arXiv subjects

Xu Liu

Publications and source records attributed to Xu Liu.

At least 91 records · Page 5Linked to original sources

arXiv2025

Beyond Autophagy: VPS39 Deficiency Triggers Migrasome-Driven Stress Adaptation Revealed by Super-Resolution Imaging

Autophagy and migrasome formation constitute critical cellular mechanisms for maintaining cellular homeostasis, however, their potential compensatory interplay remains poorly understood. In this study, we identify VPS39, a core component of the HOPS complex, as a molecular switch coordinating these processes. Genetic ablation of VPS39 not only impairs autophagic flux but also triggers cell migration through RhoA/Rac1 GTPases upregulation, consequently facilitating migrasome formation. Using super-resolution microscopy, we further demonstrate that migrasomes serve as an alternative disposal route for damaged mitochondria during VPS39-induced autophagy impairment, revealing a novel stress adaptation mechanism. Our work establishes a previously unrecognized autophagy-migrasome axis and provides direct visual evidence of organelle quality control via migrasomal extrusion. These findings position VPS39-regulated pathway switching as a potential therapeutic strategy for neurodegenerative diseases characterized by autophagy dysfunction.

q-bio.CB↗

arXiv2025

Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation

Text-to-image (T2I) diffusion models have recently demonstrated significant progress in video editing. However, existing video editing methods are severely limited by their high computational overhead and memory consumption. Furthermore, these approaches often sacrifice visual fidelity, leading to undesirable temporal inconsistencies and artifacts such as blurring and pronounced mosaic-like patterns. We propose Edit-Your-Interest, a lightweight, text-driven, zero-shot video editing method. Edit-Your-Interest introduces a spatio-temporal feature memory to cache features from previous frames, significantly reducing computational overhead compared to full-sequence spatio-temporal modeling approaches. Specifically, we first introduce a Spatio-Temporal Feature Memory bank (SFM), which is designed to efficiently cache and retain the crucial image tokens processed by spatial attention. Second, we propose the Feature Most-Similar Propagation (FMP) method. FMP propagates the most relevant tokens from previous frames to subsequent ones, preserving temporal consistency. Finally, we introduce an SFM update algorithm that continuously refreshes the cached features, ensuring their long-term relevance and effectiveness throughout the video sequence. Furthermore, we leverage cross-attention maps to automatically extract masks for the instances of interest. These masks are seamlessly integrated into the diffusion denoising process, enabling fine-grained control over target objects and allowing Edit-Your-Interest to perform highly accurate edits while robustly preserving the background integrity. Extensive experiments decisively demonstrate that the proposed Edit-Your-Interest outperforms state-of-the-art methods in both efficiency and visual fidelity, validating its superior effectiveness and practicality.

cs.CV↗

arXiv2025

VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones

Recent studies have indicated that vision models pre-trained on images can serve as time series foundation models (TSFMs) by reformulating time series forecasting (TSF) as image reconstruction. However, effective cross-modal transfer from vision to time series remains challenging due to three discrepancies: (1) the data-modality gap between structured, bounded image data and unbounded, heterogeneous time series; (2) the multivariate-forecasting gap between fixed RGB-three-channel vision models and time series with arbitrary numbers of variates; and (3) the probabilistic-forecasting gap between the deterministic outputs of vision models and the requirement for uncertainty-aware probabilistic predictions. To bridge these gaps, we propose VisonTS++, a TSFM based on continual pre-training of a vision model on large-scale time series. Our approach introduces three key innovations: (1) vision-model-based filtering to identify high-quality sequences to stabilize pre-training and mitigate modality gap; (2) colorized multivariate conversion, encoding multivariate series as multi-subfigure RGB images to enhance cross-variate modeling; (3) multi-quantile forecasting, using parallel reconstruction heads to generate quantile forecasts without parametric assumptions. Experiments show that VisionTS++ achieves state-of-the-art performance in both in-distribution and out-of-distribution forecasting, outperforming specialized TSFMs by 6%-44% in MSE reduction and ranking first in GIFT-Eval benchmark which comprises 23 datasets across 7 domains. Our work demonstrates that with appropriate adaptation, vision models can effectively generalize to TSF, thus advancing the pursuit of universal TSFMs. Code is available at https://github.com/HALF111/VisionTSpp.

cs.CV↗

arXiv2025

SlideSLAM: Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Multi-Robot Navigation

This paper develops a real-time decentralized metric-semantic SLAM algorithm that enables a heterogeneous robot team to collaboratively construct object-based metric-semantic maps. The proposed framework integrates a data-driven front-end for instance segmentation from either RGBD cameras or LiDARs and a custom back-end for optimizing robot trajectories and object landmarks in the map. To allow multiple robots to merge their information, we design semantics-driven place recognition algorithms that leverage the informativeness and viewpoint invariance of the object-level metric-semantic map for inter-robot loop closure detection. A communication module is designed to track each robot's observations and those of other robots whenever communication links are available. The framework supports real-time, decentralized operation onboard the robots and has been integrated with three types of aerial and ground platforms. We validate its effectiveness through experiments in both indoor and outdoor environments, as well as benchmarks on public datasets and comparisons with existing methods. The framework is open-sourced and suitable for both single-agent and multi-robot real-time metric-semantic SLAM applications. The code is available at: https://github.com/KumarRobotics/SLIDE_SLAM.

cs.RO↗

arXiv2025

Two conjectures on vertex-disjoint rainbow triangles

In 1963, Dirac proved that every $n$-vertex graph has $k$ vertex-disjoint triangles if $n\geq 3k$ and minimum degree $δ(G)\geq \frac{n+k}{2}$. The base case $n=3k$ can be reduced to the Corrádi-Hajnál Theorem. Towards a rainbow version of Dirac's Theorem, Hu, Li, and Yang conjectured that for all positive integers $n$ and $k$ with $n\geq 3k$, every edge-colored graph $G$ of order $n$ with $δ^c(G)\geq \frac{n+k}{2}$ contains $k$ vertex-disjoint rainbow triangles. In another direction, Wu et al. conjectured an exact formula for anti-Ramsey number $ar(n,kC_3)$, generalizing the earlier work of Erdős, Sós and Simonovits. The conjecture of Hu, Li, and Yang was confirmed for the cases $k=1$ and $k=2$. However, Lo and Williams disproved the conjecture when $n\leq \frac{17k}{5}.$ It is therefore natural to ask whether the conjecture holds for $n=Ω(k)$. In this paper, we confirm this by showing that the Hu-Li-Yang conjecture holds when $n\ge 42.5k+48$. We disprove the conjecture of Wu et al. and propose a modified conjecture. This conjecture is motivated by previous works due to Allen, Böttcher, Hladký, and Piguet on Turán number of vertex-disjoint triangles.

math.CO↗

arXiv2025

Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation

We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a) acceptance of only one style image, thus prohibiting hybrid aesthetics and scalability to more styles, and (b) lack of a principled mechanism to balance several stylistic influences. AMSF mitigates these challenges by encoding all style images and textual hints with a semantic token decomposition module that is adaptively injected into every cross-attention layer of an frozen diffusion model. A similarity-aware re-weighting module then recalibrates, at each denoising step, the attention allocated to every style component, yielding balanced and user-controllable blends without any fine-tuning or external adapters. Both qualitative and quantitative evaluations show that AMSF produces multi-style fusion results that consistently outperform the state-of-the-art approaches, while its fusion design scales seamlessly to two or more styles. These capabilities position AMSF as a practical step toward expressive multi-style generation in diffusion models.

cs.CV↗

arXiv2025

Prompt-Guided Dual Latent Steering for Inversion Problems

Inverting corrupted images into the latent space of diffusion models is challenging. Current methods, which encode an image into a single latent vector, struggle to balance structural fidelity with semantic accuracy, leading to reconstructions with semantic drift, such as blurred details or incorrect attributes. To overcome this, we introduce Prompt-Guided Dual Latent Steering (PDLS), a novel, training-free framework built upon Rectified Flow models for their stable inversion paths. PDLS decomposes the inversion process into two complementary streams: a structural path to preserve source integrity and a semantic path guided by a prompt. We formulate this dual guidance as an optimal control problem and derive a closed-form solution via a Linear Quadratic Regulator (LQR). This controller dynamically steers the generative trajectory at each step, preventing semantic drift while ensuring the preservation of fine detail without costly, per-image optimization. Extensive experiments on FFHQ-1K and ImageNet-1K under various inversion tasks, including Gaussian deblurring, motion deblurring, super-resolution and freeform inpainting, demonstrate that PDLS produces reconstructions that are both more faithful to the original image and better aligned with the semantic information than single-latent baselines.

cs.CV↗

arXiv2025

Outer Contour-driven Ruled Surface Generation for Linear Hot-wire Rough Machining

We propose a novel method to generate a small set of ruled surfaces that do not collide with the input shape for linear hot-wire rough machining. Central to our technique is a new observation: the ruled surfaces constructed by vertical extrusion from planar smooth curves, which approach the input shape's outer contour lines while having no collisions, are capable of removing materials effectively during rough machining. Accordingly, we develop an iterative algorithm that alternates in each iteration between computing a viewpoint to determine an outer contour line and optimizing a smooth curve to approximate that contour line under the collision-free constraint. Specifically, a view selection approach based on genetic algorithm is used to optimize the viewpoint for removing materials as much as possible, and present an adaptive algorithm to find the constrained curves. The feasibility and practicability of our method are demonstrated through 10 physical examples. Compared with manual designs, our method obtains lower errors with the same number of cuts.

cs.CG↗

arXiv2025

Mechanical non-reciprocity programmed by shear jamming in soft composite solids

Mechanical non-reciprocity-manifested as asymmetric responses to opposing mechanical stimuli-has traditionally been achieved through intricate structural nonlinearities in metamaterials. However, continuum solids with inherent non-reciprocal mechanics remain underexplored, despite their promising potential for applications such as wave guiding, robotics, and adaptive materials. Here, we introduce a design principle by employing the shear jamming transition from granular physics to engineer non-reciprocal mechanics in soft composite solids. Through the control of the interplay between inclusion contact networks and matrix elasticity, we achieve tunable, direction-dependent asymmetry in both shear and normal mechanical responses. In addition to static regimes, we demonstrate programmable non-reciprocal dynamics by combining responsive magnetic profiles with the anisotropic characteristics of shear-jammed systems. This strategy enables asymmetric spatiotemporal control over motion transmission, a previously challenging feat in soft materials. Our work establishes a novel paradigm for designing non-reciprocal matter, bridging granular physics with soft material engineering to realize functionalities essential for mechano-intelligent systems.

cond-mat.soft↗

arXiv2025

Domain-aware Category-level Geometry Learning Segmentation for 3D Point Clouds

Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global geometric patterns in point clouds while ignoring the category-level distribution and alignment. In this paper, a category-level geometry learning framework is proposed to explore the domain-invariant geometric features for domain generalized 3D semantic segmentation. Specifically, Category-level Geometry Embedding (CGE) is proposed to perceive the fine-grained geometric properties of point cloud features, which constructs the geometric properties of each class and couples geometric embedding to semantic learning. Secondly, Geometric Consistent Learning (GCL) is proposed to simulate the latent 3D distribution and align the category-level geometric embeddings, allowing the model to focus on the geometric invariant information to improve generalization. Experimental results verify the effectiveness of the proposed method, which has very competitive segmentation accuracy compared with the state-of-the-art domain generalized point cloud methods.

cs.CV↗

arXiv2025

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation

Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online data distribution for data augmentation. However, generated data still exhibits a gap with the online data, limiting overall performance. To address this, we propose a new data augmentation approach, Classifier-Free Diffusion Generation (CFDG). Without introducing additional classifier training overhead, CFDG leverages classifier-free guidance diffusion to significantly enhance the generation quality of offline and online data with different distributions. Additionally, it employs a reweighting method to enable more generated data to align with the online data, enhancing performance while maintaining the agent's stability. Experimental results show that CFDG outperforms replaying the two data types or using a standard diffusion model to generate new data. Our method is versatile and can be integrated with existing offline-to-online RL algorithms. By implementing CFDG to popular methods IQL, PEX and APL, we achieve a notable 15% average improvement in empirical performance on the D4RL benchmark such as MuJoCo and AntMaze.

cs.LG↗

arXiv2025

Unified Linear Parametric Map Modeling and Perception-aware Trajectory Planning for Mobile Robotics

Autonomous navigation in mobile robots, reliant on perception and planning, faces major hurdles in large-scale, complex environments. These include heavy computational burdens for mapping, sensor occlusion failures for UAVs, and traversal challenges on irregular terrain for UGVs, all compounded by a lack of perception-aware strategies. To address these challenges, we introduce Random Mapping and Random Projection (RMRP). This method constructs a lightweight linear parametric map by first mapping data to a high-dimensional space, followed by a sparse random projection for dimensionality reduction. Our novel Residual Energy Preservation Theorem provides theoretical guarantees for this process, ensuring critical geometric properties are preserved. Based on this map, we propose the RPATR (Robust Perception-Aware Trajectory Planner) framework. For UAVs, our method unifies grid and Euclidean Signed Distance Field (ESDF) maps. The front-end uses an analytical occupancy gradient to refine initial paths for safety and smoothness, while the back-end uses a closed-form ESDF for trajectory optimization. Leveraging the trained RMRP model's generalization, the planner predicts unobserved areas for proactive navigation. For UGVs, the model characterizes terrain and provides closed-form gradients, enabling online planning to circumvent large holes. Validated in diverse scenarios, our framework demonstrates superior mapping performance in time, memory, and accuracy, and enables computationally efficient, safe navigation for high-speed UAVs and UGVs. The code will be released to foster community collaboration.

cs.RO↗

arXiv2025

McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models

As large language models (LLMs) are increasingly applied to various NLP tasks, their inherent biases are gradually disclosed. Therefore, measuring biases in LLMs is crucial to mitigate its ethical risks. However, most existing bias evaluation datasets focus on English and North American culture, and their bias categories are not fully applicable to other cultures. The datasets grounded in the Chinese language and culture are scarce. More importantly, these datasets usually only support single evaluation tasks and cannot evaluate the bias from multiple aspects in LLMs. To address these issues, we present a Multi-task Chinese Bias Evaluation Benchmark (McBE) that includes 4,077 bias evaluation instances, covering 12 single bias categories, 82 subcategories and introducing 5 evaluation tasks, providing extensive category coverage, content diversity, and measuring comprehensiveness. Additionally, we evaluate several popular LLMs from different series and with parameter sizes. In general, all these LLMs demonstrated varying degrees of bias. We conduct an in-depth analysis of results, offering novel insights into bias in LLMs.

cs.CL↗

arXiv2025

CUTHERMO: Understanding GPU Memory Inefficiencies with Heat Map Profiling

GPUs have become indispensable in high-performance computing, machine learning, and many other domains. Efficiently utilizing the memory subsystem on GPUs is critical for maximizing computing power through massive parallelism. Analyzing memory access patterns has proven to be an effective method for understanding memory bottlenecks in applications. However, comprehensive runtime and fine-grained memory profiling support is lacking on GPU architectures. In this work, we introduce cuThermo, a lightweight and practical profiling tool for GPU memory analysis. It operates on GPU binaries without requiring any modifications to hardware, operating system, or application source code. Given a CUDA application, cuThermo identifies memory inefficiencies at runtime via a heat map based on distinct visited warp counts to represent word-sector-level data sharing and provides optimization guidance in performance tuning iterations. Through our experiments on six applications, we identified five memory access patterns that are portable across different GPU architectures. By evaluating optimization on two GPUs, cuThermo achieves up to $721.79\%$ performance improvement.

cs.DC↗

arXiv2025

High-throughput Super-Resolution Imaging Chip based on Miniaturized Full-frequency Encoded-illumination

A miniaturized full-frequency encoded illumination (mini-FEI) chip is presented for high-throughput super-resolution imaging using the spatial frequency shift (SFS) effect. A tunable full SFS scheme is achieved through propagating and evanescent wave. The multi-illumination modes are precisely and flexibly modulated by an encoded LED array. The light travels to the sample via a set of prisms, producing the super-resolution images with high signal-to-noise ratio (SNR). Mini-FEI super-resolution imaging reaches a resolution of 333 nm (~λ/4NA), close to the theoretical limit, while maintaining a large field of view (FOV) of ~1 mm2. The method is validated on label-free samples including USAF Target, Star Target, and onion root tip cells, all of which could be successfully reconstructed. Through the introduction of integrated LED arrays for evanescent wave excitation, expensive laser systems can be avoided and the system significantly miniaturized. The mini-FEI super-resolution imaging chip is simple and cost effective to fabricate and can be used in conjunction with any inverted brightfield microscope frame and thus has great potential for widespread use in scientific and industrial research environments.

physics.optics↗

arXiv2025

3D Active Metric-Semantic SLAM

In this letter, we address the problem of exploration and metric-semantic mapping of multi-floor GPS-denied indoor environments using Size Weight and Power (SWaP) constrained aerial robots. Most previous work in exploration assumes that robot localization is solved. However, neglecting the state uncertainty of the agent can ultimately lead to cascading errors both in the resulting map and in the state of the agent itself. Furthermore, actions that reduce localization errors may be at direct odds with the exploration task. We propose a framework that balances the efficiency of exploration with actions that reduce the state uncertainty of the agent. In particular, our algorithmic approach for active metric-semantic SLAM is built upon sparse information abstracted from raw problem data, to make it suitable for SWaP-constrained robots. Furthermore, we integrate this framework within a fully autonomous aerial robotic system that achieves autonomous exploration in cluttered, 3D environments. From extensive real-world experiments, we showed that by including Semantic Loop Closure (SLC), we can reduce the robot pose estimation errors by over 90% in translation and approximately 75% in yaw, and the uncertainties in pose estimates and semantic maps by over 70% and 65%, respectively. Although discussed in the context of indoor multi-floor exploration, our system can be used for various other applications, such as infrastructure inspection and precision agriculture where reliable GPS data may not be available.

cs.RO↗

arXiv2025

Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics

Motion forecasting for on-road traffic agents presents both a significant challenge and a critical necessity for ensuring safety in autonomous driving systems. In contrast to most existing data-driven approaches that directly predict future trajectories, we rethink this task from a planning perspective, advocating a "First Reasoning, Then Forecasting" strategy that explicitly incorporates behavior intentions as spatial guidance for trajectory prediction. To achieve this, we introduce an interpretable, reward-driven intention reasoner grounded in a novel query-centric Inverse Reinforcement Learning (IRL) scheme. Our method first encodes traffic agents and scene elements into a unified vectorized representation, then aggregates contextual features through a query-centric paradigm. This enables the derivation of a reward distribution, a compact yet informative representation of the target agent's behavior within the given scene context via IRL. Guided by this reward heuristic, we perform policy rollouts to reason about multiple plausible intentions, providing valuable priors for subsequent trajectory generation. Finally, we develop a hierarchical DETR-like decoder integrated with bidirectional selective state space models to produce accurate future trajectories along with their associated probabilities. Extensive experiments on the large-scale Argoverse and nuScenes motion forecasting datasets demonstrate that our approach significantly enhances trajectory prediction confidence, achieving highly competitive performance relative to state-of-the-art methods.

cs.CV↗

arXiv2025

ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models

Video understanding plays a vital role in bridging low-level visual signals with high-level cognitive reasoning, and is fundamental to applications such as autonomous driving, embodied AI, and the broader pursuit of AGI. The rapid development of large language models (LLMs), particularly those utilizing Chain-of-Thought (CoT) technology, has significantly advanced video reasoning capabilities. However, current approaches primarily depend on textual information for reasoning, overlooking the visual modality in the actual video reasoning process. In contrast, humans naturally re-examine visual content while reasoning. Motivated by this, we introduce a novel video reasoning paradigm: Video-Text Interleaved CoT (ViTCoT), which facilitates more intuitive and cognitively aligned reasoning. To the end, first, we construct the Video-Text Interleaved Benchmark (ViTIB), which is created using MLLMs for key-video selection and manually verified. Furthermore, we extensively explore the potential of the ViTCoT paradigm in the video understanding field. Extensive experiments demonstrate that ViTCoT significantly enhances performance compared to the traditional text-only CoT paradigm and effectively activates more neuron values in MLLMs.

cs.CV↗