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.

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.

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.

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.

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.

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.

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.

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.

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.

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.