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

Jiawei Wu

Jiawei Wu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and LanguageMachine Learningquant-phArtificial Intelligenceastro-ph.SRComputer VisionHuman-Computer InteractionInformation RetrievalInformation Theorymath.ITNetworking and Internet Architecturenucl-exnucl-thSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
14topics
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

9 published item(s)

preprint2026arXiv

Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement

Understanding patient feedback is crucial for improving healthcare services, yet analyzing unlabeled short-text feedback presents challenges due to limited data and domain-specific nuances. Traditional supervised approaches require extensive labeled datasets, making unsupervised methods more practical for extracting insights. This study applies unsupervised techniques to analyze 439 survey responses from a healthcare system in Wisconsin, USA. A keyword-based filter was used to isolate complaint-related feedback using a domain-specific lexicon. To identify dominant themes, we evaluated traditional topic models such as Latent Dirichlet Allocation (LDA) and Gibbs Sampling Dirichlet Multinomial Mixture (GSDMM) -- alongside BERTopic, a neural embedding-based clustering method. To improve coherence and interpretability in sparse, short-text data, we propose kBERT, which integrates BERT embeddings with k-means clustering. Model performance was assessed using coherence scores (Cv ) and average Inverted Rank-Biased Overlap (IRBOavg). kBERT achieved the highest coherence (Cv = 0.53) and topic separation (IRBOavg = 1.00), outperforming all other models. These findings highlight the value of embedding-based, context-aware models in healthcare analytics.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens despite only a subset encoding the knowledge targeted for removal. This introduces gradient noise, degrades utility, and leads to suboptimal forgetting. We propose TokenUnlearn, a token-level attribution framework that identifies and selectively targets critical tokens. Our approach combines knowledge-aware signals via masking, and entropy-aware signals to yield importance scores for precise token selection. We develop two complementary strategies: hard selection, applying unlearning only to high-importance tokens, and soft weighting, modulating gradient contributions based on importance scores. Both extend existing methods to token-level variants. Theoretical analysis shows token-level selection improves gradient signal-to-noise ratio. Experiments on TOFU and WMDP benchmarks across three model architectures demonstrate consistent improvements over sequence-level baselines in both forgetting effectiveness and utility preservation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Nuclear mass table in deformed relativistic Hartree-Bogoliubov theory in continuum: I. even-even nuclei

Ground-state properties of even-even nuclei with $8\le Z\le120$ from the proton drip line to the neutron drip line have been investigated using the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with the density functional PC-PK1. With the effects of deformation and continuum included simultaneously, 2583 even-even nuclei are predicted to be bound. The calculated binding energies, two-nucleon separation energies, root-mean-square (rms) radii of neutron, proton, matter, and charge distributions, quadrupole deformations, and neutron and proton Fermi surfaces are tabulated and compared with available experimental data. The rms deviation from the 637 mass data is 1.518 MeV, providing one of the best microscopic descriptions for nuclear masses. The drip lines obtained from DRHBc calculations are compared with other calculations, including the spherical relativistic continuum Hartree-Bogoliubov (RCHB) and triaxial relativistic Hartree-Bogoliubov (TRHB) calculations with PC-PK1. The deformation and continuum effects on the limits of the nuclear landscape are discussed. Possible peninsulas consisting of bound nuclei beyond the two-neutron drip line are predicted. The systematics of the two-nucleon separation energies, two-nucleon gaps, rms radii, quadrupole deformations, potential energy curves, neutron densities, neutron mean-field potentials, and pairing energies in the DRHBc calculations are also discussed. In addition, the $α$ decay energies extracted are in good agreement with available data.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Quantum secure direct communication with private dense coding using general preshared quantum state

We study quantum secure direct communication by using a general preshared quantum state and a generalization of dense coding. In this scenario, Alice is allowed to apply a unitary on the preshared state to encode her message, and the set of allowed unitaries forms a group. To decode the message, Bob is allowed to apply a measurement across his own system and the system he receives. In the worst scenario, we guarantee that Eve obtains no information for the message even when Eve access the joint system between the system that she intercepts and her original system of the preshared state. For a practical application, we propose a concrete protocol and derive an upper bound of information leakage in the finite-length setting. We also discuss how to apply our scenario to the case with discrete Weyl-Heisenberg representation when the preshared state is unknown.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions

At the time of writing, the ongoing pandemic of coronavirus disease (COVID-19) has caused severe impacts on society, economy and people's daily lives. People constantly express their opinions on various aspects of the pandemic on social media, making user-generated content an important source for understanding public emotions and concerns. In this paper, we perform a comprehensive analysis on the affective trajectories of the American people and the Chinese people based on Twitter and Weibo posts between January 20th, 2020 and May 11th 2020. Specifically, by identifying people's sentiments, emotions (i.e., anger, disgust, fear, happiness, sadness, surprise) and the emotional triggers (e.g., what a user is angry/sad about) we are able to depict the dynamics of public affect in the time of COVID-19. By contrasting two very different countries, China and the Unites States, we reveal sharp differences in people's views on COVID-19 in different cultures. Our study provides a computational approach to unveiling public emotions and concerns on the pandemic in real-time, which would potentially help policy-makers better understand people's need and thus make optimal policy.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Experimental free-space quantum secure direct communication and its security analysis

We report an experimental implementation of free-space quantum secure direct communication based on single photons. The quantum communication scheme uses phase encoding, and the asymmetric Mach-Zehnder interferometer is optimized so as to automatically compensate phase drift of the photons during their transitions over the free-space medium. An information transmission rate of 500 bps over a 10-meter free space with a mean quantum bit error rate of 0.49%$\pm$0.27% is achieved. The security is analyzed under the scenario that Eve performs collective attack and photon number splitting collective attack. Our results show that quantum secure direct communication is feasible in free space.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Improving Robustness and Generality of NLP Models Using Disentangled Representations

Supervised neural networks, which first map an input $x$ to a single representation $z$, and then map $z$ to the output label $y$, have achieved remarkable success in a wide range of natural language processing (NLP) tasks. Despite their success, neural models lack for both robustness and generality: small perturbations to inputs can result in absolutely different outputs; the performance of a model trained on one domain drops drastically when tested on another domain. In this paper, we present methods to improve robustness and generality of NLP models from the standpoint of disentangled representation learning. Instead of mapping $x$ to a single representation $z$, the proposed strategy maps $x$ to a set of representations $\{z_1,z_2,...,z_K\}$ while forcing them to be disentangled. These representations are then mapped to different logits $l$s, the ensemble of which is used to make the final prediction $y$. We propose different methods to incorporate this idea into currently widely-used models, including adding an $L$2 regularizer on $z$s or adding Total Correlation (TC) under the framework of variational information bottleneck (VIB). We show that models trained with the proposed criteria provide better robustness and domain adaptation ability in a wide range of supervised learning tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Cognitive Routing based on Deep Reinforcement Learning

Routing is one of the key functions for stable operation of network infrastructure. Nowadays, the rapid growth of network traffic volume and changing of service requirements call for more intelligent routing methods than before. Towards this end, we propose a definition of cognitive routing and an implementation approach based on Deep Reinforcement Learning (DRL). To facilitate the research of DRL-based cognitive routing, we introduce a simulator named RL4Net for DRL-based routing algorithm development and simulation. Then, we design and implement a DDPG-based routing algorithm. The simulation results on an example network topology show that the DDPG-based routing algorithm achieves better performance than OSPF and random weight algorithms. It demonstrate the preliminary feasibility and potential advantage of cognitive routing for future network.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research

We present a new large-scale multilingual video description dataset, VATEX, which contains over 41,250 videos and 825,000 captions in both English and Chinese. Among the captions, there are over 206,000 English-Chinese parallel translation pairs. Compared to the widely-used MSR-VTT dataset, VATEX is multilingual, larger, linguistically complex, and more diverse in terms of both video and natural language descriptions. We also introduce two tasks for video-and-language research based on VATEX: (1) Multilingual Video Captioning, aimed at describing a video in various languages with a compact unified captioning model, and (2) Video-guided Machine Translation, to translate a source language description into the target language using the video information as additional spatiotemporal context. Extensive experiments on the VATEX dataset show that, first, the unified multilingual model can not only produce both English and Chinese descriptions for a video more efficiently, but also offer improved performance over the monolingual models. Furthermore, we demonstrate that the spatiotemporal video context can be effectively utilized to align source and target languages and thus assist machine translation. In the end, we discuss the potentials of using VATEX for other video-and-language research.

0 citations0 reviewsNo code linkedOpen access