Searcharxiv⌕ Search

arXiv subjects

Chen Zhang

Publications and source records attributed to Chen Zhang.

At least 379 records · Page 21Linked to original sources
arXiv2024

PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstruction

Surface reconstruction has traditionally relied on the Multi-View Stereo (MVS)-based pipeline, which often suffers from noisy and incomplete geometry. This is due to that although MVS has been proven to be an effective way to recover the geometry of the scenes, especially for locally detailed areas with rich textures, it struggles to deal with areas with low texture and large variations of illumination where the photometric consistency is unreliable. Recently, Neural Implicit Surface Reconstruction (NISR) combines surface rendering and volume rendering techniques and bypasses the MVS as an intermediate step, which has emerged as a promising alternative to overcome the limitations of traditional pipelines. While NISR has shown impressive results on simple scenes, it remains challenging to recover delicate geometry from uncontrolled real-world scenes which is caused by its underconstrained optimization. To this end, the framework PSDF is proposed which resorts to external geometric priors from a pretrained MVS network and internal geometric priors inherent in the NISR model to facilitate high-quality neural implicit surface learning. Specifically, the visibility-aware feature consistency loss and depth prior-assisted sampling based on external geometric priors are introduced. These proposals provide powerfully geometric consistency constraints and aid in locating surface intersection points, thereby significantly improving the accuracy and delicate reconstruction of NISR. Meanwhile, the internal prior-guided importance rendering is presented to enhance the fidelity of the reconstructed surface mesh by mitigating the biased rendering issue in NISR. Extensive experiments on the Tanks and Temples dataset show that PSDF achieves state-of-the-art performance on complex uncontrolled scenes.

cs.CV↗
arXiv2024

A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators

Automatic evaluation is an integral aspect of dialogue system research. The traditional reference-based NLG metrics are generally found to be unsuitable for dialogue assessment. Consequently, recent studies have suggested various unique, reference-free neural metrics that better align with human evaluations. Notably among them, large language models (LLMs), particularly the instruction-tuned variants like ChatGPT, are shown to be promising substitutes for human judges. Yet, existing works on utilizing LLMs for automatic dialogue evaluation are limited in their scope in terms of the number of meta-evaluation datasets, mode of evaluation, coverage of LLMs, etc. Hence, it remains inconclusive how effective these LLMs are. To this end, we conduct a comprehensive study on the application of LLMs for automatic dialogue evaluation. Specifically, we analyze the multi-dimensional evaluation capability of 30 recently emerged LLMs at both turn and dialogue levels, using a comprehensive set of 12 meta-evaluation datasets. Additionally, we probe the robustness of the LLMs in handling various adversarial perturbations at both turn and dialogue levels. Finally, we explore how model-level and dimension-level ensembles impact the evaluation performance. All resources are available at https://github.com/e0397123/comp-analysis.

cs.CL↗
arXiv2024

Hybrid Strangeon Stars

It was conjectured that the basic units of the ground state of bulk strong matter may be strange-clusters called strangeons, and they can form self-bound strangeon stars that are highly compact. Strangeon stars can develop a strange quark matter (SQM) core at high densities, particularly in the color-flavor-locking phase, yielding a branch of hybrid strangeon stars. We explore the stellar structure and astrophysical implications of hybrid strangeon stars. We find that hybrid strangeon stars can meet various astrophysical constraints on pulsar masses, radii, and tidal deformabilities. Finally, we show that the strangeon-SQM mixed phase is not preferred if the charge-neutrality condition is imposed at the strangeon-SQM transition region.

nucl-th↗
arXiv2023

BAE-Net: A Low complexity and high fidelity Bandwidth-Adaptive neural network for speech super-resolution

Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches primarily focus on fixed upsampling ratios, disregarding the fact that the effective bandwidth of captured audio may fluctuate frequently due to various capturing devices and transmission conditions. In this paper, we propose a novel streaming adaptive bandwidth extension solution dubbed BAE-Net, which is suitable to handle the low-resolution speech with unknown and varying effective bandwidth. To address the challenges of recovering both the high-frequency magnitude and phase speech content blindly, we devise a dual-stream architecture that incorporates the magnitude inpainting and phase refinement. For potential applications on edge devices, this paper also introduces BAE-NET-lite, which is a lightweight, streaming and efficient framework. Quantitative results demonstrate the superiority of BAE-Net in terms of both performance and computational efficiency when compared with existing state-of-the-art BWE methods.

cs.SD↗
arXiv2023

Relation-Aware Question Answering for Heterogeneous Knowledge Graphs

Multi-hop Knowledge Base Question Answering(KBQA) aims to find the answer entity in a knowledge graph (KG), which requires multiple steps of reasoning. Existing retrieval-based approaches solve this task by concentrating on the specific relation at different hops and predicting the intermediate entity within the reasoning path. During the reasoning process of these methods, the representation of relations are fixed but the initial relation representation may not be optimal. We claim they fail to utilize information from head-tail entities and the semantic connection between relations to enhance the current relation representation, which undermines the ability to capture information of relations in KGs. To address this issue, we construct a \textbf{dual relation graph} where each node denotes a relation in the original KG (\textbf{primal entity graph}) and edges are constructed between relations sharing same head or tail entities. Then we iteratively do primal entity graph reasoning, dual relation graph information propagation, and interaction between these two graphs. In this way, the interaction between entity and relation is enhanced, and we derive better entity and relation representations. Experiments on two public datasets, WebQSP and CWQ, show that our approach achieves a significant performance gain over the prior state-of-the-art. Our code is available on \url{https://github.com/yanmenxue/RAH-KBQA}.

cs.CL↗
arXiv2023

PR-NeuS: A Prior-based Residual Learning Paradigm for Fast Multi-view Neural Surface Reconstruction

Neural surfaces learning has shown impressive performance in multi-view surface reconstruction. However, most existing methods use large multilayer perceptrons (MLPs) to train their models from scratch, resulting in hours of training for a single scene. Recently, how to accelerate the neural surfaces learning has received a lot of attention and remains an open problem. In this work, we propose a prior-based residual learning paradigm for fast multi-view neural surface reconstruction. This paradigm consists of two optimization stages. In the first stage, we propose to leverage generalization models to generate a basis signed distance function (SDF) field. This initial field can be quickly obtained by fusing multiple local SDF fields produced by generalization models. This provides a coarse global geometry prior. Based on this prior, in the second stage, a fast residual learning strategy based on hash-encoding networks is proposed to encode an offset SDF field for the basis SDF field. Moreover, we introduce a prior-guided sampling scheme to help the residual learning stage converge better, and thus recover finer structures. With our designed paradigm, experimental results show that our method only takes about 3 minutes to reconstruct the surface of a single scene, while achieving competitive surface quality. Our code will be released upon publication.

cs.CV↗
arXiv2023

Ground Calibration Result of the Lobster Eye Imager for Astronomy

We report on results of the on-ground X-ray calibration of the Lobster Eye Imager for Astronomy (LEIA), an experimental space wide-field (18.6*18.6 square degrees) X-ray telescope built from novel lobster eye mirco-pore optics. LEIA was successfully launched on July 27, 2022 onboard the SATech-01 satellite. To achieve full characterisation of its performance before launch, a series of tests and calibrations have been carried out at different levels of devices, assemblies and the complete module. In this paper, we present the results of the end-to-end calibration campaign of the complete module carried out at the 100-m X-ray Test Facility at IHEP. The PSF, effective area and energy response of the detectors were measured in a wide range of incident directions at several X-ray line energies. The distributions of the PSF and effective areas are roughly uniform across the FoV, in large agreement with the prediction of lobster-eye optics. The mild variations and deviations from the prediction of idealized lobster-eye optics can be understood to be caused by the imperfect shapes and alignment of the micro-pores as well as the obscuration by the supporting frames, which can be well reproduced by MC simulations. The spatial resolution of LEIA defined by the FWHM of the focal spot ranges from 4-8 arcmin with a median of 5.7. The measured effective areas are in range of 2-3 $cm^2$ at ~1.25 keV across the entire FoV, and its dependence on photon energy is in large agreement with simulations. The gains of the CMOS sensors are in range of 6.5-6.9 eV/DN, and the energy resolutions in the range of ~120-140 eV at 1.25 keV and ~170-190 eV at 4.5 keV. These results have been ingested into the calibration database and applied to the analysis of the scientific data acquired by LEIA. This work paves the way for the calibration of the Wide-field X-Ray Telescope modules of the Einstein Probe mission.

astro-ph.IM↗
arXiv2023

Do We Fully Understand Students' Knowledge States? Identifying and Mitigating Answer Bias in Knowledge Tracing

Knowledge tracing (KT) aims to monitor students' evolving knowledge states through their learning interactions with concept-related questions, and can be indirectly evaluated by predicting how students will perform on future questions. In this paper, we observe that there is a common phenomenon of answer bias, i.e., a highly unbalanced distribution of correct and incorrect answers for each question. Existing models tend to memorize the answer bias as a shortcut for achieving high prediction performance in KT, thereby failing to fully understand students' knowledge states. To address this issue, we approach the KT task from a causality perspective. A causal graph of KT is first established, from which we identify that the impact of answer bias lies in the direct causal effect of questions on students' responses. A novel COunterfactual REasoning (CORE) framework for KT is further proposed, which separately captures the total causal effect and direct causal effect during training, and mitigates answer bias by subtracting the latter from the former in testing. The CORE framework is applicable to various existing KT models, and we implement it based on the prevailing DKT, DKVMN, and AKT models, respectively. Extensive experiments on three benchmark datasets demonstrate the effectiveness of CORE in making the debiased inference for KT. We have released our code at https://github.com/lucky7-code/CORE.

cs.AI↗
arXiv2023

VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing

Video dubbing aims to translate the original speech in a film or television program into the speech in a target language, which can be achieved with a cascaded system consisting of speech recognition, machine translation and speech synthesis. To ensure the translated speech to be well aligned with the corresponding video, the length/duration of the translated speech should be as close as possible to that of the original speech, which requires strict length control. Previous works usually control the number of words or characters generated by the machine translation model to be similar to the source sentence, without considering the isochronicity of speech as the speech duration of words/characters in different languages varies. In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech. Specifically, we control the speech length of generated sentence by guiding the prediction of each word with the duration information, including the speech duration of itself as well as how much duration is left for the remaining words. We design experiments on four language directions (German -> English, Spanish -> English, Chinese <-> English), and the results show that the proposed method achieves better length control ability on the generated speech than baseline methods. To make up the lack of real-world datasets, we also construct a real-world test set collected from films to provide comprehensive evaluations on the video dubbing task.

cs.CL↗
arXiv2023

An algebraic combinatorial approach to Sylvester's denumerant

For a positive integer sequence $\boldsymbol{a}=(a_1, \dots, a_{N+1})$, Sylvester's denumerant $E(\boldsymbol{a}; t)$ counts the number of nonnegative integer solutions to $\sum_{i=1}^{N+1} a_i x_i = t$ for a nonnegative integer $t$. It has been extensively studied and a well-known result asserts that $E(\boldsymbol{a}; t)$ is a quasi-polynomial in $t$ of degree $N$. A milestone is Baldoni et al.'s polynomial algorithm in 2015 for computing the top $k$ coefficients when $k$ is fixed. Their development uses heavily lattice point counting theory in computational geometry. In this paper, we explain their work in the context of algebraic combinatorics and simplify their computation. Our work is based on constant term method, Barvinok's unimodular cone decomposition, and recent results on fast computation of generalized Todd polynomials. We develop the algorithm \texttt{CT-Knapsack}, together with an implementation in \texttt{Maple}. Our algorithm avoids plenty of repeated computations and is hence faster.

math.CO↗
arXiv2023

Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection

The goal of weakly supervised video anomaly detection is to learn a detection model using only video-level labeled data. However, prior studies typically divide videos into fixed-length segments without considering the complexity or duration of anomalies. Moreover, these studies usually just detect the most abnormal segments, potentially overlooking the completeness of anomalies. To address these limitations, we propose a Dynamic Erasing Network (DE-Net) for weakly supervised video anomaly detection, which learns multi-scale temporal features. Specifically, to handle duration variations of abnormal events, we first propose a multi-scale temporal modeling module, capable of extracting features from segments of varying lengths and capturing both local and global visual information across different temporal scales. Then, we design a dynamic erasing strategy, which dynamically assesses the completeness of the detected anomalies and erases prominent abnormal segments in order to encourage the model to discover gentle abnormal segments in a video. The proposed method obtains favorable performance compared to several state-of-the-art approaches on three datasets: XD-Violence, TAD, and UCF-Crime. Code will be made available at https://github.com/ArielZc/DE-Net.

cs.CV↗
arXiv2023

Radiation effects on scientific CMOS sensors for X-ray astronomy: I. proton irradiation

Complementary metal-oxide-semiconductor (CMOS) sensors are a competitive choice for future X-ray astronomy missions. Typically, CMOS sensors on space astronomical telescopes are exposed to a high dose of irradiation. We investigate the impact of irradiation on the performance of two scientific CMOS (sCMOS) sensors between -30 to 20 degree at high gain mode (7.5 times), including the bias map, readout noise, dark current, conversion gain, and energy resolution. The two sensors are irradiated with 50 MeV protons with a total dose of 5.3*10^10 p/cm^2. After the exposure, the bias map, readout noise and conversion gain at various temperatures are not significantly degraded, nor is the energy resolution at -30 degree. However, after the exposure the dark current has increased by hundreds of times, and for every 20 degree increase in temperature, the dark current also increases by an order of magnitude. Therefore, at room temperature, the fluctuations of the dark currents dominate the noise and lead to a serious degradation of the energy resolution. Moreover, among the 4k * 4k pixels, there are about 100 pixels whose bias at 50 ms has changed by more than 10 DN (~18 e-), and about 10 pixels whose readout noise has increased by over 15 e- at -30 degree. Fortunately, the influence of the dark current can be reduced by decreasing the integration time, and the degraded pixels can be masked by regular analysis of the dark images. Some future X-ray missions will likely operate at -30 degree, under which the dark current is too small to significantly affect the X-ray performance. Our investigations show the high tolerance of the sCMOS sensors for proton radiation and prove their suitability for X-ray astronomy applications.

astro-ph.IM↗
arXiv2023

An Aluminum-coated sCMOS sensor for X-Ray Astronomy

In recent years, tremendous progress has been made on scientific Complementary Metal Oxide Semiconductor (sCMOS) sensors, making them a promising device for future space X-ray missions. We have customized a large-format sCMOS sensor, G1516BI, dedicated for X-ray applications. In this work, a 200 nm thick aluminum layer is successfully sputtered on the surface of this sensor. This Al-coated sensor, named EP4K, shows consistent performance with the uncoated version. The readout noise of the EP4K sensor is around 2.5 e- and the dark current is less than 0.01 e-/pixel/s at -30 degree. The maximum frame rate is 20 Hz in the current design. The ratio of single pixel events of the sensor is 45.0%. The energy resolution can reach 153.2 eV at 4.51 keV and 174.2 eV at 5.90 keV at -30 degree. The optical transmittance of the aluminum layer is approximately 1e-8 to 1e-10 for optical lights from 365 to 880 nm, corresponding to an effective aluminum thickness of around 140 to 160 nm. The good X-ray performance and low optical transmittance of this Al-coated sCMOS sensor make it a good choice for space X-ray missions. The Lobster Eye Imager for Astronomy (LEIA), which has been working in orbit for about one year, is equipped with four pieces of EP4K sensors. Furthermore, 48 pieces of EP4K sensors are used on the Wide-field X-ray Telescope (WXT) on the Einstein Probe (EP) satellite, which will be launched at the end of 2023.

astro-ph.IM↗
arXiv2023

PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction

Recently, learning multi-view neural surface reconstruction with the supervision of point clouds or depth maps has been a promising way. However, due to the underutilization of prior information, current methods still struggle with the challenges of limited accuracy and excessive time complexity. In addition, prior data perturbation is also an important but rarely considered issue. To address these challenges, we propose a novel point-guided method named PG-NeuS, which achieves accurate and efficient reconstruction while robustly coping with point noise. Specifically, aleatoric uncertainty of the point cloud is modeled to capture the distribution of noise, leading to noise robustness. Furthermore, a Neural Projection module connecting points and images is proposed to add geometric constraints to implicit surface, achieving precise point guidance. To better compensate for geometric bias between volume rendering and point modeling, high-fidelity points are filtered into a Bias Network to further improve details representation. Benefiting from the effective point guidance, even with a lightweight network, the proposed PG-NeuS achieves fast convergence with an impressive 11x speedup compared to NeuS. Extensive experiments show that our method yields high-quality surfaces with high efficiency, especially for fine-grained details and smooth regions, outperforming the state-of-the-art methods. Moreover, it exhibits strong robustness to noisy data and sparse data.

cs.CV↗
arXiv2023

Nonparametric Teaching for Multiple Learners

We study the problem of teaching multiple learners simultaneously in the nonparametric iterative teaching setting, where the teacher iteratively provides examples to the learner for accelerating the acquisition of a target concept. This problem is motivated by the gap between current single-learner teaching setting and the real-world scenario of human instruction where a teacher typically imparts knowledge to multiple students. Under the new problem formulation, we introduce a novel framework -- Multi-learner Nonparametric Teaching (MINT). In MINT, the teacher aims to instruct multiple learners, with each learner focusing on learning a scalar-valued target model. To achieve this, we frame the problem as teaching a vector-valued target model and extend the target model space from a scalar-valued reproducing kernel Hilbert space used in single-learner scenarios to a vector-valued space. Furthermore, we demonstrate that MINT offers significant teaching speed-up over repeated single-learner teaching, particularly when the multiple learners can communicate with each other. Lastly, we conduct extensive experiments to validate the practicality and efficiency of MINT.

cs.LG↗
arXiv2023

Work State-Centric AI Agents: Design, Implementation, and Management of Cognitive Work Threads

AI agents excel in executing predefined tasks, but the dynamic management of work state information during task execution remains an underexplored area. We propose a work state-centric AI agent model employing "work notes" to record and reflect the state throughout task execution. This paper details the model's architecture, featuring worker threads for task oversight, planner modules for task decomposition and planning, and executor modules for performing subtasks using a ReAct-inspired thought-action loop. We provide an exhaustive work state record incorporating plans and outcomes, constituting a comprehensive work journal. Our results show that this model not only improves task execution efficiency but also lays a solid foundation for subsequent task analysis and auditing.

cs.CL↗
arXiv2023

On Elastic Language Models

Large-scale pretrained language models have achieved compelling performance in a wide range of language understanding and information retrieval tasks. Knowledge distillation offers an opportunity to compress a large language model to a small one, in order to reach a reasonable latency-performance tradeoff. However, for scenarios where the number of requests (e.g., queries submitted to a search engine) is highly variant, the static tradeoff attained by the compressed language model might not always fit. Once a model is assigned with a static tradeoff, it could be inadequate in that the latency is too high when the number of requests is large or the performance is too low when the number of requests is small. To this end, we propose an elastic language model (ElasticLM) that elastically adjusts the tradeoff according to the request stream. The basic idea is to introduce a compute elasticity to the compressed language model, so that the tradeoff could vary on-the-fly along scalable and controllable compute. Specifically, we impose an elastic structure to enable ElasticLM with compute elasticity and design an elastic optimization to learn ElasticLM under compute elasticity. To serve ElasticLM, we apply an elastic schedule. Considering the specificity of information retrieval, we adapt ElasticLM to dense retrieval and reranking and present ElasticDenser and ElasticRanker respectively. Offline evaluation is conducted on a language understanding benchmark GLUE; and several information retrieval tasks including Natural Question, Trivia QA, and MS MARCO. The results show that ElasticLM along with ElasticDenser and ElasticRanker can perform correctly and competitively compared with an array of static baselines. Furthermore, online simulation with concurrency is also carried out. The results demonstrate that ElasticLM can provide elastic tradeoffs with respect to varying request stream.

cs.IR↗