BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Jinyang Li

Jinyang Li contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningArtificial IntelligenceComputation and Languagequant-phDatabasesDistributed, Parallel, and Cluster Computingmath.NANumerical AnalysisSocial and Information NetworksComputer Visioncs.CYphysics.atom-phSoftware Engineering

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
17works
0followers
13topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

17 published item(s)

preprint2026arXiv

Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals

Internet of Things (IoT) systems continuously collect heterogeneous sensing signals from ubiquitous sensors to support intelligent applications such as human activity analysis, emotion monitoring, and environmental perception. These signals are inherently non-stationary and multi-scale, posing unique challenges for standard tokenization techniques. This paper proposes Dywave, a dynamic tokenization framework for IoT sensing signals that constructs compact input representations aligned with intrinsic temporal structures and underlying physical events. Dywave leverages wavelet-based hierarchical decomposition, identifies meaningful temporal boundaries corresponding to underlying semantic events, and adaptively compresses redundant intervals while preserving temporal coherence. Extensive evaluations on five real-world IoT sensing datasets across activity recognition, stress assessment, and nearby object detection demonstrate that Dywave outperforms state-of-the-art methods by up to 12% in accuracy, while improving computational efficiency by reducing input token lengths by up to 75% across mainstream sequence models. Moreover, Dywave exhibits improved robustness to domain shifts and varying sequence lengths.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Revisiting Speculative Leaderless Protocols for Low-Latency BFT Replication

As Byzantine Fault Tolerant (BFT) protocols begin to be used in permissioned blockchains for user-facing applications such as payments, it is crucial that they provide low latency. In pursuit of low latency, some recently proposed BFT consensus protocols employ a leaderless optimistic fast path, in which clients broadcast their requests directly to replicas without first serializing requests at a leader, resulting in an end-to-end commit latency of 2 message delays ($2Δ$) during fault-free, synchronous periods. However, such a fast path only works if there is no contention: concurrent contending requests can cause replicas to diverge if they receive conflicting requests in different orders, triggering costly recovery procedures. In this work, we present Aspen, a leaderless BFT protocol that achieves a near-optimal latency of $2Δ+ \varepsilon$, where $\varepsilon$ indicates a short waiting delay. Aspen removes the no-contention condition by utilizing a best-effort sequencing layer based on loosely synchronized clocks and network delay estimates. Aspen requires $n = 3f + 2p + 1$ replicas to cope with up to $f$ Byzantine nodes. The $2p$ extra nodes allow Aspen's fast path to proceed even if up to $p$ replicas diverge due to unpredictable network delays. When its optimistic conditions do not hold, Aspen falls back to PBFT-style protocol, guaranteeing safety and liveness under partial synchrony. In experiments with wide-area distributed replicas, Aspen commits requests in less than 75 ms, a 1.2 to 3.3$\times$ improvement compared to previous protocols, while supporting 19,000 requests per second.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TTrace: Lightweight Error Checking and Diagnosis for Distributed Training

Distributed training is essential for scaling the training of large neural network models, such as large language models (LLMs), across thousands of GPUs. However, the complexity of distributed training programs makes them particularly prone to silent bugs, which do not produce explicit error signals but lead to incorrect training outcomes. Effectively detecting and localizing such silent bugs in distributed training is challenging. Common debugging practices based on monitoring training loss or gradient norm curves are indirect, inefficient, and provide no way to localize bugs. To address those challenges, we design and implement TTrace, the first systematic differential testing system for detecting and localizing silent bugs in distributed training. TTrace aligns intermediate tensors from distributed training with those from a trusted reference implementation. To properly compare the floating-point values in the corresponding tensors, we propose a novel mathematical analysis that provides a guideline for setting tolerances, enabling TTrace to distinguish bug-induced errors from numerical errors. Experimental results demonstrate that TTrace effectively detects 11 existing bugs and 3 new bugs in the widely used Megatron-LM framework, while requiring fewer than 10 lines of code changes. TTrace is effective in various training recipes, including low-precision recipes involving BF16 and FP8. Notably, a popular open-source training framework has already adopted the method proposed by TTrace in its development workflow.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies

Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively. Despite its importance, existing relevant benchmarks largely evaluate agents on pre-specified or synthesized files with limited real-world dependencies, leaving workspace-level evaluation underexplored. To this end, we introduce Workspace-Bench, a benchmark for evaluating AI agents on Workspace Learning involving Large-Scale File Dependencies. We construct realistic workspaces with 5 worker profiles, 74 file types, 20,476 files (up to 20GB) and curate 388 tasks, each with its own file dependency graph, evaluated across 7,399 total rubrics that require cross-file retrieval, contextual reasoning, and adaptive decision-making. We further provide Workspace-Bench-Lite, a 100-task subset that preserves the benchmark distribution while reducing evaluation costs by about 70%. We evaluate 4 popular agent harnesses and 7 foundation models. Experimental results show that current agents remain far from reliable workspace learning, where the best reaches only about 60%, substantially below the human result of 80.7%, and the average performance across agents is only 43.3%.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing

The task of text-to-SQL parsing, which aims at converting natural language questions into executable SQL queries, has garnered increasing attention in recent years, as it can assist end users in efficiently extracting vital information from databases without the need for technical background. One of the major challenges in text-to-SQL parsing is domain generalization, i.e., how to generalize well to unseen databases. Recently, the pre-trained text-to-text transformer model, namely T5, though not specialized for text-to-SQL parsing, has achieved state-of-the-art performance on standard benchmarks targeting domain generalization. In this work, we explore ways to further augment the pre-trained T5 model with specialized components for text-to-SQL parsing. Such components are expected to introduce structural inductive bias into text-to-SQL parsers thus improving model's capacity on (potentially multi-hop) reasoning, which is critical for generating structure-rich SQLs. To this end, we propose a new architecture GRAPHIX-T5, a mixed model with the standard pre-trained transformer model augmented by some specially-designed graph-aware layers. Extensive experiments and analysis demonstrate the effectiveness of GRAPHIX-T5 across four text-to-SQL benchmarks: SPIDER, SYN, REALISTIC and DK. GRAPHIX-T5 surpass all other T5-based parsers with a significant margin, achieving new state-of-the-art performance. Notably, GRAPHIX-T5-large reach performance superior to the original T5-large by 5.7% on exact match (EM) accuracy and 6.6% on execution accuracy (EX). This even outperforms the T5-3B by 1.2% on EM and 1.5% on EX.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions

Text-to-SQL parsing is an essential and challenging task. The goal of text-to-SQL parsing is to convert a natural language (NL) question to its corresponding structured query language (SQL) based on the evidences provided by relational databases. Early text-to-SQL parsing systems from the database community achieved a noticeable progress with the cost of heavy human engineering and user interactions with the systems. In recent years, deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output SQL query. Subsequently, the large pre-trained language models have taken the state-of-the-art of the text-to-SQL parsing task to a new level. In this survey, we present a comprehensive review on deep learning approaches for text-to-SQL parsing. First, we introduce the text-to-SQL parsing corpora which can be categorized as single-turn and multi-turn. Second, we provide a systematical overview of pre-trained language models and existing methods for text-to-SQL parsing. Third, we present readers with the challenges faced by text-to-SQL parsing and explore some potential future directions in this field.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

An AIoT-enabled Autonomous Dementia Monitoring System

An autonomous Artificial Internet of Things (AIoT) system for elderly dementia patients monitoring in a smart home is presented. The system mainly implements two functions based on the activity inference of the sensor data, which are real time abnormal activity monitoring and trend prediction of disease related activities. Specifically, CASAS dataset is employed to train a Random Forest (RF) model for activity inference. Then, another RF model trained by the output data of activity inference is used for abnormal activity monitoring. Particularly, RF is chosen for these tasks because of its balanced trade offs between accuracy, time efficiency, flexibility, and interpretability. Moreover, Long Short Term Memory (LSTM) is utilised to forecast the disease related activity trend of a patient. Consequently, the accuracy of two RF classifiers designed for activity inference and abnormal activity detection is greater than 99 percent and 94 percent, respectively. Furthermore, using the duration of sleep as an example, the LSTM model achieves accurate and evident future trends prediction.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments

We develop a new, principled algorithm for estimating the contribution of training data points to the behavior of a deep learning model, such as a specific prediction it makes. Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to a subset of the training data, sampled from a given distribution. When subsets are sampled from the uniform distribution, the AME reduces to the well-known Shapley value. Our approach is inspired by causal inference and randomized experiments: we sample different subsets of the training data to train multiple submodels, and evaluate each submodel's behavior. We then use a LASSO regression to jointly estimate the AME of each data point, based on the subset compositions. Under sparsity assumptions ($k \ll N$ datapoints have large AME), our estimator requires only $O(k\log N)$ randomized submodel trainings, improving upon the best prior Shapley value estimators.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-axis Accelerometry and Rotation Sensing using a Point Source Atom Interferometer

A point source atom interferometer (PSI) is a device where atoms are split and recombined by applying a temporal sequence of Raman pulses during the expansion of a cloud of cold atoms behaving approximately as a point source. Unlike a conventional light pulse atom interferometer, the PSI can produce a signal that corresponds to multi-axis rotation only, independent of acceleration. In addition, it can be used to measure acceleration along one direction, independent of rotation. Here, we describe a modified PSI that can be used to measure multi-axis rotation and multi-axis acceleration. Specifically, this type of PSI can be used to measure two-axes rotation around the directions perpendicular to the light pulses, as well as the acceleration in all three directions, with only one pair of Raman beams. Using two pairs of Raman beams in orthogonal directions sequentially, such a scheme would enable the realization of a complete atom interferometric inertial measurement unit.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers

Deep-learning (DL) compilers such as TVM and TensorRT are increasingly being used to optimize deep neural network (DNN) models to meet performance, resource utilization and other requirements. Bugs in these compilers can result in models whose semantics differ from the original ones, producing incorrect results that corrupt the correctness of downstream applications. However, finding bugs in these compilers is challenging due to their complexity. In this work, we propose a new fuzz testing approach for finding bugs in deep-learning compilers. Our core approach consists of (i) generating diverse yet valid DNN test models that can exercise a large part of the compiler's transformation logic using light-weight operator specifications; (ii) performing gradient-based search to find model inputs that avoid any floating-point exceptional values during model execution, reducing the chance of missed bugs or false alarms; and (iii) using differential testing to identify bugs. We implemented this approach in NNSmith which has found 72 new bugs for TVM, TensorRT, ONNXRuntime, and PyTorch to date. Of these 58 have been confirmed and 51 have been fixed by their respective project maintainers.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Spin Squeezing Induced Enhancement of Sensitivity of an Atomic Clock using Coherent Population Trapping

The coherent population trapping (CPT) effect is used for making compact atomic clocks. There are two types of CPT clocks: the one in which the Raman beams are applied continuously and the one in which two CPT pulses separated by a dark period are applied (Ramsey scheme). It is obvious that the technique of spin squeezing can only be applied to the Ramsey CPT clock to enhance the sensitivity. However, it is not apparent how to adapt to the CPT clock the protocols for the microwave clock using one-axis-twist squeezing (OATS), since the Ramsey CPT clock is not trivially equivalent to the Ramsey microwave clock. In this paper, we show explicitly how to adapt two protocols using OATS, namely the Schrödinger cat state protocol (SCSP) and the generalization thereof, and the echo squeezing protocol (ESP), to the CPT clock. The ESP magnifies the phase shift by a factor of the square-root of (N/e), while the SCSP magnifies the phase shift by a factor of N/2 , making it able to achieve a higher sensitivity in the presence of excess noise.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders

This paper develops a novel unsupervised algorithm for belief representation learning in polarized networks that (i) uncovers the latent dimensions of the underlying belief space and (ii) jointly embeds users and content items (that they interact with) into that space in a manner that facilitates a number of downstream tasks, such as stance detection, stance prediction, and ideology mapping. Inspired by total correlation in information theory, we propose the Information-Theoretic Variational Graph Auto-Encoder (InfoVGAE) that learns to project both users and content items (e.g., posts that represent user views) into an appropriate disentangled latent space. To better disentangle latent variables in that space, we develop a total correlation regularization module, a Proportional-Integral (PI) control module, and adopt rectified Gaussian distribution to ensure the orthogonality. The latent representation of users and content can then be used to quantify their ideological leaning and detect/predict their stances on issues. We evaluate the performance of the proposed InfoVGAE on three real-world datasets, of which two are collected from Twitter and one from U.S. Congress voting records. The evaluation results show that our model outperforms state-of-the-art unsupervised models by reducing 10.5% user clustering errors and achieving 12.1% higher F1 scores for stance separation of content items. In addition, InfoVGAE produces a comparable result with supervised models. We also discuss its performance on stance prediction and user ranking within ideological groups.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

The Paradox of Information Access: On Modeling Social-Media-Induced Polarization

The paper develops a stochastic model of drift in human beliefs that shows that today's sheer volume of accessible information, combined with consumers' confirmation bias and natural preference to more outlying content, necessarily lead to increased polarization. The model explains the paradox of growing ideological fragmentation in the age of increased sharing. As social media, search engines, and other real-time information sharing outlets purport to facilitate access to information, a need for content filtering arises due to the ensuing information overload. In general, consumers select information that matches their individual views and values. The bias inherent in such selection is echoed by today's information curation services that maximize user engagement by filtering new content in accordance with observed consumer preferences. Consequently, individuals get exposed to increasingly narrower bands of the ideology spectrum, thus fragmenting society into increasingly ideologically isolated enclaves. We call this dynamic the paradox of information access. The model also suggests the disproportionate damage attainable with a small infusion of well-positioned misinformation. The paper describes the modeling methodology, and evaluates modeling results for different population sizes and parameter settings.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and implementation of Deep Graph Library (DGL). DGL distills the computational patterns of GNNs into a few generalized sparse tensor operations suitable for extensive parallelization. By advocating graph as the central programming abstraction, DGL can perform optimizations transparently. By cautiously adopting a framework-neutral design, DGL allows users to easily port and leverage the existing components across multiple deep learning frameworks. Our evaluation shows that DGL significantly outperforms other popular GNN-oriented frameworks in both speed and memory consumption over a variety of benchmarks and has little overhead for small scale workloads.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition

State-of-the-art video action recognition models with complex network architecture have archived significant improvements, but these models heavily depend on large-scale well-labeled datasets. To reduce such dependency, we propose a self-supervised teacher-student architecture, i.e., the Differentiated Teachers Guided self-supervised Network (DTG-Net). In DTG-Net, except for reducing labeled data dependency by self-supervised learning (SSL), pre-trained action related models are used as teacher guidance providing prior knowledge to alleviate the demand for a large number of unlabeled videos in SSL. Specifically, leveraging the years of effort in action-related tasks, e.g., image classification, image-based action recognition, the DTG-Net learns the self-supervised video representation under various teacher guidance, i.e., those well-trained models of action-related tasks. Meanwhile, the DTG-Net is optimized in the way of contrastive self-supervised learning. When two image sequences are randomly sampled from the same video or different videos as the positive or negative pairs, respectively, they are then sent to the teacher and student networks for feature embedding. After that, the contrastive feature consistency is defined between features embedding of each pair, i.e., consistent for positive pair and inconsistent for negative pairs. Meanwhile, to reflect various teacher tasks' different guidance, we also explore different weighted guidance on teacher tasks. Finally, the DTG-Net is evaluated in two ways: (i) the self-supervised DTG-Net to pre-train the supervised action recognition models with only unlabeled videos; (ii) the supervised DTG-Net to be jointly trained with the supervised action networks in an end-to-end way. Its performance is better than most pre-training methods but also has excellent competitiveness compared to supervised action recognition methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

High sensitivity multi-axes rotation sensing using large momentum transfer point source atom interferometry

A point source interferometer (PSI) is a device where atoms are split and recombined by applying a temporal sequence of Raman pulses during the expansion of a cloud of cold atoms behaving approximately as a point source. The PSI can work as a sensitive multi-axes gyroscope that can automatically filter out the signal from accelerations. The phase shift arising from rotations is proportional to the momentum transferred to each atom from the Raman pulses. Therefore, by increasing the momentum transfer, it should be possibly to enhance the sensitivity of the PSI. Here, we investigate the degree of enhancement in sensitivity that could be achieved by augmenting the PSI with large momentum transfer (LMT) employing a sequence of many Raman pulses with alternating directions. Contrary to typical approaches used for describing a PSI, we employ a model under which the motion of the center of mass of each atom is described quantum mechanically. We show how increasing Doppler shifts lead to imperfections, thereby limiting the visibility of the signal fringes, and identify ways to suppress this effect by increasing the effective, two-photon Rabi frequencies of the Raman pulses. Taking into account the effect of spontaneous emission, we show that, for a given value of the one-photon Rabi frequency, there is an optimum value for the number of pulses employed, beyond which the net enhancement in sensitivity begins to decrease. For a one-photon Rabi frequency of 200 MHz, for example, the peak value of the factor of enhancement in sensitivity is ~39, for a momentum transfer that is ~69 times as large as that for a conventional PSI. We also find that this peak value scales as the one-photon Rabi frequency to the power of 4/5.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The Paradox of Information Access: Growing Isolation in the Age of Sharing

Modern online media, such as Twitter, Instagram, and YouTube, enable anyone to become an information producer and to offer online content for potentially global consumption. By increasing the amount of globally accessible real-time information, today's ubiquitous producers contribute to a world, where an individual consumes vanishingly smaller fractions of all produced content. In general, consumers preferentially select information that closely matches their individual views and values. The bias inherent in such selection is further magnified by today's information curation services that maximize user engagement (and thus service revenue) by filtering new content in accordance with observed consumer preferences. Consequently, individuals get exposed to increasingly narrower bands of the ideology spectrum. Societies get fragmented into increasingly ideologically isolated enclaves. These enclaves (or echo-chambers) then become vulnerable to misinformation spread, which in turn further magnifies polarization and bias. We call this dynamic the paradox of information access; a growing ideological fragmentation in the age of sharing. This article describes the technical, economic, and socio-cognitive contributors to this paradox, and explores research directions towards its mitigation.

0 citations0 reviewsNo code linkedOpen access