M instances across 1,800+ categories, and UAVCAP-15K, providing rich image-text pairs for vision-language pretraining. Second, we introduce the Cross-Attention Gated Enhancement (CAGE) module, a lightweight dual-path fusion design that integrates cross-attention, adaptive gating, and global FiLM modulation for robust textvision alignment. By embedding CAGE into the YOLO-World-v2 framework, our method achieves significant gains in both accuracy and efficiency, notably improving zero-shot detection on VisDrone by +5.3 mAP while reducing parameters and GFLOPs, and demonstrating strong cross-domain generalization on SIMD. Extensive experiments and real-world UAV deployment confirm the effectiveness and practicality of our proposed solution for UAV-based OVD

cs.CV↗

arXiv2025

Multimodal Spiking Neural Network for Space Robotic Manipulation

This paper presents a multimodal control framework based on spiking neural networks (SNNs) for robotic arms aboard space stations. It is designed to cope with the constraints of limited onboard resources while enabling autonomous manipulation and material transfer in space operations. By combining geometric states with tactile and semantic information, the framework strengthens environmental awareness and contributes to more robust control strategies. To guide the learning process progressively, a dual-channel, three-stage curriculum reinforcement learning (CRL) scheme is further integrated into the system. The framework was tested across a range of tasks including target approach, object grasping, and stable lifting with wall-mounted robotic arms, demonstrating reliable performance throughout. Experimental evaluations demonstrate that the proposed method consistently outperforms baseline approaches in both task success rate and energy efficiency. These findings highlight its suitability for real-world aerospace applications.

cs.RO↗

arXiv2025

Language-Conditioned Open-Vocabulary Mobile Manipulation with Pretrained Models

Open-vocabulary mobile manipulation (OVMM) that involves the handling of novel and unseen objects across different workspaces remains a significant challenge for real-world robotic applications. In this paper, we propose a novel Language-conditioned Open-Vocabulary Mobile Manipulation framework, named LOVMM, incorporating the large language model (LLM) and vision-language model (VLM) to tackle various mobile manipulation tasks in household environments. Our approach is capable of solving various OVMM tasks with free-form natural language instructions (e.g. "toss the food boxes on the office room desk to the trash bin in the corner", and "pack the bottles from the bed to the box in the guestroom"). Extensive experiments simulated in complex household environments show strong zero-shot generalization and multi-task learning abilities of LOVMM. Moreover, our approach can also generalize to multiple tabletop manipulation tasks and achieve better success rates compared to other state-of-the-art methods.

cs.RO↗

arXiv2025

Megrez2 Technical Report

We present Megrez2, a novel lightweight and high-performance language model architecture optimized for device native deployment. Megrez2 introduces a novel cross-layer expert sharing mechanism, which significantly reduces total parameter count by reusing expert modules across adjacent transformer layers while maintaining most of the model's capacity. It also incorporates pre-gated routing, enabling memory-efficient expert loading and faster inference. As the first instantiation of the Megrez2 architecture, we introduce the Megrez2-Preview model, which is pre-trained on a 5-trillion-token corpus and further enhanced through supervised fine-tuning and reinforcement learning with verifiable rewards. With only 3B activated and 7.5B stored parameters, Megrez2-Preview demonstrates competitive or superior performance compared to larger models on a wide range of tasks, including language understanding, instruction following, mathematical reasoning, and code generation. These results highlight the effectiveness of the Megrez2 architecture to achieve a balance between accuracy, efficiency, and deployability, making it a strong candidate for real-world, resource-constrained applications.

cs.CL↗

arXiv2025

GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraft

Monocular pose estimation of non-cooperative spacecraft is significant for on-orbit service (OOS) tasks, such as satellite maintenance, space debris removal, and station assembly. Considering the high demands on pose estimation accuracy, mainstream monocular pose estimation methods typically consist of keypoint detectors and PnP solver. However, current keypoint detectors remain vulnerable to structural symmetry and partial occlusion of non-cooperative spacecraft. To this end, we propose a graph-based keypoints network for the monocular pose estimation of non-cooperative spacecraft, GKNet, which leverages the geometric constraint of keypoints graph. In order to better validate keypoint detectors, we present a moderate-scale dataset for the spacecraft keypoint detection, named SKD, which consists of 3 spacecraft targets, 90,000 simulated images, and corresponding high-precise keypoint annotations. Extensive experiments and an ablation study have demonstrated the high accuracy and effectiveness of our GKNet, compared to the state-of-the-art spacecraft keypoint detectors. The code for GKNet and the SKD dataset is available at https://github.com/Dongzhou-1996/GKNet.

cs.CV↗

arXiv2025

AMD-Hummingbird: Towards an Efficient Text-to-Video Model

Text-to-Video (T2V) generation has attracted significant attention for its ability to synthesize realistic videos from textual descriptions. However, existing models struggle to balance computational efficiency and high visual quality, particularly on resource-limited devices, e.g.,iGPUs and mobile phones. Most prior work prioritizes visual fidelity while overlooking the need for smaller, more efficient models suitable for real-world deployment. To address this challenge, we propose a lightweight T2V framework, termed Hummingbird, which prunes existing models and enhances visual quality through visual feedback learning. Our approach reduces the size of the U-Net from 1.4 billion to 0.7 billion parameters, significantly improving efficiency while preserving high-quality video generation. Additionally, we introduce a novel data processing pipeline that leverages Large Language Models (LLMs) and Video Quality Assessment (VQA) models to enhance the quality of both text prompts and video data. To support user-driven training and style customization, we publicly release the full training code, including data processing and model training. Extensive experiments show that our method achieves a 31X speedup compared to state-of-the-art models such as VideoCrafter2, while also attaining the highest overall score on VBench. Moreover, our method supports the generation of videos with up to 26 frames, addressing the limitations of existing U-Net-based methods in long video generation. Notably, the entire training process requires only four GPUs, yet delivers performance competitive with existing leading methods. Hummingbird presents a practical and efficient solution for T2V generation, combining high performance, scalability, and flexibility for real-world applications.

cs.CV↗

arXiv2025

LLM-driven Effective Knowledge Tracing by Integrating Dual-channel Difficulty

Knowledge Tracing (KT) is a fundamental technology in intelligent tutoring systems used to simulate changes in students' knowledge state during learning, track personalized knowledge mastery, and predict performance. However, current KT models face three major challenges: (1) When encountering new questions, models face cold-start problems due to sparse interaction records, making precise modeling difficult; (2) Traditional models only use historical interaction records for student personalization modeling, unable to accurately track individual mastery levels, resulting in unclear personalized modeling; (3) The decision-making process is opaque to educators, making it challenging for them to understand model judgments. To address these challenges, we propose a novel Dual-channel Difficulty-aware Knowledge Tracing (DDKT) framework that utilizes Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) for subjective difficulty assessment, while integrating difficulty bias-aware algorithms and student mastery algorithms for precise difficulty measurement. Our framework introduces three key innovations: (1) Difficulty Balance Perception Sequence (DBPS) - students' subjective perceptions combined with objective difficulty, measuring gaps between LLM-assessed difficulty, mathematical-statistical difficulty, and students' subjective perceived difficulty through attention mechanisms; (2) Difficulty Mastery Ratio (DMR) - precise modeling of student mastery levels through different difficulty zones; (3) Knowledge State Update Mechanism - implementing personalized knowledge acquisition through gated networks and updating student knowledge state. Experimental results on two real datasets show our method consistently outperforms nine baseline models, improving AUC metrics by 2% to 10% while effectively addressing cold-start problems and enhancing model interpretability.

cs.AI↗

arXiv2025

Megrez-Omni Technical Report

In this work, we present the Megrez models, comprising a language model (Megrez-3B-Instruct) and a multimodal model (Megrez-3B-Omni). These models are designed to deliver fast inference, compactness, and robust edge-side intelligence through a software-hardware co-design approach. Megrez-3B-Instruct offers several advantages, including high accuracy, high speed, ease of use, and a wide range of applications. Building on Megrez-3B-Instruct, Megrez-3B-Omni is an on-device multimodal understanding LLM that supports image, text, and audio analysis. It achieves state-of-the-art accuracy across all three modalities and demonstrates strong versatility and robustness, setting a new benchmark for multimodal AI models.

cs.LG↗