arXiv subjects

Chao Xu

Publications and source records attributed to Chao Xu.

At least 163 records · Page 9Linked to original sources

arXiv2024

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers

Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance and good scalability; but meanwhile, the abandonment of U-Net by DiTs and their following improvements is worth rethinking. To this end, we conduct a simple toy experiment by comparing a U-Net architectured DiT with an isotropic one. It turns out that the U-Net architecture only gain a slight advantage amid the U-Net inductive bias, indicating potential redundancies within the U-Net-style DiT. Inspired by the discovery that U-Net backbone features are low-frequency-dominated, we perform token downsampling on the query-key-value tuple for self-attention that bring further improvements despite a considerable amount of reduction in computation. Based on self-attention with downsampled tokens, we propose a series of U-shaped DiTs (U-DiTs) in the paper and conduct extensive experiments to demonstrate the extraordinary performance of U-DiT models. The proposed U-DiT could outperform DiT-XL/2 with only 1/6 of its computation cost. Codes are available at https://github.com/YuchuanTian/U-DiT.

cs.CV↗

arXiv2024

AuditWen:An Open-Source Large Language Model for Audit

Intelligent auditing represents a crucial advancement in modern audit practices, enhancing both the quality and efficiency of audits within the realm of artificial intelligence. With the rise of large language model (LLM), there is enormous potential for intelligent models to contribute to audit domain. However, general LLMs applied in audit domain face the challenges of lacking specialized knowledge and the presence of data biases. To overcome these challenges, this study introduces AuditWen, an open-source audit LLM by fine-tuning Qwen with constructing instruction data from audit domain. We first outline the application scenarios for LLMs in the audit and extract requirements that shape the development of LLMs tailored for audit purposes. We then propose an audit LLM, called AuditWen, by fine-tuning Qwen with constructing 28k instruction dataset from 15 audit tasks and 3 layers. In evaluation stage, we proposed a benchmark with 3k instructions that covers a set of critical audit tasks derived from the application scenarios. With the benchmark, we compare AuditWen with other existing LLMs from information extraction, question answering and document generation. The experimental results demonstrate superior performance of AuditWen both in question understanding and answer generation, making it an immediately valuable tool for audit.

cs.CL↗

arXiv2024

TeX-NeRF: Neural Radiance Fields from Pseudo-TeX Vision

Neural radiance fields (NeRF) has gained significant attention for its exceptional visual effects. However, most existing NeRF methods reconstruct 3D scenes from RGB images captured by visible light cameras. In practical scenarios like darkness, low light, or bad weather, visible light cameras become ineffective. Therefore, we propose TeX-NeRF, a 3D reconstruction method using only infrared images, which introduces the object material emissivity as a priori, preprocesses the infrared images using Pseudo-TeX vision, and maps the temperatures (T), emissivities (e), and textures (X) of the scene into the saturation (S), hue (H), and value (V) channels of the HSV color space, respectively. Novel view synthesis using the processed images has yielded excellent results. Additionally, we introduce 3D-TeX Datasets, the first dataset comprising infrared images and their corresponding Pseudo-TeX vision images. Experiments demonstrate that our method not only matches the quality of scene reconstruction achieved with high-quality RGB images but also provides accurate temperature estimations for objects in the scene.

cs.CV↗

arXiv2024

MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition

Applying large-scale vision-language pre-trained models like CLIP to few-shot action recognition (FSAR) can significantly enhance both performance and efficiency. While several studies have recognized this advantage, most of them resort to full-parameter fine-tuning to make CLIP's visual encoder adapt to the FSAR data, which not only costs high computations but also overlooks the potential of the visual encoder to engage in temporal modeling and focus on targeted semantics directly. To tackle these issues, we introduce MA-FSAR, a framework that employs the Parameter-Efficient Fine-Tuning (PEFT) technique to enhance the CLIP visual encoder in terms of action-related temporal and semantic representations. Our solution involves a Fine-grained Multimodal Adaptation, which is different from the previous attempts of PEFT in regular action recognition. Specifically, we first insert a Global Temporal Adaptation that only receives the class token to capture global motion cues efficiently. Then these outputs integrate with visual tokens to enhance local temporal dynamics by a Local Multimodal Adaptation, which incorporates text features unique to the FSAR support set branch to highlight fine-grained semantics related to actions. In addition to these token-level designs, we propose a prototype-level text-guided construction module to further enrich the temporal and semantic characteristics of video prototypes. Extensive experiments demonstrate our superior performance in various tasks using minor trainable parameters.

cs.CV↗

arXiv2024

Nonsymmorphic spin-space cubic groups and SU(2)$_1$ conformal invariance in one-dimensional spin-1/2 models

Recently, extended gapless phases with emergent SU(2)$_1$ conformal invariance occupying finite regions in the phase diagrams have been found in one-dimensional spin-1/2 models with nonsymmorphic $O_h$ symmetry groups. In this work, we investigate the question of whether the conditions for emergent SU(2)$_1$ invariance can be loosened. We find that besides the nonsymmorphic $O_h$ group, the other four smaller nonsymmorphic cubic groups including $O$, $T_h$, $T_d$ and $T$ can also give rise to emergent SU(2)$_1$ invariance. Minimal spin-1/2 models having these nonsymmorphic cubic groups as symmetry groups are constructed, and numerical evidences for the emergent SU(2)$_1$ invariance are provided. Our work is useful for understanding gapless phases in one-dimensional spin systems with nonsymmorphic symmetries.

cond-mat.str-el↗

arXiv2024

MinerU: An Open-Source Solution for Precise Document Content Extraction

Document content analysis has been a crucial research area in computer vision. Despite significant advancements in methods such as OCR, layout detection, and formula recognition, existing open-source solutions struggle to consistently deliver high-quality content extraction due to the diversity in document types and content. To address these challenges, we present MinerU, an open-source solution for high-precision document content extraction. MinerU leverages the sophisticated PDF-Extract-Kit models to extract content from diverse documents effectively and employs finely-tuned preprocessing and postprocessing rules to ensure the accuracy of the final results. Experimental results demonstrate that MinerU consistently achieves high performance across various document types, significantly enhancing the quality and consistency of content extraction. The MinerU open-source project is available at https://github.com/opendatalab/MinerU.

cs.CV↗

arXiv2024

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models

Scientific documents record research findings and valuable human knowledge, comprising a vast corpus of high-quality data. Leveraging multi-modality data extracted from these documents and assessing large models' abilities to handle scientific document-oriented tasks is therefore meaningful. Despite promising advancements, large models still perform poorly on multi-page scientific document extraction and understanding tasks, and their capacity to process within-document data formats such as charts and equations remains under-explored. To address these issues, we present DocGenome, a structured document benchmark constructed by annotating 500K scientific documents from 153 disciplines in the arXiv open-access community, using our custom auto-labeling pipeline. DocGenome features four key characteristics: 1) Completeness: It is the first dataset to structure data from all modalities including 13 layout attributes along with their LaTeX source codes. 2) Logicality: It provides 6 logical relationships between different entities within each scientific document. 3) Diversity: It covers various document-oriented tasks, including document classification, visual grounding, document layout detection, document transformation, open-ended single-page QA and multi-page QA. 4) Correctness: It undergoes rigorous quality control checks conducted by a specialized team. We conduct extensive experiments to demonstrate the advantages of DocGenome and objectively evaluate the performance of large models on our benchmark.

cs.CV↗

arXiv2024

UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition

The paper introduces the UniMER dataset, marking the first study on Mathematical Expression Recognition (MER) targeting complex real-world scenarios. The UniMER dataset includes a large-scale training set, UniMER-1M, which offers unprecedented scale and diversity with one million training instances to train high-quality, robust models. Additionally, UniMER features a meticulously designed, diverse test set, UniMER-Test, which covers a variety of formula distributions found in real-world scenarios, providing a more comprehensive and fair evaluation. To better utilize the UniMER dataset, the paper proposes a Universal Mathematical Expression Recognition Network (UniMERNet), tailored to the characteristics of formula recognition. UniMERNet consists of a carefully designed encoder that incorporates detail-aware and local context features, and an optimized decoder for accelerated performance. Extensive experiments conducted using the UniMER-1M dataset and UniMERNet demonstrate that training on the large-scale UniMER-1M dataset can produce a more generalizable formula recognition model, significantly outperforming all previous datasets. Furthermore, the introduction of UniMERNet enhances the model's performance in formula recognition, achieving higher accuracy and speeds. All data, models, and code are available at https://github.com/opendatalab/UniMERNet.

cs.CV↗

arXiv2024

SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views

Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that may not align with users' expectations. In this paper, we explore an important scenario in which the input consists of one or a few unposed 2D images of a single object, with little or no overlap. We propose a novel method, SpaRP, to reconstruct a 3D textured mesh and estimate the relative camera poses for these sparse-view images. SpaRP distills knowledge from 2D diffusion models and finetunes them to implicitly deduce the 3D spatial relationships between the sparse views. The diffusion model is trained to jointly predict surrogate representations for camera poses and multi-view images of the object under known poses, integrating all information from the input sparse views. These predictions are then leveraged to accomplish 3D reconstruction and pose estimation, and the reconstructed 3D model can be used to further refine the camera poses of input views. Through extensive experiments on three datasets, we demonstrate that our method not only significantly outperforms baseline methods in terms of 3D reconstruction quality and pose prediction accuracy but also exhibits strong efficiency. It requires only about 20 seconds to produce a textured mesh and camera poses for the input views. Project page: https://chaoxu.xyz/sparp.

cs.CV↗

arXiv2024

MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model

Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruction model that explicitly leverages 3D native structure, input guidance, and training supervision. Specifically, instead of using a triplane representation, we store features in 3D sparse voxels and combine transformers with 3D convolutions to leverage an explicit 3D structure and projective bias. In addition to sparse-view RGB input, we require the network to take input and generate corresponding normal maps. The input normal maps can be predicted by 2D diffusion models, significantly aiding in the guidance and refinement of the geometry's learning. Moreover, by combining Signed Distance Function (SDF) supervision with surface rendering, we directly learn to generate high-quality meshes without the need for complex multi-stage training processes. By incorporating these explicit 3D biases, MeshFormer can be trained efficiently and deliver high-quality textured meshes with fine-grained geometric details. It can also be integrated with 2D diffusion models to enable fast single-image-to-3D and text-to-3D tasks. Project page: https://meshformer3d.github.io

cs.CV↗

arXiv2024

Unveiling Correlated Two-dimensional Topological Insulators through Fermionic Tensor Network States -- Classification, Edge Theories and Variational Wavefunctions

The study of topological band insulators has revealed fascinating phases characterized by band topology indices and anomalous boundary modes protected by global symmetries. In strongly correlated systems, where the traditional notion of electronic bands becomes obsolete, it has been established that the topological insulator phases persist as stable phases, separate from the trivial insulators. However, due to the inability to express the ground states of such systems as Slater determinants, the formulation of generic variational wavefunctions for numerical simulations is highly desirable. In this paper, we tackle this challenge for two-dimensional topological insulators by developing a comprehensive framework for fermionic tensor network states. Starting from simple assumptions, we obtain possible sets of tensor equations for any given symmetry group, capturing consistent relations governing symmetry transformation rules on tensor legs. We then examine the connections between these tensor equations and non-chiral topological insulators by construing edge theories and extracting quantum anomaly data from each set of tensor equations. By exhaustively exploring all possible sets of equations, we achieve a systematic classification of non-chiral topological insulator phases. Imposing the solutions of a given set of equations onto local tensors, we obtain generic variational wavefunctions for corresponding topological insulator phases. Our methodology provides an important step towards simulating topological insulators in strongly correlated systems. We discuss the limitations and potential generalizations of our results, paving the way for further advancements in this field.

cond-mat.str-el↗

arXiv2024

LF-3PM: a LiDAR-based Framework for Perception-aware Planning with Perturbation-induced Metric

Just as humans can become disoriented in featureless deserts or thick fogs, not all environments are conducive to the Localization Accuracy and Stability (LAS) of autonomous robots. This paper introduces an efficient framework designed to enhance LiDAR-based LAS through strategic trajectory generation, known as Perception-aware Planning. Unlike vision-based frameworks, the LiDAR-based requires different considerations due to unique sensor attributes. Our approach focuses on two main aspects: firstly, assessing the impact of LiDAR observations on LAS. We introduce a perturbation-induced metric to provide a comprehensive and reliable evaluation of LiDAR observations. Secondly, we aim to improve motion planning efficiency. By creating a Static Observation Loss Map (SOLM) as an intermediary, we logically separate the time-intensive evaluation and motion planning phases, significantly boosting the planning process. In the experimental section, we demonstrate the effectiveness of the proposed metrics across various scenes and the feature of trajectories guided by different metrics. Ultimately, our framework is tested in a real-world scenario, enabling the robot to actively choose topologies and orientations preferable for localization. The source code is accessible at https://github.com/ZJU-FAST-Lab/LF-3PM.

cs.RO↗

arXiv2024

Intention-Aware Planner for Robust and Safe Aerial Tracking

Autonomous target tracking with quadrotors has wide applications in many scenarios, such as cinematographic follow-up shooting or suspect chasing. Target motion prediction is necessary when designing the tracking planner. However, the widely used constant velocity or constant rotation assumption can not fully capture the dynamics of the target. The tracker may fail when the target happens to move aggressively, such as sudden turn or deceleration. In this paper, we propose an intention-aware planner by additionally considering the intention of the target to enhance safety and robustness in aerial tracking applications. Firstly, a designated intention prediction method is proposed, which combines a user-defined potential assessment function and a state observation function. A reachable region is generated to specifically evaluate the turning intentions. Then we design an intention-driven hybrid A* method to predict the future possible positions for the target. Finally, an intention-aware optimization approach is designed to generate a spatial-temporal optimal trajectory, allowing the tracker to perceive unexpected situations from the target. Benchmark comparisons and real-world experiments are conducted to validate the performance of our method.

cs.RO↗

arXiv2024

WING: Wheel-Inertial Neural Odometry with Ground Manifold Constraints

In this paper, we propose an interoceptive-only odometry system for ground robots with neural network processing and soft constraints based on the assumption of a globally continuous ground manifold. Exteroceptive sensors such as cameras, GPS and LiDAR may encounter difficulties in scenarios with poor illumination, indoor environments, dusty areas and straight tunnels. Therefore, improving the pose estimation accuracy only using interoceptive sensors is important to enhance the reliability of navigation system even in degrading scenarios mentioned above. However, interoceptive sensors like IMU and wheel encoders suffer from large drift due to noisy measurements. To overcome these challenges, the proposed system trains deep neural networks to correct the measurements from IMU and wheel encoders, while considering their uncertainty. Moreover, because ground robots can only travel on the ground, we model the ground surface as a globally continuous manifold using a dual cubic B-spline manifold to further improve the estimation accuracy by this soft constraint. A novel space-based sliding-window filtering framework is proposed to fully exploit the $C^2$ continuity of ground manifold soft constraints and fuse all the information from raw measurements and neural networks in a yaw-independent attitude convention. Extensive experiments demonstrate that our proposed approach can outperform state-of-the-art learning-based interoceptive-only odometry methods.

cs.RO↗

arXiv2024

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that such data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. However, the limited scale and diversity of current image-text interleaved data restrict the development of multimodal large language models. In this paper, we introduce OmniCorpus, a 10 billion-scale image-text interleaved dataset. Using an efficient data engine, we filter and extract large-scale high-quality documents, which contain 8.6 billion images and 1,696 billion text tokens. Compared to counterparts (e.g., MMC4, OBELICS), our dataset 1) has 15 times larger scales while maintaining good data quality; 2) features more diverse sources, including both English and non-English websites as well as video-centric websites; 3) is more flexible, easily degradable from an image-text interleaved format to pure text corpus and image-text pairs. Through comprehensive analysis and experiments, we validate the quality, usability, and effectiveness of the proposed dataset. We hope this could provide a solid data foundation for future multimodal model research. Code and data are released at https://github.com/OpenGVLab/OmniCorpus.

cs.CV↗

arXiv2024

MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos

We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos. Recent methods for avatar learning are typically based on neural radiance fields (NeRF), which is not compatible with traditional graphics pipeline and poses great challenges for operations like editing or synthesizing under different environments. To overcome these limitations, our method represents the avatar with an explicit triangular mesh extracted from an implicit SDF field, complemented by an implicit material field conditioned on given poses. Leveraging this triangular avatar representation, we incorporate physics-based rendering to accurately decompose geometry and texture. To enhance both the geometric and appearance details, we further employ a 2D UNet as the network backbone and introduce pseudo normal ground-truth as additional supervision. Experiments show that our method can learn triangular avatars with high-quality geometry reconstruction and plausible material decomposition, inherently supporting editing, manipulation or relighting operations.

cs.CV↗

arXiv2024

Gamma positivity of variations of $(α,t)$-Eulerian polynomials

In 1977 Carlitz and Scoville introduced the cycle $(α,t)$-Eulerian polynomials $A^{\mathrm{cyc}}_n(x,y, t\,|\,α)$ by enumerating permutations with respect to the number of excedances, drops, fixed points and cycles. In this paper, we introduce a nine-variable generalization of the Eulerian polynomials $A_n(u_1,u_2,u_3,u_4, f, g, t\,|\,α, β)$ in terms of descent based statistics of permutations and prove a connection formula between these two kinds of generalized Eulerian polynomials. By exploring the connection formula, we derive plainly the exponential generating function of the latter polynomials and various $γ$-positive formulas for variants of Eulerian polynomials. In particular, our results unify and strengthen the recent results by Ji and Ji-Lin. In related work to the transition matrix between the Specht and web bases, Hwang, Jang and Oh recently introduced the web permutations, which can be characterised by cycle André permutations. We show that enumerating the latter permutations with respect to the number of drops, fixed points and cycles gives rise to the normalised $γ$-vectors of the $(α,t)$-Eulerian polynomials. Our result generalizes and unifies several known results in the literature.

math.CO↗

arXiv2024

Almost optimum $\ell$-covering of $\mathbb{Z}_n$

A subset $B$ of the ring $\mathbb{Z}_n$ is referred to as a $\ell$-covering set if $\{ ab \pmod n | 0\leq a \leq \ell, b\in B\} = \mathbb{Z}_n$. We show that there exists a $\ell$-covering set of $\mathbb{Z}_n$ of size $O(\frac{n}{\ell}\log n)$ for all $n$ and $\ell$, and how to construct such a set. We also provide examples where any $\ell$-covering set must have a size of $Ω(\frac{n}{\ell}\frac{\log n}{\log \log n})$. The proof employs a refined bound for the relative totient function obtained through sieve theory and the existence of a large divisor with a linear divisor sum. The result can be used to simplify a modular subset sum algorithm.

cs.DM↗