arXiv subjects

Xingjian Zhang

Publications and source records attributed to Xingjian Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Be.FM: Open Foundation Models for Human Behavior

Despite their success in numerous fields, the potential of foundation models for modeling and understanding human behavior remains largely unexplored. We introduce Be.FM, one of the first open foundation models designed for human behavior modeling. Built upon open-source large language models and fine-tuned on a diverse range of behavioral data, Be.FM can be used to understand and predict human decision-making. We construct a comprehensive set of benchmark tasks for testing the capabilities of behavioral foundation models. Our results demonstrate that Be.FM can predict behaviors, infer characteristics of individuals and populations, generate insights about contexts, and apply behavioral science knowledge.

cs.AI↗

arXiv2025

DCA-Bench: A Benchmark for Dataset Curation Agents

The quality of datasets plays an increasingly crucial role in the research and development of modern artificial intelligence (AI). Despite the proliferation of open dataset platforms nowadays, data quality issues, such as incomplete documentation, inaccurate labels, ethical concerns, and outdated information, remain common in widely used datasets. Furthermore, these issues are often subtle and difficult to be detected by rule-based scripts, therefore requiring identification and verification by dataset users or maintainers--a process that is both time-consuming and prone to human mistakes. With the surging ability of large language models (LLM), it's promising to streamline the discovery of hidden dataset issues with LLM agents. To achieve this, one significant challenge is enabling LLM agents to detect issues in the wild rather than simply fixing known ones. In this work, we establish a benchmark to measure LLM agent's ability to tackle this challenge. We carefully curate 221 real-world test cases from eight popular dataset platforms and propose an automatic evaluation framework using GPT-4o. Our proposed framework shows strong empirical alignment with expert evaluations, validated through extensive comparisons with human annotations. Without any hints, most competitive Curator agent can only reveal $\sim$30\% of the data quality issues in the proposed dataset, highlighting the complexity of this task and indicating that applying LLM agents to real-world dataset curation still requires further in-depth exploration and innovation. The data and code are available at \href{https://github.com/TRAIS-Lab/dca-bench}{https://github.com/TRAIS-Lab/dca-bench}.

cs.AI↗

arXiv2025

MapExplorer: New Content Generation from Low-Dimensional Visualizations

Low-dimensional visualizations, or "projection maps," are widely used in scientific and creative domains to interpret large-scale and complex datasets. These visualizations not only aid in understanding existing knowledge spaces but also implicitly guide exploration into unknown areas. Although techniques such as t-SNE and UMAP can generate these maps, there exists no systematic method for leveraging them to generate new content. To address this, we introduce MapExplorer, a novel knowledge discovery task that translates coordinates within any projection map into coherent, contextually aligned textual content. This allows users to interactively explore and uncover insights embedded in the maps. To evaluate the performance of MapExplorer methods, we propose Atometric, a fine-grained metric inspired by ROUGE that quantifies logical coherence and alignment between generated and reference text. Experiments on diverse datasets demonstrate the versatility of MapExplorer in generating scientific hypotheses, crafting synthetic personas, and devising strategies for attacking large language models-even with simple baseline methods. By bridging visualization and generation, our work highlights the potential of MapExplorer to enable intuitive human-AI collaboration in large-scale data exploration.

cs.AI↗

arXiv2025

Minder: Faulty Machine Detection for Large-scale Distributed Model Training

Large-scale distributed model training requires simultaneous training on up to thousands of machines. Faulty machine detection is critical when an unexpected fault occurs in a machine. From our experience, a training task can encounter two faults per day on average, possibly leading to a halt for hours. To address the drawbacks of the time-consuming and labor-intensive manual scrutiny, we propose Minder, an automatic faulty machine detector for distributed training tasks. The key idea of Minder is to automatically and efficiently detect faulty distinctive monitoring metric patterns, which could last for a period before the entire training task comes to a halt. Minder has been deployed in our production environment for over one year, monitoring daily distributed training tasks where each involves up to thousands of machines. In our real-world fault detection scenarios, Minder can accurately and efficiently react to faults within 3.6 seconds on average, with a precision of 0.904 and F1-score of 0.893.

cs.DC↗

arXiv2025

TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning

Recently, improving the reasoning ability of large multimodal models (LMMs) through reinforcement learning has made great progress. However, most existing works are based on highly reasoning-intensive datasets such as mathematics and code, and researchers generally choose large-scale models as the foundation. We argue that exploring small-scale models' reasoning capabilities remains valuable for researchers with limited computational resources. Moreover, enabling models to explain their reasoning processes on general question-answering datasets is equally meaningful. Therefore, we present the small-scale video reasoning model TinyLLaVA-Video-R1. Based on TinyLLaVA-Video, a traceably trained video understanding model with no more than 4B parameters, it not only demonstrates significantly improved reasoning and thinking capabilities after using reinforcement learning on general Video-QA datasets, but also exhibits the emergent characteristic of "aha moments". Furthermore, we share a series of experimental findings, aiming to provide practical insights for future exploration of video reasoning (thinking) abilities in small-scale models. It is available at https://github.com/ZhangXJ199/TinyLLaVA-Video-R1.

cs.CV↗

arXiv2025

Virtual Channel Purification

Quantum error mitigation is a key approach for extracting target state properties on state-of-the-art noisy machines and early fault-tolerant devices. Using the ideas from flag fault tolerance and virtual state purification, we develop the virtual channel purification (VCP) protocol, which consumes similar qubit and gate resources as virtual state purification but offers stronger error suppression with increased system size and more noisy operation copies. The application of VCP does not require specific knowledge about the target quantum state, the target problem and the gate noise model in the target circuit, and can still offer rigorous performance guarantees for practical noise regimes as long as the noise is incoherent. Further connections are made between VCP and quantum error correction to produce the virtual error correction (VEC) protocol, one of the first protocols that combine quantum error correction (QEC) and quantum error mitigation beyond directly applying error mitigation protocols on top of logical qubits. Assuming perfect syndrome extraction, VEC can virtually remove all correctable noise in the channel while paying only the same sampling cost as low-order purification. It can achieve QEC-level protection on an unencoded register when transmitting it through a noisy channel, removing the associated encoding qubit overhead. Another variant of VEC can mimic the error suppression power of the surface code by inputting only a bit-flip and a phase-flip code. Our protocol can also be adapted to key tasks in quantum networks like channel capacity activation and entanglement distribution.

quant-ph↗

arXiv2025

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e.g., the reasoning-focused model DeepSeek-R1 achieved the highest accuracy of 61.82% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

cs.CL↗

arXiv2024

Advantage Distillation for Quantum Key Distribution

Quantum key distribution promises information-theoretically secure communication, with data post-processing playing a vital role in extracting secure keys from raw data. While hardware advancements have significantly improved practical implementations, optimizing post-processing techniques offers a cost-effective avenue to enhance performance. Advantage distillation, which extends beyond standard information reconciliation and privacy amplification, has proven instrumental in various post-processing methods. However, the optimal post-processing remains an open question. Therefore, it is important to develop a comprehensive framework to encapsulate and enhance these existing methods. In this work, we propose an advantage distillation framework for quantum key distribution, generalizing and unifying existing key distillation protocols. Inspired by entanglement distillation, our framework not only integrates current techniques but also improves upon them. Notably, by employing classical linear codes, we achieve higher key rates, particularly in scenarios where one-time pad encryption is not used for post-processing. Our approach provides insights into existing protocols and offers a systematic way for further enhancements in quantum key distribution.

quant-ph↗

arXiv2024

Bench-CoE: a Framework for Collaboration of Experts from Benchmark

Large Language Models (LLMs) are key technologies driving intelligent systems to handle multiple tasks. To meet the demands of various tasks, an increasing number of LLMs-driven experts with diverse capabilities have been developed, accompanied by corresponding benchmarks to evaluate their performance. This paper proposes the Bench-CoE framework, which enables Collaboration of Experts (CoE) by effectively leveraging benchmark evaluations to achieve optimal performance across various tasks. Bench-CoE includes a set of expert models, a router for assigning tasks to corresponding experts, and a benchmark dataset for training the router. Moreover, we formulate Query-Level and Subject-Level approaches based on our framework, and analyze the merits and drawbacks of these two approaches. Finally, we conduct a series of experiments with vary data distributions on both language and multimodal tasks to validate that our proposed Bench-CoE outperforms any single model in terms of overall performance. We hope this method serves as a baseline for further research in this area. The code is available at \url{https://github.com/ZhangXJ199/Bench-CoE}.

cs.AI↗

arXiv2024

Unconditional quantum magic advantage in shallow circuit computation

Quantum theory promises computational speed-ups over classical approaches. The celebrated Gottesman-Knill Theorem implies that the full power of quantum computation resides in the specific resource of "magic" states -- the secret sauce to establish universal quantum computation. However, it is still questionable whether magic indeed brings the believed quantum advantage, ridding unproven complexity assumptions or black-box oracles. In this work, we demonstrate the first unconditional magic advantage: a separation between the power of generic constant-depth or shallow quantum circuits and magic-free counterparts. For this purpose, we link the shallow circuit computation with the strongest form of quantum nonlocality -- quantum pseudo-telepathy, where distant non-communicating observers generate perfectly synchronous statistics. We prove quantum magic is indispensable for such correlated statistics in a specific nonlocal game inspired by the linear binary constraint system. Then, we translate generating quantum pseudo-telepathy into computational tasks, where magic is necessary for a shallow circuit to meet the target. As a by-product, we provide an efficient algorithm to solve a general linear binary constraint system over the Pauli group, in contrast to the broad undecidability in constraint systems. We anticipate our results will enlighten the final establishment of the unconditional advantage of universal quantum computation.

quant-ph↗

arXiv2024

GBSense: A GHz-Bandwidth Compressed Spectrum Sensing System

This paper presents GBSense, an innovative compressed spectrum sensing system designed for GHz-bandwidth signals in dynamic spectrum access (DSA) applications. GBSense introduces an efficient approach to periodic nonuniform sampling, capturing wideband signals using significantly lower sampling rates compared to traditional Nyquist sampling. By integrating time-interleaved analog-to-digital conversion, GBSense overcomes the hardware complexity typically associated with traditional multicoset sampling, providing precise, real-time adjustable sampling patterns without the need for analog delay circuits. The system's ability to process signals with a 2 GHz radio frequency bandwidth using only a 400 MHz average sampling rate enables more efficient spectrum monitoring and access in wideband cognitive radios. Lab tests demonstrate 100\% accurate spectrum detection when the spectrum occupancy is below 100 MHz and over 80\% accuracy for occupancy up to 200 MHz. Additionally, an integrated system utilizing a low-power Raspberry Pi processor achieves a low processing latency of around 30 ms per frame, demonstrating the system's potential for real-time applications in cognitive radio networks, 5G, and future 6G infrastructures.

eess.SP↗

arXiv2024

Polarization-encoded quantum key distribution with a room-temperature telecom single-photon emitter

Single photon sources (SPSs) are directly applicable in quantum key distribution (QKD) because they allow the implementation of the canonical BB84 protocol. To date, QKD implementations using SPS are not widespread because of the need for cryogenic operation, or frequency conversion to a wavelength efficiently transmitted over telecommunication fibers. We report an observation of polarization-encoded QKD using a room-temperature telecom SPS based on a GaN defect. A field test over 3.5 km of deployed fiber with 4.0 dB loss yielded a secure key rate of 585.9~bps. Further testing in a 32.5 km fiber spool (attenuation of 11.2 dB), which exhibited substantially lower polarization mode dispersion, yielded a secure key rate of 50.4 bps. Both results exhibited a quantum bit error rate (QBER) of approximately 5%. These results illustrate the potential of the GaN defects for supporting polarization-encoded quantum communication.

quant-ph↗

arXiv2024

$\texttt{dattri}$: A Library for Efficient Data Attribution

Data attribution methods aim to quantify the influence of individual training samples on the prediction of artificial intelligence (AI) models. As training data plays an increasingly crucial role in the modern development of large-scale AI models, data attribution has found broad applications in improving AI performance and safety. However, despite a surge of new data attribution methods being developed recently, there lacks a comprehensive library that facilitates the development, benchmarking, and deployment of different data attribution methods. In this work, we introduce $\texttt{dattri}$, an open-source data attribution library that addresses the above needs. Specifically, $\texttt{dattri}$ highlights three novel design features. Firstly, $\texttt{dattri}$ proposes a unified and easy-to-use API, allowing users to integrate different data attribution methods into their PyTorch-based machine learning pipeline with a few lines of code changed. Secondly, $\texttt{dattri}$ modularizes low-level utility functions that are commonly used in data attribution methods, such as Hessian-vector product, inverse-Hessian-vector product or random projection, making it easier for researchers to develop new data attribution methods. Thirdly, $\texttt{dattri}$ provides a comprehensive benchmark framework with pre-trained models and ground truth annotations for a variety of benchmark settings, including generative AI settings. We have implemented a variety of state-of-the-art efficient data attribution methods that can be applied to large-scale neural network models, and will continuously update the library in the future. Using the developed $\texttt{dattri}$ library, we are able to perform a comprehensive and fair benchmark analysis across a wide range of data attribution methods. The source code of $\texttt{dattri}$ is available at https://github.com/TRAIS-Lab/dattri.

cs.LG↗

arXiv2024

Metropolitan quantum key distribution using a GaN-based room-temperature telecommunication single-photon source

Single-photon sources (SPS) hold the potential to enhance the performance of quantum key distribution (QKD). QKD systems using SPS often require cryogenic cooling, while recent QKD attempts using SPS operating at room-temperature have failed to achieve long-distance transmission due to the SPS not operating at telecommunication wavelength. In this work, we have successfully demonstrated QKD using a room-temperature SPS at telecommunication wavelength. The SPS used in this work is based on point defects hosted by gallium nitride (GaN) thin films grown on sapphire substrates. We employed a time-bin and phase encoding scheme to perform the BB84 and reference-frame-independent QKD protocols over a 33 km fiber spool, achieving a secure key rate of $7.58\times 10^{-7}$ per pulse. Moreover, we also implemented a metropolitan QKD experiment over a 30 km deployed fiber, achieving a secure key rate of $6.06\times 10^{-8}$ per pulse. These results broaden the prospects for future use of SPS in commercial QKD applications.

quant-ph↗

arXiv2024

Interplay of Quantum Resources in Nonlocality Tests

Nonlocality, evidenced by the violation of Bell inequalities, not only signifies entanglement but also highlights measurement incompatibility in quantum systems. Utilizing the generalized Clauser-Horne-Shimony-Holt (CHSH) Bell inequality, our high-efficiency optical setup achieves a loophole-free violation of $2.0132$. This result provides a device-independent lower bound on entanglement, quantified as the entanglement of formation at $0.0159$. Moreover, by tuning the parameters of the generalized Bell inequality, we enhance the estimation of measurement incompatibility, which is quantified by an effective overlap of $4.3883 \times 10^{-5}$. To explore the intricate interplay among nonlocality, entanglement, and measurement incompatibility, we generate mixed states, allowing for flexible modulation of entanglement via fast switching among the four Bell states using Pockels cells, achieving a fidelity above $99.10\%$. Intriguingly, our results reveal a counterintuitive relationship where increasing incompatibility initially boosts nonlocality but eventually leads to its reduction. Typically, maximal nonlocality does not coincide with maximal incompatibility. This experimental study sheds light on the optimal management of quantum resources for Bell-inequality-based quantum information processing.

quant-ph↗

arXiv2024

Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?

Large language models (LLMs) are gaining increasing attention for their capability to process graphs with rich text attributes, especially in a zero-shot fashion. Recent studies demonstrate that LLMs obtain decent text classification performance on common text-rich graph benchmarks, and the performance can be improved by appending encoded structural information as natural languages into prompts. We aim to understand why the incorporation of structural information inherent in graph data can improve the prediction performance of LLMs. First, we rule out the concern of data leakage by curating a novel leakage-free dataset and conducting a comparative analysis alongside a previously widely-used dataset. Second, as past work usually encodes the ego-graph by describing the graph structure in natural language, we ask the question: do LLMs understand the graph structure in accordance with the intent of the prompt designers? Third, we investigate why LLMs can improve their performance after incorporating structural information. Our exploration of these questions reveals that (i) there is no substantial evidence that the performance of LLMs is significantly attributed to data leakage; (ii) instead of understanding prompts as graph structures as intended by the prompt designers, LLMs tend to process prompts more as contextual paragraphs and (iii) the most efficient elements of the local neighborhood included in the prompt are phrases that are pertinent to the node label, rather than the graph structure.

cs.LG↗

arXiv2024

MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows

Scientific innovation relies on detailed workflows, which include critical steps such as analyzing literature, generating ideas, validating these ideas, interpreting results, and inspiring follow-up research. However, scientific publications that document these workflows are extensive and unstructured. This makes it difficult for both human researchers and AI systems to effectively navigate and explore the space of scientific innovation. To address this issue, we introduce MASSW, a comprehensive text dataset on Multi-Aspect Summarization of Scientific Workflows. MASSW includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years. Using Large Language Models (LLMs), we automatically extract five core aspects from these publications -- context, key idea, method, outcome, and projected impact -- which correspond to five key steps in the research workflow. These structured summaries facilitate a variety of downstream tasks and analyses. The quality of the LLM-extracted summaries is validated by comparing them with human annotations. We demonstrate the utility of MASSW through multiple novel machine-learning tasks that can be benchmarked using this new dataset, which make various types of predictions and recommendations along the scientific workflow. MASSW holds significant potential for researchers to create and benchmark new AI methods for optimizing scientific workflows and fostering scientific innovation in the field. Our dataset is openly available at \url{https://github.com/xingjian-zhang/massw}.

cs.CL↗

arXiv2024

TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models

We present TinyLLaVA Factory, an open-source modular codebase for small-scale large multimodal models (LMMs) with a focus on simplicity of code implementations, extensibility of new features, and reproducibility of training results. Following the design philosophy of the factory pattern in software engineering, TinyLLaVA Factory modularizes the entire system into interchangeable components, with each component integrating a suite of cutting-edge models and methods, meanwhile leaving room for extensions to more features. In addition to allowing users to customize their own LMMs, TinyLLaVA Factory provides popular training recipes to let users pretrain and finetune their models with less coding effort. Empirical experiments validate the effectiveness of our codebase. The goal of TinyLLaVA Factory is to assist researchers and practitioners in exploring the wide landscape of designing and training small-scale LMMs with affordable computational resources.

cs.LG↗