arXiv subjects

Xueqian Wang

Publications and source records attributed to Xueqian Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

CausalNav: A Long-term Embodied Navigation System for Autonomous Mobile Robots in Dynamic Outdoor Scenarios

Autonomous language-guided navigation in large-scale outdoor environments remains a key challenge in mobile robotics, due to difficulties in semantic reasoning, dynamic conditions, and long-term stability. We propose CausalNav, the first scene graph-based semantic navigation framework tailored for dynamic outdoor environments. We construct a multi-level semantic scene graph using LLMs, referred to as the Embodied Graph, that hierarchically integrates coarse-grained map data with fine-grained object entities. The constructed graph serves as a retrievable knowledge base for Retrieval-Augmented Generation (RAG), enabling semantic navigation and long-range planning under open-vocabulary queries. By fusing real-time perception with offline map data, the Embodied Graph supports robust navigation across varying spatial granularities in dynamic outdoor environments. Dynamic objects are explicitly handled in both the scene graph construction and hierarchical planning modules. The Embodied Graph is continuously updated within a temporal window to reflect environmental changes and support real-time semantic navigation. Extensive experiments in both simulation and real-world settings demonstrate superior robustness and efficiency.

cs.RO↗

arXiv2025

Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges

Brain-body co-evolution enables animals to develop complex behaviors in their environments. Inspired by this biological synergy, embodied co-design (ECD) has emerged as a transformative paradigm for creating intelligent agents-from virtual creatures to physical robots-by jointly optimizing their morphologies and controllers rather than treating control in isolation. This integrated approach facilitates richer environmental interactions and robust task performance. In this survey, we provide a systematic overview of recent advances in ECD. We first formalize the concept of ECD and position it within related fields. We then introduce a hierarchical taxonomy: a lower layer that breaks down agent design into three fundamental components-controlling brain, body morphology, and task environment-and an upper layer that integrates these components into four major ECD frameworks: bi-level, single-level, generative, and open-ended. This taxonomy allows us to synthesize insights from more than one hundred recent studies. We further review notable benchmarks, datasets, and applications in both simulated and real-world scenarios. Finally, we identify significant challenges and offer insights into promising future research directions. A project associated with this survey has been created at https://github.com/Yuxing-Wang-THU/SurveyBrainBody.

cs.RO↗

arXiv2025

No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching

Diffusion models achieve remarkable generative quality, but computational overhead scales with step count, model depth, and sequence length. Feature caching is effective since adjacent timesteps yield highly similar features. However, an inherent trade-off remains: aggressive timestep reuse offers large speedups but can easily cross the critical line, hurting fidelity, while block- or token-level reuse is safer but yields limited computational savings. We present X-Slim (eXtreme-Slimming Caching), a training-free, cache-based accelerator that, to our knowledge, is the first unified framework to exploit cacheable redundancy across timesteps, structure (blocks), and space (tokens). Rather than simply mixing levels, X-Slim introduces a dual-threshold controller that turns caching into a push-then-polish process: it first pushes reuse at the timestep level up to an early-warning line, then switches to lightweight block- and token-level refresh to polish the remaining redundancy, and triggers full inference once the critical line is crossed to reset accumulated error. At each level, context-aware indicators decide when and where to cache. Across diverse tasks, X-Slim advances the speed-quality frontier. On FLUX.1-dev and HunyuanVideo, it reduces latency by up to 4.97x and 3.52x with minimal perceptual loss. On DiT-XL/2, it reaches 3.13x acceleration and improves FID by 2.42 over prior methods.

cs.CV↗

arXiv2025

Count Every Rotation and Every Rotation Counts: Exploring Drone Dynamics via Propeller Sensing

As drone-based applications proliferate, paramount contactless sensing of airborne drones from the ground becomes indispensable. This work demonstrates concentrating on propeller rotational speed will substantially improve drone sensing performance and proposes an event-camera-based solution, \sysname. \sysname features two components: \textit{Count Every Rotation} achieves accurate, real-time propeller speed estimation by mitigating ultra-high sensitivity of event cameras to environmental noise. \textit{Every Rotation Counts} leverages these speeds to infer both internal and external drone dynamics. Extensive evaluations in real-world drone delivery scenarios show that \sysname achieves a sensing latency of 3$ms$ and a rotational speed estimation error of merely 0.23\%. Additionally, \sysname infers drone flight commands with 96.5\% precision and improves drone tracking accuracy by over 22\% when combined with other sensing modalities. \textit{ Demo: {\color{blue}https://eventpro25.github.io/EventPro/.} }

cs.RO↗

arXiv2025

AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization

Implicit Q-learning (IQL) serves as a strong baseline for offline RL, which learns the value function using only dataset actions through quantile regression. However, it is unclear how to recover the implicit policy from the learned implicit Q-function and why IQL can utilize weighted regression for policy extraction. IDQL reinterprets IQL as an actor-critic method and gets weights of implicit policy, however, this weight only holds for the optimal value function. In this work, we introduce a different way to solve the implicit policy-finding problem (IPF) by formulating this problem as an optimization problem. Based on this optimization problem, we further propose two practical algorithms AlignIQL and AlignIQL-hard, which inherit the advantages of decoupling actor from critic in IQL and provide insights into why IQL can use weighted regression for policy extraction. Compared with IQL and IDQL, we find our method keeps the simplicity of IQL and solves the implicit policy-finding problem. Experimental results on D4RL datasets show that our method achieves competitive or superior results compared with other SOTA offline RL methods. Especially in complex sparse reward tasks like Antmaze and Adroit, our method outperforms IQL and IDQL by a significant margin.

cs.LG↗

arXiv2025

GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to exploit the inherent parallelism among independent sub-tasks. This sequential bottleneck leads to inefficient tool utilization and suboptimal performance in multi-step reasoning scenarios. We introduce Graph-based Agent Planning (GAP), a novel framework that explicitly models inter-task dependencies through graph-based planning to enable adaptive parallel and serial tool execution. Our approach trains agent foundation models to decompose complex tasks into dependency-aware sub-task graphs, autonomously determining which tools can be executed in parallel and which must follow sequential dependencies. This dependency-aware orchestration achieves substantial improvements in both execution efficiency and task accuracy. To train GAP, we construct a high-quality dataset of graph-based planning traces derived from the Multi-Hop Question Answering (MHQA) benchmark. We employ a two-stage training strategy: supervised fine-tuning (SFT) on the curated dataset, followed by reinforcement learning (RL) with a correctness-based reward function on strategically sampled queries where tool-based reasoning provides maximum value. Experimental results on MHQA datasets demonstrate that GAP significantly outperforms traditional ReAct baselines, particularly on multi-step retrieval tasks, while achieving dramatic improvements in tool invocation efficiency through intelligent parallelization. The project page is available at: https://github.com/WJQ7777/Graph-Agent-Planning.

cs.AI↗

arXiv2025

Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption

Pretraining a policy on offline data followed by fine-tuning through online interactions, known as Offline-to-Online Reinforcement Learning (O2O RL), has emerged as a promising paradigm for real-world RL deployment. However, both offline datasets and online interactions in practical environments are often noisy or even maliciously corrupted, severely degrading the performance of O2O RL. Existing works primarily focus on mitigating the conservatism of offline policies via online exploration, while the robustness of O2O RL under data corruption, including states, actions, rewards, and dynamics, is still unexplored. In this work, we observe that data corruption induces heavy-tailed behavior in the policy, thereby substantially degrading the efficiency of online exploration. To address this issue, we incorporate Inverse Probability Weighted (IPW) into the online exploration policy to alleviate heavy-tailedness, and propose a novel, simple yet effective method termed $\textbf{RPEX}$: $\textbf{R}$obust $\textbf{P}$olicy $\textbf{EX}$pansion. Extensive experimental results on D4RL datasets demonstrate that RPEX achieves SOTA O2O performance across a wide range of data corruption scenarios. Code is available at $\href{https://github.com/felix-thu/RPEX}{https://github.com/felix-thu/RPEX}$.

cs.LG↗

arXiv2025

When marine radar target detection meets pretrained large language models

Deep learning (DL) methods are widely used to extract high-dimensional patterns from the sequence features of radar echo signals. However, conventional DL algorithms face challenges such as redundant feature segments, and constraints from restricted model sizes. To address these issues, we propose a framework that integrates feature preprocessing with large language models (LLMs). Our preprocessing module tokenizes radar sequence features, applies a patch selection algorithm to filter out uninformative segments, and projects the selected patches into embeddings compatible with the feature space of pre-trained LLMs. Leveraging these refined embeddings, we incorporate a pre-trained LLM, fine-tuning only the normalization layers to reduce training burdens while enhancing performance. Experiments on measured datasets demonstrate that the proposed method significantly outperforms the state-of-the-art baselines on supervised learning tests.

eess.SP↗

arXiv2025

A Hybrid Force-Position Strategy for Shape Control of Deformable Linear Objects With Graph Attention Networks

Manipulating deformable linear objects (DLOs) such as wires and cables is crucial in various applications like electronics assembly and medical surgeries. However, it faces challenges due to DLOs' infinite degrees of freedom, complex nonlinear dynamics, and the underactuated nature of the system. To address these issues, this paper proposes a hybrid force-position strategy for DLO shape control. The framework, combining both force and position representations of DLO, integrates state trajectory planning in the force space and Model Predictive Control (MPC) in the position space. We present a dynamics model with an explicit action encoder, a property extractor and a graph processor based on Graph Attention Networks. The model is used in the MPC to enhance prediction accuracy. Results from both simulations and real-world experiments demonstrate the effectiveness of our approach in achieving efficient and stable shape control of DLOs. Codes and videos are available at https://sites.google.com/view/dlom.

cs.RO↗

arXiv2025

GSON: A Group-based Social Navigation Framework with Large Multimodal Model

With the increasing presence of service robots and autonomous vehicles in human environments, navigation systems need to evolve beyond simple destination reach to incorporate social awareness. This paper introduces GSON, a novel group-based social navigation framework that leverages Large Multimodal Models (LMMs) to enhance robots' social perception capabilities. Our approach uses visual prompting to enable zero-shot extraction of social relationships among pedestrians and integrates these results with robust pedestrian detection and tracking pipelines to overcome the inherent inference speed limitations of LMMs. The planning system incorporates a mid-level planner that sits between global path planning and local motion planning, effectively preserving both global context and reactive responsiveness while avoiding disruption of the predicted social group. We validate GSON through extensive real-world mobile robot navigation experiments involving complex social scenarios such as queuing, conversations, and photo sessions. Comparative results show that our system significantly outperforms existing navigation approaches in minimizing social perturbations while maintaining comparable performance on traditional navigation metrics.

cs.RO↗

arXiv2025

A Universal Vehicle-Trailer Navigation System with Neural Kinematics and Online Residual Learning

Autonomous navigation of vehicle-trailer systems is crucial in environments like airports, supermarkets, and concert venues, where various types of trailers are needed to navigate with different payloads and conditions. However, accurately modeling such systems remains challenging, especially for trailers with castor wheels. In this work, we propose a novel universal vehicle-trailer navigation system that integrates a hybrid nominal kinematic model--combining classical nonholonomic constraints for vehicles and neural network-based trailer kinematics--with a lightweight online residual learning module to correct real-time modeling discrepancies and disturbances. Additionally, we develop a model predictive control framework with a weighted model combination strategy that improves long-horizon prediction accuracy and ensures safer motion planning. Our approach is validated through extensive real-world experiments involving multiple trailer types and varying payload conditions, demonstrating robust performance without manual tuning or trailer-specific calibration.

cs.RO↗

arXiv2025

Data-Driven MPC with Data Selection for Flexible Cable-Driven Robotic Arms

Flexible cable-driven robotic arms (FCRAs) offer dexterous and compliant motion. Still, the inherent properties of cables, such as resilience, hysteresis, and friction, often lead to particular difficulties in modeling and control. This paper proposes a model predictive control (MPC) method that relies exclusively on input-output data, without a physical model, to improve the control accuracy of FCRAs. First, we develop an implicit model based on input-output data and integrate it into an MPC optimization framework. Second, a data selection algorithm (DSA) is introduced to filter the data that best characterize the system, thereby reducing the solution time per step to approximately 4 ms, which is an improvement of nearly 80%. Lastly, the influence of hyperparameters on tracking error is investigated through simulation. The proposed method has been validated on a real FCRA platform, including five-point positioning accuracy tests, a five-point response tracking test, and trajectory tracking for letter drawing. The results demonstrate that the average positioning accuracy is approximately 2.070 mm. Moreover, compared to the PID method with an average tracking error of 1.418°, the proposed method achieves an average tracking error of 0.541°.

cs.RO↗

arXiv2025

OMR-Diffusion:Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Intent Understanding

Generative AI has significantly advanced text-driven image generation, but it still faces challenges in producing outputs that consistently align with evolving user preferences and intents, particularly in multi-turn dialogue scenarios. In this research, We present a Visual Co-Adaptation (VCA) framework that incorporates human-in-the-loop feedback, utilizing a well-trained reward model specifically designed to closely align with human preferences. Using a diverse multi-turn dialogue dataset, the framework applies multiple reward functions (such as diversity, consistency, and preference feedback) to refine the diffusion model through LoRA, effectively optimizing image generation based on user input. We also constructed multi-round dialogue datasets with prompts and image pairs that well-fit user intent. Experiments show the model achieves 508 wins in human evaluation, outperforming DALL-E 3 (463 wins) and others. It also achieves 3.4 rounds in dialogue efficiency (vs. 13.7 for DALL-E 3) and excels in metrics like LPIPS (0.15) and BLIP (0.59). Various experiments demonstrate the effectiveness of the proposed method over state-of-the-art baselines, with significant improvements in image consistency and alignment with user intent.

cs.CV↗

arXiv2025

TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation

Although text-to-image generation technologies have made significant advancements, they still face challenges when dealing with ambiguous prompts and aligning outputs with user intent.Our proposed framework, TDRI (Two-Phase Dialogue Refinement and Co-Adaptation), addresses these issues by enhancing image generation through iterative user interaction. It consists of two phases: the Initial Generation Phase, which creates base images based on user prompts, and the Interactive Refinement Phase, which integrates user feedback through three key modules. The Dialogue-to-Prompt (D2P) module ensures that user feedback is effectively transformed into actionable prompts, which improves the alignment between user intent and model input. By evaluating generated outputs against user expectations, the Feedback-Reflection (FR) module identifies discrepancies and facilitates improvements. In an effort to ensure consistently high-quality results, the Adaptive Optimization (AO) module fine-tunes the generation process by balancing user preferences and maintaining prompt fidelity. Experimental results show that TDRI outperforms existing methods by achieving 33.6% human preference, compared to 6.2% for GPT-4 augmentation, and the highest CLIP and BLIP alignment scores (0.338 and 0.336, respectively). In iterative feedback tasks, user satisfaction increased to 88% after 8 rounds, with diminishing returns beyond 6 rounds. Furthermore, TDRI has been found to reduce the number of iterations and improve personalization in the creation of fashion products. TDRI exhibits a strong potential for a wide range of applications in the creative and industrial domains, as it streamlines the creative process and improves alignment with user preferences

cs.CV↗

arXiv2025

Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion

Recent advancements in text-to-image (T2I) generation using diffusion models have enabled cost-effective video-editing applications by leveraging pre-trained models, eliminating the need for resource-intensive training. However, the frame-independence of T2I generation often results in poor temporal consistency. Existing methods address this issue through temporal layer fine-tuning or inference-based temporal propagation, but these approaches suffer from high training costs or limited temporal coherence. To address these challenges, we propose a General and Efficient Adapter (GE-Adapter) that integrates temporal-spatial and semantic consistency with Baliteral DDIM inversion. This framework introduces three key components: (1) Frame-based Temporal Consistency Blocks (FTC Blocks) to capture frame-specific features and enforce smooth inter-frame transitions via temporally-aware loss functions; (2) Channel-dependent Spatial Consistency Blocks (SCD Blocks) employing bilateral filters to enhance spatial coherence by reducing noise and artifacts; and (3) Token-based Semantic Consistency Module (TSC Module) to maintain semantic alignment using shared prompt tokens and frame-specific tokens. Our method significantly improves perceptual quality, text-image alignment, and temporal coherence, as demonstrated on the MSR-VTT dataset. Additionally, it achieves enhanced fidelity and frame-to-frame coherence, offering a practical solution for T2V editing.

cs.CV↗

arXiv2025

QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning

Prompt engineering has demonstrated remarkable success in enhancing the performance of large language models (LLMs) across diverse tasks. However, most existing prompt optimization methods only focus on the task-level performance, overlooking the importance of query-preferred prompts, which leads to suboptimal performances. Additionally, these methods rely heavily on frequent interactions with LLMs to obtain feedback for guiding the optimization process, incurring substantial redundant interaction costs. In this paper, we introduce Query-dependent Prompt Optimization (QPO), which leverages multi-loop offline reinforcement learning to iteratively fine-tune a small pretrained language model to generate optimal prompts tailored to the input queries, thus significantly improving the prompting effect on the large target LLM. We derive insights from offline prompting demonstration data, which already exists in large quantities as a by-product of benchmarking diverse prompts on open-sourced tasks, thereby circumventing the expenses of online interactions. Furthermore, we continuously augment the offline dataset with the generated prompts in each loop, as the prompts from the fine-tuned model are supposed to outperform the source prompts in the original dataset. These iterative loops bootstrap the model towards generating optimal prompts. Experiments on various LLM scales and diverse NLP and math tasks demonstrate the efficacy and cost-efficiency of our method in both zero-shot and few-shot scenarios.

cs.AI↗

arXiv2025

Safety Reasoning with Guidelines

Training safe LLMs remains a critical challenge. The most widely used method, Refusal Training (RT), struggles to generalize against various Out-of-Distribution (OOD) jailbreaking attacks. Although various advanced methods have been proposed to address this issue, we instead question whether OOD attacks inherently surpass the capability of vanilla RT. Evaluations using Best-of-N (BoN) reveal significant safety improvements as N increases, indicating models possess adequate latent safety knowledge but RT fails to consistently elicit it under OOD scenarios. Further domain adaptation analysis reveals that direct RT causes reliance on superficial shortcuts, resulting in non-generalizable representation mappings. Inspired by our findings, we propose training model to perform safety reasoning for each query. Specifically, we synthesize reasoning supervision aligned with specified guidelines that reflect diverse perspectives on safety knowledge. This encourages model to engage in deeper reasoning, explicitly eliciting and utilizing latent safety knowledge for each query. Extensive experiments show that our method significantly improves model generalization against OOD attacks.

cs.LG↗

arXiv2025

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

Despite recent advancements in offline multi-task reinforcement learning (MTRL) have harnessed the powerful capabilities of the Transformer architecture, most approaches focus on a limited number of tasks, with scaling to extremely massive tasks remaining a formidable challenge. In this paper, we first revisit the key impact of task numbers on current MTRL method, and further reveal that naively expanding the parameters proves insufficient to counteract the performance degradation as the number of tasks escalates. Building upon these insights, we propose M3DT, a novel mixture-of-experts (MoE) framework that tackles task scalability by further unlocking the model's parameter scalability. Specifically, we enhance both the architecture and the optimization of the agent, where we strengthen the Decision Transformer (DT) backbone with MoE to reduce task load on parameter subsets, and introduce a three-stage training mechanism to facilitate efficient training with optimal performance. Experimental results show that, by increasing the number of experts, M3DT not only consistently enhances its performance as model expansion on the fixed task numbers, but also exhibits remarkable task scalability, successfully extending to 160 tasks with superior performance.

cs.LG↗