arXiv subjects

Chao Xu

Publications and source records attributed to Chao Xu.

At least 127 records · Page 7Linked to original sources

arXiv2025

Ground-Effect-Aware Modeling and Control for Multicopters

The ground effect on multicopters introduces several challenges, such as control errors caused by additional lift, oscillations that may occur during near-ground flight due to external torques, and the influence of ground airflow on models such as the rotor drag and the mixing matrix. This article collects and analyzes the dynamics data of near-ground multicopter flight through various methods, including force measurement platforms and real-world flights. For the first time, we summarize the mathematical model of the external torque of multicopters under ground effect. The influence of ground airflow on rotor drag and the mixing matrix is also verified through adequate experimentation and analysis. Through simplification and derivation, the differential flatness of the multicopter's dynamic model under ground effect is confirmed. To mitigate the influence of these disturbance models on control, we propose a control method that combines dynamic inverse and disturbance models, ensuring consistent control effectiveness at both high and low altitudes. In this method, the additional thrust and variations in rotor drag under ground effect are both considered and compensated through feedforward models. The leveling torque of ground effect can be equivalently represented as variations in the center of gravity and the moment of inertia. In this way, the leveling torque does not explicitly appear in the dynamic model. The final experimental results show that the method proposed in this paper reduces the control error (RMSE) by \textbf{45.3\%}. Please check the supplementary material at: https://github.com/ZJU-FAST-Lab/Ground-effect-controller.

cs.RO↗

arXiv2025

Diagnosing 2D symmetry protected topological states via mixed state anomaly

Symmetry-protected topological (SPT) phases are short-range entangled quantum states characterized by anomalous edge behavior, a manifestation of the bulk-boundary correspondence for topological phases. Moreover, the Li-Haldane conjecture posits that the entanglement spectrum exhibits the same anomaly as the physical edge spectrum, thereby serving as an entanglement-based fingerprint for identifying topological phases. In this work, we extend the entanglement-based diagnostic tools by demonstrating that the edge anomaly is manifested not only in the entanglement spectrum but also in the reduced density matrix itself, a phenomenon we refer to as the mixed state anomaly. Focusing on the two-dimensional $\mathbb{Z}_2$ SPT phase, we show that this anomaly is subtly encoded in symmetry-twisted mixed states, leading to a topological contribution to the disorder parameter beyond the area law, as well as a spontaneous-symmetry-breaking type long-range order when time reversal symmetry is present.

cond-mat.str-el↗

arXiv2025

DiC: Rethinking Conv3x3 Designs in Diffusion Models

Diffusion models have shown exceptional performance in visual generation tasks. Recently, these models have shifted from traditional U-Shaped CNN-Attention hybrid structures to fully transformer-based isotropic architectures. While these transformers exhibit strong scalability and performance, their reliance on complicated self-attention operation results in slow inference speeds. Contrary to these works, we rethink one of the simplest yet fastest module in deep learning, 3x3 Convolution, to construct a scaled-up purely convolutional diffusion model. We first discover that an Encoder-Decoder Hourglass design outperforms scalable isotropic architectures for Conv3x3, but still under-performing our expectation. Further improving the architecture, we introduce sparse skip connections to reduce redundancy and improve scalability. Based on the architecture, we introduce conditioning improvements including stage-specific embeddings, mid-block condition injection, and conditional gating. These improvements lead to our proposed Diffusion CNN (DiC), which serves as a swift yet competitive diffusion architecture baseline. Experiments on various scales and settings show that DiC surpasses existing diffusion transformers by considerable margins in terms of performance while keeping a good speed advantage. Project page: https://github.com/YuchuanTian/DiC

cs.CV↗

arXiv2025

Universal Trajectory Optimization Framework for Differential Drive Robot Class

Differential drive robots are widely used in various scenarios thanks to their straightforward principle, from household service robots to disaster response field robots. There are several types of driving mechanisms for real-world applications, including two-wheeled, four-wheeled skid-steering, tracked robots, and so on. The differences in the driving mechanisms usually require specific kinematic modeling when precise control is desired. Furthermore, the nonholonomic dynamics and possible lateral slip lead to different degrees of difficulty in getting feasible and high-quality trajectories. Therefore, a comprehensive trajectory optimization framework to compute trajectories efficiently for various kinds of differential drive robots is highly desirable. In this paper, we propose a universal trajectory optimization framework that can be applied to differential drive robots, enabling the generation of high-quality trajectories within a restricted computational timeframe. We introduce a novel trajectory representation based on polynomial parameterization of motion states or their integrals, such as angular and linear velocities, which inherently matches the robots' motion to the control principle. The trajectory optimization problem is formulated to minimize complexity while prioritizing safety and operational efficiency. We then build a full-stack autonomous planning and control system to demonstrate its feasibility and robustness. We conduct extensive simulations and real-world testing in crowded environments with three kinds of differential drive robots to validate the effectiveness of our approach.

cs.RO↗

arXiv2025

Graph Neural Network Aided Detection for the Multi-User Multi-Dimensional Index Modulated Uplink

The concept of Compressed Sensing-aided Space-Frequency Index Modulation (CS-SFIM) is conceived for the Large-Scale Multi-User Multiple-Input Multiple-Output Uplink (LS-MU-MIMO-UL) of Next-Generation (NG) networks. Explicitly, in CS-SFIM, the information bits are mapped to both spatial- and frequency-domain indices, where we treat the activation patterns of the transmit antennas and of the subcarriers separately. Serving a large number of users in an MU-MIMO-UL system leads to substantial Multi-User Interference (MUI). Hence, we design the Space-Frequency (SF) domain matrix as a joint factor graph, where the Approximate Message Passing (AMP) and Expectation Propagation (EP) based MU detectors can be utilized. In the LS-MU-MIMO-UL scenario considered, the proposed system uses optimal Maximum Likelihood (ML) and Minimum Mean Square Error (MMSE) detectors as benchmarks for comparison with the proposed MP-based detectors. These MP-based detectors significantly reduce the detection complexity compared to ML detection, making the design eminently suitable for LS-MU scenarios. To further reduce the detection complexity and improve the detection performance, we propose a pair of Graph Neural Network (GNN) based detectors, which rely on the orthogonal AMP (OAMP) and on the EP algorithm, which we refer to as the GNN-AMP and GEPNet detectors, respectively. The GEPNet detector maximizes the detection performance, while the GNN-AMP detector strikes a performance versus complexity trade-off. The GNN is trained for a single system configuration and yet it can be used for any number of users in the system. The simulation results show that the GNN-based detector approaches the ML performance in various configurations.

eess.SP↗

arXiv2025

AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era

Animation has gained significant interest in the recent film and TV industry. Despite the success of advanced video generation models like Sora, Kling, and CogVideoX in generating natural videos, they lack the same effectiveness in handling animation videos. Evaluating animation video generation is also a great challenge due to its unique artist styles, violating the laws of physics and exaggerated motions. In this paper, we present a comprehensive system, AniSora, designed for animation video generation, which includes a data processing pipeline, a controllable generation model, and an evaluation benchmark. Supported by the data processing pipeline with over 10M high-quality data, the generation model incorporates a spatiotemporal mask module to facilitate key animation production functions such as image-to-video generation, frame interpolation, and localized image-guided animation. We also collect an evaluation benchmark of 948 various animation videos, with specifically developed metrics for animation video generation. Our entire project is publicly available on https://github.com/bilibili/Index-anisora/tree/main.

cs.GR↗

arXiv2025

PSC: Extending Context Window of Large Language Models via Phase Shift Calibration

Rotary Position Embedding (RoPE) is an efficient position encoding approach and is widely utilized in numerous large language models (LLMs). Recently, a lot of methods have been put forward to further expand the context window based on RoPE. The core concept of those methods is to predefine or search for a set of factors to rescale the base frequencies of RoPE. Nevertheless, it is quite a challenge for existing methods to predefine an optimal factor due to the exponential search space. In view of this, we introduce PSC (Phase Shift Calibration), a small module for calibrating the frequencies predefined by existing methods. With the employment of PSC, we demonstrate that many existing methods can be further enhanced, like PI, YaRN, and LongRoPE. We conducted extensive experiments across multiple models and tasks. The results demonstrate that (1) when PSC is enabled, the comparative reductions in perplexity increase as the context window size is varied from 16k, to 32k, and up to 64k. (2) Our approach is broadly applicable and exhibits robustness across a variety of models and tasks. The code can be found at https://github.com/WNQzhu/PSC.

cs.CL↗

arXiv2025

Learning to Deblur Polarized Images

A polarization camera can capture four linear polarized images with different polarizer angles in a single shot, which is useful in polarization-based vision applications since the degree of linear polarization (DoLP) and the angle of linear polarization (AoLP) can be directly computed from the captured polarized images. However, since the on-chip micro-polarizers block part of the light so that the sensor often requires a longer exposure time, the captured polarized images are prone to motion blur caused by camera shakes, leading to noticeable degradation in the computed DoLP and AoLP. Deblurring methods for conventional images often show degraded performance when handling the polarized images since they only focus on deblurring without considering the polarization constraints. In this paper, we propose a polarized image deblurring pipeline to solve the problem in a polarization-aware manner by adopting a divide-and-conquer strategy to explicitly decompose the problem into two less ill-posed sub-problems, and design a two-stage neural network to handle the two sub-problems respectively. Experimental results show that our method achieves state-of-the-art performance on both synthetic and real-world images, and can improve the performance of polarization-based vision applications such as image dehazing and reflection removal.

cs.CV↗

arXiv2025

Task-oriented Age of Information for Remote Inference with Hybrid Language Models

Large Language Models (LLMs) have revolutionized the field of artificial intelligence (AI) through their advanced reasoning capabilities, but their extensive parameter sets introduce significant inference latency, posing a challenge to ensure the timeliness of inference results. While Small Language Models (SLMs) offer faster inference speeds with fewer parameters, they often compromise accuracy on complex tasks. This study proposes a novel remote inference system comprising a user, a sensor, and an edge server that integrates both model types alongside a decision maker. The system dynamically determines the resolution of images transmitted by the sensor and routes inference tasks to either an SLM or LLM to optimize performance. The key objective is to minimize the Task-oriented Age of Information (TAoI) by jointly considering the accuracy and timeliness of the inference task. Due to the non-uniform transmission time and inference time, we formulate this problem as a Semi-Markov Decision Process (SMDP). By converting the SMDP to an equivalent Markov decision process, we prove that the optimal control policy follows a threshold-based structure. We further develop a relative policy iteration algorithm leveraging this threshold property. Simulation results demonstrate that our proposed optimal policy significantly outperforms baseline approaches in managing the accuracy-timeliness trade-off.

cs.IT↗

arXiv2025

LAM: Large Avatar Model for One-shot Animatable Gaussian Head

We present LAM, an innovative Large Avatar Model for animatable Gaussian head reconstruction from a single image. Unlike previous methods that require extensive training on captured video sequences or rely on auxiliary neural networks for animation and rendering during inference, our approach generates Gaussian heads that are immediately animatable and renderable. Specifically, LAM creates an animatable Gaussian head in a single forward pass, enabling reenactment and rendering without additional networks or post-processing steps. This capability allows for seamless integration into existing rendering pipelines, ensuring real-time animation and rendering across a wide range of platforms, including mobile phones. The centerpiece of our framework is the canonical Gaussian attributes generator, which utilizes FLAME canonical points as queries. These points interact with multi-scale image features through a Transformer to accurately predict Gaussian attributes in the canonical space. The reconstructed canonical Gaussian avatar can then be animated utilizing standard linear blend skinning (LBS) with corrective blendshapes as the FLAME model did and rendered in real-time on various platforms. Our experimental results demonstrate that LAM outperforms state-of-the-art methods on existing benchmarks. Our code and video are available at https://aigc3d.github.io/projects/LAM/

cs.CV↗

arXiv2025

Accelerated Distributed Aggregative Optimization

This paper delves into the investigation of a distributed aggregative optimization problem within a network. In this scenario, each agent possesses its own local cost function, which relies not only on the local state variable but also on an aggregated function of state variables from all agents. To expedite the optimization process, we amalgamate the heavy ball and Nesterovs accelerated method with distributed aggregative gradient tracking, resulting in the proposal of two innovative algorithms, aimed at resolving the distributed aggregative optimization problem. Our analysis demonstrates that the proposed algorithms can converge to an optimal solution at a global linear convergence rate when the objective function is strongly convex with the Lipschitz-continuous gradient, and when the parameters (e.g., step size and momentum coefficients) are chosen within specific ranges. Additionally, we present several numerical experiments to verify the effectiveness, robustness and superiority of our proposed algorithms.

math.OC↗

arXiv2025

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping

Diffusion Transformer (DiT) has now become the preferred choice for building image generation models due to its great generation capability. Unlike previous convolution-based UNet models, DiT is purely composed of a stack of transformer blocks, which renders DiT excellent in scalability like large language models. However, the growing model size and multi-step sampling paradigm bring about considerable pressure on deployment and inference. In this work, we propose a post-training quantization framework tailored for Diffusion Transforms to tackle these challenges. We firstly locate that the quantization difficulty of DiT mainly originates from the time-dependent channel-specific outliers. We propose a timestep-aware shift-and-scale strategy to smooth the activation distribution to reduce the quantization error. Secondly, based on the observation that activations of adjacent timesteps have similar distributions, we utilize a hierarchical clustering scheme to divide the denoising timesteps into multiple groups. We further design a re-parameterization scheme which absorbs the quantization parameters into nearby module to avoid redundant computations. Comprehensive experiments demonstrate that out PTQ method successfully quantize the Diffusion Transformer into 8-bit weight and 8-bit activation (W8A8) with state-of-the-art FiD score. And our method can further quantize DiT model into 4-bit weight and 8-bit activation (W4A8) without sacrificing generation quality.

cs.CV↗

arXiv2025

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations

Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems. Despite recent progress, current document parsing methods have not been fairly and comprehensively evaluated due to the narrow coverage of document types and the simplified, unrealistic evaluation procedures in existing benchmarks. To address these gaps, we introduce OmniDocBench, a novel benchmark featuring high-quality annotations across nine document sources, including academic papers, textbooks, and more challenging cases such as handwritten notes and densely typeset newspapers. OmniDocBench supports flexible, multi-level evaluations--ranging from an end-to-end assessment to the task-specific and attribute--based analysis using 19 layout categories and 15 attribute labels. We conduct a thorough evaluation of both pipeline-based methods and end-to-end vision-language models, revealing their strengths and weaknesses across different document types. OmniDocBench sets a new standard for the fair, diverse, and fine-grained evaluation in document parsing. Dataset and code are available at https://github.com/opendatalab/OmniDocBench.

cs.CV↗

arXiv2025

SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded sub-images with skip tokens, and simplifying multi-stage training into a one-stage all-in-one paradigm. To fully unleash the potential of MLLMs, we assemble a comprehensive multi-domain and multimodal dataset covering publicly available resources in language, vision, and vision-language tasks. We further enrich this collection with our curated OCR intensive and Set-of-Mark datasets, extending the diversity and generality. By training over different base LLMs including TinyLlama1.1B, InternLM2-7B, LLaMA2-13B, and Mixtral8x7B, we obtain a spectrum of MLLMs that vary in parameter size and multilingual capabilities. Comprehensive benchmarking reveals a strong correlation between the multi-modal performance with the data and parameter scales. Code and models are released at https://github.com/Alpha-VLLM/LLaMA2-Accessory

cs.CV↗

arXiv2025

Fast Iterative Region Inflation for Computing Large 2-D/3-D Convex Regions of Obstacle-Free Space

Convex polytopes have compact representations and exhibit convexity, which makes them suitable for abstracting obstacle-free spaces from various environments. Existing generation methods struggle with balancing high-quality output and efficiency. Moreover, another crucial requirement for convex polytopes to accurately contain certain seed point sets, such as a robot or a front-end path, is proposed in various tasks, which we refer to as manageability. In this paper, we propose Fast Iterative Regional Inflation (FIRI) to generate high-quality convex polytope while ensuring efficiency and manageability simultaneously. FIRI consists of two iteratively executed submodules: Restrictive Inflation (RsI) and Maximum Volume Inscribed Ellipsoid (MVIE) computation. By explicitly incorporating constraints that include the seed point set, RsI guarantees manageability. Meanwhile, iterative MVIE optimization ensures high-quality result through monotonic volume bound improvement.In terms of efficiency, we design methods tailored to the low-dimensional and multi-constrained nature of both modules, resulting in orders of magnitude improvement compared to generic solvers. Notably, in 2-D MVIE, we present the first linear-complexity analytical algorithm for maximum area inscribed ellipse, further enhancing the performance in 2-D cases. Extensive benchmarks conducted against state-of-the-art methods validate the superior performance of FIRI in terms of quality, manageability, and efficiency. Furthermore, various real-world applications showcase the generality and practicality of FIRI.

cs.RO↗

arXiv2025

PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation

Vision-and-language navigation (VLN) tasks require agents to navigate three-dimensional environments guided by natural language instructions, offering substantial potential for diverse applications. However, the scarcity of training data impedes progress in this field. This paper introduces PanoGen++, a novel framework that addresses this limitation by generating varied and pertinent panoramic environments for VLN tasks. PanoGen++ incorporates pre-trained diffusion models with domain-specific fine-tuning, employing parameter-efficient techniques such as low-rank adaptation to minimize computational costs. We investigate two settings for environment generation: masked image inpainting and recursive image outpainting. The former maximizes novel environment creation by inpainting masked regions based on textual descriptions, while the latter facilitates agents' learning of spatial relationships within panoramas. Empirical evaluations on room-to-room (R2R), room-for-room (R4R), and cooperative vision-and-dialog navigation (CVDN) datasets reveal significant performance enhancements: a 2.44% increase in success rate on the R2R test leaderboard, a 0.63% improvement on the R4R validation unseen set, and a 0.75-meter enhancement in goal progress on the CVDN validation unseen set. PanoGen++ augments the diversity and relevance of training environments, resulting in improved generalization and efficacy in VLN tasks.

cs.CV↗

arXiv2025

Efficient Trajectory Generation Based on Traversable Planes in 3D Complex Architectural Spaces

With the increasing integration of robots into human life, their role in architectural spaces where people spend most of their time has become more prominent. While motion capabilities and accurate localization for automated robots have rapidly developed, the challenge remains to generate efficient, smooth, comprehensive, and high-quality trajectories in these areas. In this paper, we propose a novel efficient planner for ground robots to autonomously navigate in large complex multi-layered architectural spaces. Considering that traversable regions typically include ground, slopes, and stairs, which are planar or nearly planar structures, we simplify the problem to navigation within and between complex intersecting planes. We first extract traversable planes from 3D point clouds through segmenting, merging, classifying, and connecting to build a plane-graph, which is lightweight but fully represents the traversable regions. We then build a trajectory optimization based on motion state trajectory and fully consider special constraints when crossing multi-layer planes to maximize the robot's maneuverability. We conduct experiments in simulated environments and test on a CubeTrack robot in real-world scenarios, validating the method's effectiveness and practicality.

cs.RO↗

arXiv2025

Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition

Video-to-audio generation is essential for synthesizing realistic audio tracks that synchronize effectively with silent videos. Following the perspective of extracting essential signals from videos that can precisely control the mature text-to-audio generative diffusion models, this paper presents how to balance the representation of mel-spectrograms in terms of completeness and complexity through a new approach called Mel Quantization-Continuum Decomposition (Mel-QCD). We decompose the mel-spectrogram into three distinct types of signals, employing quantization or continuity to them, we can effectively predict them from video by a devised video-to-all (V2X) predictor. Then, the predicted signals are recomposed and fed into a ControlNet, along with a textual inversion design, to control the audio generation process. Our proposed Mel-QCD method demonstrates state-of-the-art performance across eight metrics, evaluating dimensions such as quality, synchronization, and semantic consistency. Our codes and demos will be released at \href{Website}{https://wjc2830.github.io/MelQCD/}.

cs.SD↗