arXiv subjects

Xiaodong Shi

Publications and source records attributed to Xiaodong Shi.

At least 37 records · Page 2Linked to original sources

arXiv2025

LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline

When the complete source sentence is provided, Large Language Models (LLMs) perform excellently in offline machine translation even with a simple prompt "Translate the following sentence from [src lang] into [tgt lang]:". However, in many real scenarios, the source tokens arrive in a streaming manner and simultaneous machine translation (SiMT) is required, then the efficiency and performance of decoder-only LLMs are significantly limited by their auto-regressive nature. To enable LLMs to achieve high-quality SiMT as efficiently as offline translation, we propose a novel paradigm that includes constructing supervised fine-tuning (SFT) data for SiMT, along with new training and inference strategies. To replicate the token input/output stream in SiMT, the source and target tokens are rearranged into an interleaved sequence, separated by special tokens according to varying latency requirements. This enables powerful LLMs to learn read and write operations adaptively, based on varying latency prompts, while still maintaining efficient auto-regressive decoding. Experimental results show that, even with limited SFT data, our approach achieves state-of-the-art performance across various SiMT benchmarks, and preserves the original abilities of offline translation. Moreover, our approach generalizes well to document-level SiMT setting without requiring specific fine-tuning, even beyond the offline translation model.

cs.CL↗

arXiv2025

How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation

Large language models (LLMs) have demonstrated strong performance in general-purpose machine translation, but their effectiveness in complex, domain-sensitive translation tasks remains underexplored. Recent advancements in Large Reasoning Models (LRMs), raise the question of whether structured reasoning can enhance translation quality across diverse domains. In this work, we compare the performance of LRMs with traditional LLMs across 15 representative domains and four translation directions. Our evaluation considers various factors, including task difficulty, input length, and terminology density. We use a combination of automatic metrics and an enhanced MQM-based evaluation hierarchy to assess translation quality. Our findings show that LRMs consistently outperform traditional LLMs in semantically complex domains, especially in long-text and high-difficulty translation scenarios. Moreover, domain-adaptive prompting strategies further improve performance by better leveraging the reasoning capabilities of LRMs. These results highlight the potential of structured reasoning in MDMT tasks and provide valuable insights for optimizing translation systems in domain-sensitive contexts.

cs.CL↗

arXiv2025

Enabling Highly Efficient Infrared Silicon Photodetectors via Disordered Metasurfaces with Upconversion Nanoparticles

Silicon photodetectors are highly desirable for their CMOS compatibility, low cost, and fast response speed. However, their application the infrared (IR) is limited by silicon's intrinsic bandgap, which restricts its detection to photons with wavelengths shorter than 1100 nm. Although several methods have been developed to extend silicon photodetectors further in the IR range, these approaches often introduce additional challenges, such as increased fabrication complexity and compatibility issues with standard CMOS processes. Here, we present an approach to overcome these limitations by integrating disordered metasurfaces with upconversion nanoparticles (UCNPs), enabling IR detection by silicon photodetectors. The disordered design consists of hybrid Mie-plasmonic cavities, which can enhance both the near-field localization and wide-band light absorption from visible to IR, improving photocurrent conversion. Compared to ordered structures, the infrared absorption and near field of the highly disordered configuration are increased by 2.6-folds and 3.9-folds, respectively. UCNPs not only convert near-infrared photons into visible light but also enhance absorption in the mid-infrared range, thereby improving hot electron generation. The measured responsivity of the disordered element for 1550 nm laser is up to 0.22 A/W at room temperature, corresponding to an external quantum efficiency of 17.6%. Our design not only enhances the photocurrent performance significantly, but also extends the working wavelength of silicon photodetectors to IR wavelength, making them suitable for broad spectrum applications.

physics.optics↗

arXiv2024

A Cross-Font Image Retrieval Network for Recognizing Undeciphered Oracle Bone Inscriptions

Oracle Bone Inscription (OBI) is the earliest mature writing system in China, which represents a crucial stage in the development of hieroglyphs. Nevertheless, the substantial quantity of undeciphered OBI characters remains a significant challenge for scholars, while conventional methods of ancient script research are both time-consuming and labor-intensive. In this paper, we propose a cross-font image retrieval network (CFIRN) to decipher OBI characters by establishing associations between OBI characters and other script forms, simulating the interpretive behavior of paleography scholars. Concretely, our network employs a siamese framework to extract deep features from character images of various fonts, fully exploring structure clues with different resolutions by multiscale feature integration (MFI) module and multiscale refinement classifier (MRC). Extensive experiments on three challenging cross-font image retrieval datasets demonstrate that, given undeciphered OBI characters, our CFIRN can effectively achieve accurate matches with characters from other gallery fonts, thereby facilitating the deciphering.

cs.CV↗

arXiv2024

Representation Purification for End-to-End Speech Translation

Speech-to-text translation (ST) is a cross-modal task that involves converting spoken language into text in a different language. Previous research primarily focused on enhancing speech translation by facilitating knowledge transfer from machine translation, exploring various methods to bridge the gap between speech and text modalities. Despite substantial progress made, factors in speech that are not relevant to translation content, such as timbre and rhythm, often limit the efficiency of knowledge transfer. In this paper, we conceptualize speech representation as a combination of content-agnostic and content-relevant factors. We examine the impact of content-agnostic factors on translation performance through preliminary experiments and observe a significant performance deterioration when content-agnostic perturbations are introduced to speech signals. To address this issue, we propose a \textbf{S}peech \textbf{R}epresentation \textbf{P}urification with \textbf{S}upervision \textbf{E}nhancement (SRPSE) framework, which excludes the content-agnostic components within speech representations to mitigate their negative impact on ST. Experiments on MuST-C and CoVoST-2 datasets demonstrate that SRPSE significantly improves translation performance across all translation directions in three settings and achieves preeminent performance under a \textit{transcript-free} setting.

cs.CL↗

arXiv2024

LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models

Enlarging the context window of large language models (LLMs) has become a crucial research area, particularly for applications involving extremely long texts. In this work, we propose a novel training-free framework for processing long texts, utilizing a divide-and-conquer strategy to achieve comprehensive document understanding. The proposed LLM$\times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate answers to produce the final output. The main challenge for divide-and-conquer long text processing frameworks lies in the risk of losing essential long-range information when splitting the document, which can lead the model to produce incomplete or incorrect answers based on the segmented texts. Disrupted long-range information can be classified into two categories: inter-chunk dependency and inter-chunk conflict. We design a structured information protocol to better cope with inter-chunk dependency and an in-context confidence calibration mechanism to resolve inter-chunk conflicts. Experimental results demonstrate that LLM$\times$MapReduce can outperform representative open-source and commercial long-context LLMs, and is applicable to several different models.

cs.CL↗

arXiv2024

UniMem: Towards a Unified View of Long-Context Large Language Models

Long-context processing is a critical ability that constrains the applicability of large language models (LLMs). Although there exist various methods devoted to enhancing the long-context processing ability of LLMs, they are developed in an isolated manner and lack systematic analysis and integration of their strengths, hindering further developments. In this paper, we introduce UniMem, a Unified framework that reformulates existing long-context methods from the view of Memory augmentation of LLMs. Distinguished by its four core dimensions-Memory Management, Memory Writing, Memory Reading, and Memory Injection, UniMem empowers researchers to conduct systematic exploration of long-context methods. We re-formulate 16 existing methods based on UniMem and analyze four representative methods: Transformer-XL, Memorizing Transformer, RMT, and Longformer into equivalent UniMem forms to reveal their design principles and strengths. Based on these analyses, we propose UniMix, an innovative approach that integrates the strengths of these algorithms. Experimental results show that UniMix achieves superior performance in handling long contexts with significantly lower perplexity than baselines.

cs.CL↗

arXiv2024

CMOS-compatible photonic integrated circuits on thin-film ScAlN

Scandium aluminum nitride (ScAlN) has recently emerged as an attractive material for integrated photonics due to its favorable nonlinear optical properties and compatibility with CMOS fabrication. Despite the promising and versatile material properties, it is still an outstanding challenge to realize low-loss photonic circuits on thin-film ScAlN-on-insulator wafers. Here, we present a systematic study on the material quality of sputtered thin-film ScAlN produced in a CMOS-compatible 200 mm line, and an optimized fabrication process to yield 400 nm thick, fully etched waveguides. With surface polishing and annealing, we achieve micro-ring resonators with an intrinsic quality factor as high as $1.47\times 10^5$, corresponding to a propagation loss of 2.4 dB/cm. These results serve as a critical step towards developing future large-scale, low-loss photonic integrated circuits based on ScAlN.

physics.optics↗

arXiv2024

Efficient photon-pair generation in layer-poled lithium niobate nanophotonic waveguides

Integrated photon-pair sources are crucial for scalable photonic quantum systems. Thin-film lithium niobate is a promising platform for on-chip photon-pair generation through spontaneous parametric down-conversion (SPDC). However, the device implementation faces practical challenges. Periodically poled lithium niobate (PPLN), despite enabling flexible quasi-phase matching, suffers from poor fabrication reliability and device repeatability, while conventional modal phase matching (MPM) methods yield limited efficiencies due to inadequate mode overlaps. Here, we introduce a layer-poled lithium niobate (LPLN) nanophotonic waveguide for efficient photon-pair generation. It leverages layer-wise polarity inversion through electrical poling to break spatial symmetry and significantly enhance nonlinear interactions for MPM, achieving a notable normalized second-harmonic generation (SHG) conversion efficiency of 4615% W^{-1}cm^{-2}. Through a cascaded SHG and SPDC process, we demonstrate photon-pair generation with a normalized brightness of 3.1*10^6 Hz nm^{-1} mW^{-2} in a 3.3 mm long LPLN waveguide, surpassing existing on-chip sources under similar operating configurations. Crucially, our LPLN waveguides offer enhanced fabrication reliability and reduced sensitivity to geometric variations and temperature fluctuations compared to PPLN devices. We expect LPLN to become a promising solution for on-chip nonlinear wavelength conversion and non-classical light generation, with immediate applications in quantum communication, networking, and on-chip photonic quantum information processing.

physics.optics↗

arXiv2024

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization

Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and multi-modal LLMs, MatPlotAgent consists of three core modules: query understanding, code generation with iterative debugging, and a visual feedback mechanism for error correction. To address the lack of benchmarks in this field, we present MatPlotBench, a high-quality benchmark consisting of 100 human-verified test cases. Additionally, we introduce a scoring approach that utilizes GPT-4V for automatic evaluation. Experimental results demonstrate that MatPlotAgent can improve the performance of various LLMs, including both commercial and open-source models. Furthermore, the proposed evaluation method shows a strong correlation with human-annotated scores.

cs.CL↗

arXiv2023

Layer-wise Representation Fusion for Compositional Generalization

Existing neural models are demonstrated to struggle with compositional generalization (CG), i.e., the ability to systematically generalize to unseen compositions of seen components. A key reason for failure on CG is that the syntactic and semantic representations of sequences in both the uppermost layer of the encoder and decoder are entangled. However, previous work concentrates on separating the learning of syntax and semantics instead of exploring the reasons behind the representation entanglement (RE) problem to solve it. We explain why it exists by analyzing the representation evolving mechanism from the bottom to the top of the Transformer layers. We find that the ``shallow'' residual connections within each layer fail to fuse previous layers' information effectively, leading to information forgetting between layers and further the RE problems. Inspired by this, we propose LRF, a novel \textbf{L}ayer-wise \textbf{R}epresentation \textbf{F}usion framework for CG, which learns to fuse previous layers' information back into the encoding and decoding process effectively through introducing a \emph{fuse-attention module} at each encoder and decoder layer. LRF achieves promising results on two realistic benchmarks, empirically demonstrating the effectiveness of our proposal.

cs.CL↗

arXiv2023

MOPRD: A multidisciplinary open peer review dataset

Open peer review is a growing trend in academic publications. Public access to peer review data can benefit both the academic and publishing communities. It also serves as a great support to studies on review comment generation and further to the realization of automated scholarly paper review. However, most of the existing peer review datasets do not provide data that cover the whole peer review process. Apart from this, their data are not diversified enough as the data are mainly collected from the field of computer science. These two drawbacks of the currently available peer review datasets need to be addressed to unlock more opportunities for related studies. In response, we construct MOPRD, a multidisciplinary open peer review dataset. This dataset consists of paper metadata, multiple version manuscripts, review comments, meta-reviews, author's rebuttal letters, and editorial decisions. Moreover, we propose a modular guided review comment generation method based on MOPRD. Experiments show that our method delivers better performance as indicated by both automatic metrics and human evaluation. We also explore other potential applications of MOPRD, including meta-review generation, editorial decision prediction, author rebuttal generation, and scientometric analysis. MOPRD is a strong endorsement for further studies in peer review-related research and other applications.

cs.DL↗

arXiv2023

Efficient Raman lasing and Raman-Kerr interaction in an integrated silicon carbide platform

Implementing stimulated Raman scattering in a low-loss microresonator could lead to Raman lasing. Here, we report the demonstration of an efficient Raman laser with $>50 \%$ power efficiency in an integrated silicon carbide platform for the first time. By fine tuning the free spectral range (FSR) of 43-$μ$m-radius silicon carbide microresonators, the Stokes resonance corresponding to the dominant Raman shift of $777\ \text{cm}^{-1}$ ($23.3$ THz) is aligned to the center of the Raman gain spectrum, resulting in a low power threshold of $2.5$ mW. The peak Raman gain coefficient is estimated to be ($0.75 \pm 0.15) \ \text{cm}/\text{GW}$ in the 1550 nm band, with an approximate full width at half maximum of ($120 \pm 30$) GHz. In addition, the microresonator is designed to exhibit normal dispersion at the pump wavelength near 1550 nm while possessing anomalous dispersion at the first Stokes near 1760 nm. At high enough input powers, a Kerr microcomb is generated by the Stokes signal acting as the secondary pump, which then mixes with the pump laser through four-wave mixing to attain a wider spectral coverage. Furthermore, cascaded Raman lasing and occurrence of multiple Raman shifts, including $204\ \text{cm}^{-1}$ ($6.1$ THz) and $266\ \text{cm}^{-1}$ ($8.0$ THz) transitions, are also observed. Finally, we show that the Stokes Raman could also help broaden the spectrum in a Kerr microcomb which has anomalous dispersion at the pump wavelength. Our example of a 100-GHz-FSR microcomb has a wavelength span from 1200 nm to 1900 nm with 300 mW on-chip power.

physics.optics↗

arXiv2023

Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference

A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints. However, there is a mismatch problem in using a model trained with complete utterances for streaming inference with partial input. We demonstrate that speech representations extracted at the end of a streaming input are significantly different from those extracted from a complete utterance. To address this issue, we propose a new approach called Future-Aware Streaming Translation (FAST) that adapts an offline ST model for streaming input. FAST includes a Future-Aware Inference (FAI) strategy that incorporates future context through a trainable masked embedding, and a Future-Aware Distillation (FAD) framework that transfers future context from an approximation of full speech to streaming input. Our experiments on the MuST-C EnDe, EnEs, and EnFr benchmarks show that FAST achieves better trade-offs between translation quality and latency than strong baselines. Extensive analyses suggest that our methods effectively alleviate the aforementioned mismatch problem between offline training and online inference.

cs.CL↗

arXiv2023

Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization

Recent studies have shown that sequence-to-sequence (seq2seq) models struggle with compositional generalization (CG), i.e., the ability to systematically generalize to unseen compositions of seen components. There is mounting evidence that one of the reasons hindering CG is the representation of the encoder uppermost layer is entangled, i.e., the syntactic and semantic representations of sequences are entangled. However, we consider that the previously identified representation entanglement problem is not comprehensive enough. Additionally, we hypothesize that the source keys and values representations passing into different decoder layers are also entangled. Starting from this intuition, we propose \textsc{CompoSition} (\textbf{Compo}se \textbf{S}yntactic and Semant\textbf{i}c Representa\textbf{tion}s), an extension to seq2seq models which learns to compose representations of different encoder layers dynamically for different tasks, since recent studies reveal that the bottom layers of the Transformer encoder contain more syntactic information and the top ones contain more semantic information. Specifically, we introduce a \textit{composed layer} between the encoder and decoder to compose different encoder layers' representations to generate specific keys and values passing into different decoder layers. \textsc{CompoSition} achieves competitive results on two comprehensive and realistic benchmarks, which empirically demonstrates the effectiveness of our proposal. Codes are available at~\url{https://github.com/thinkaboutzero/COMPOSITION}.

cs.CL↗

arXiv2023

How many preprints have actually been printed and why: a case study of computer science preprints on arXiv

Preprints play an increasingly critical role in academic communities. There are many reasons driving researchers to post their manuscripts to preprint servers before formal submission to journals or conferences, but the use of preprints has also sparked considerable controversy, especially surrounding the claim of priority. In this paper, a case study of computer science preprints submitted to arXiv from 2008 to 2017 is conducted to quantify how many preprints have eventually been printed in peer-reviewed venues. Among those published manuscripts, some are published under different titles and without an update to their preprints on arXiv. In the case of these manuscripts, the traditional fuzzy matching method is incapable of mapping the preprint to the final published version. In view of this issue, we introduce a semantics-based mapping method with the employment of Bidirectional Encoder Representations from Transformers (BERT). With this new mapping method and a plurality of data sources, we find that 66% of all sampled preprints are published under unchanged titles and 11% are published under different titles and with other modifications. A further analysis was then performed to investigate why these preprints but not others were accepted for publication. Our comparison reveals that in the field of computer science, published preprints feature adequate revisions, multiple authorship, detailed abstract and introduction, extensive and authoritative references and available source code.

cs.DL↗

arXiv2023

Automated scholarly paper review: Concepts, technologies, and challenges

Peer review is a widely accepted mechanism for research evaluation, playing a pivotal role in academic publishing. However, criticisms have long been leveled at this mechanism, mostly because of its poor efficiency and low reproducibility. Recent years have seen the application of artificial intelligence (AI) in assisting the peer review process. Nonetheless, with the involvement of humans, such limitations remain inevitable. In this paper, we propose the concept and pipeline of automated scholarly paper review (ASPR) and review the relevant literature and technologies of achieving a full-scale computerized review process. On the basis of the review and discussion, we conclude that there is already corresponding research and preliminary implementation at each stage of ASPR. We further look into the challenges in ASPR with the existing technologies. The major difficulties lie in inadequate data, imperfect document parsing and representation, defective human$\unicode{x2013}$computer interaction, and flawed deep logical reasoning. Moreover, we point out the future directions and discuss the possible moral and ethical issues of ASPR. In the foreseeable future, ASPR and peer review will coexist in a reinforcing manner before ASPR is able to fully undertake the reviewing workload from humans.

cs.AI↗

arXiv2023

A Token-level Contrastive Framework for Sign Language Translation

Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people. Recently, researchers have adopted Neural Machine Translation (NMT) methods, which usually require large-scale corpus for training, to achieve SLT. However, the publicly available SLT corpus is very limited, which causes the collapse of the token representations and the inaccuracy of the generated tokens. To alleviate this issue, we propose ConSLT, a novel token-level \textbf{Con}trastive learning framework for \textbf{S}ign \textbf{L}anguage \textbf{T}ranslation , which learns effective token representations by incorporating token-level contrastive learning into the SLT decoding process. Concretely, ConSLT treats each token and its counterpart generated by different dropout masks as positive pairs during decoding, and then randomly samples $K$ tokens in the vocabulary that are not in the current sentence to construct negative examples. We conduct comprehensive experiments on two benchmarks (PHOENIX14T and CSL-Daily) for both end-to-end and cascaded settings. The experimental results demonstrate that ConSLT can achieve better translation quality than the strong baselines.

cs.CL↗