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

Hang Yin

Hang Yin contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningRoboticsArtificial Intelligencehep-phastro-ph.IMComputation and Languagecond-mat.mtrl-scigr-qchep-exphysics.soc-phPopulations and Evolution

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
15works
0followers
11topics
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

15 published item(s)

preprint2026arXiv

LegalCiteBench: Evaluating Citation Reliability in Legal Language Models

Large language models (LLMs) are increasingly integrated into legal drafting and research workflows, where incorrect citations or fabricated precedents can cause serious professional harm. Existing legal benchmarks largely emphasize statutory reasoning, contract understanding, or general legal question answering, but they do not directly study a central common-law failure mode: when asked to provide case authorities without external grounding, models may return plausible-looking but incorrect citations or cases. We introduce LegalCiteBench, a benchmark for studying closed-book citation recovery, citation verification, and case matching in legal language models. LegalCiteBench contains approximately 24K evaluation instances constructed from 1,000 real U.S. judicial opinions from the Case Law Access Project. The benchmark covers five citation-centric tasks: citation retrieval, citation completion, citation error detection, case matching, and case verification and correction. Across 21 LLMs, exact citation recovery remains highly challenging in this closed-book setting: even the strongest models score below 7/100 on citation retrieval and completion. Within the evaluated models, scale and legal-domain pretraining provide limited gains and do not resolve this difficulty. Models also frequently provide concrete but incorrect or low-overlap authorities under our evaluation protocol, with Misleading Answer Rates (MAR) exceeding 94% for 20 of 21 evaluated models on retrieval-heavy tasks. A prompt-only abstention experiment shows that explicit uncertainty instructions reduce some confident fabrication but do not improve citation correctness. LegalCiteBench is intended as a diagnostic framework for studying authority generation failures, verification behavior, and abstention when external grounding is absent, incomplete, or bypassed.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Back to the Manifold: Recovering from Out-of-Distribution States

Learning from previously collected datasets of expert data offers the promise of acquiring robotic policies without unsafe and costly online explorations. However, a major challenge is a distributional shift between the states in the training dataset and the ones visited by the learned policy at the test time. While prior works mainly studied the distribution shift caused by the policy during the offline training, the problem of recovering from out-of-distribution states at the deployment time is not very well studied yet. We alleviate the distributional shift at the deployment time by introducing a recovery policy that brings the agent back to the training manifold whenever it steps out of the in-distribution states, e.g., due to an external perturbation. The recovery policy relies on an approximation of the training data density and a learned equivariant mapping that maps visual observations into a latent space in which translations correspond to the robot actions. We demonstrate the effectiveness of the proposed method through several manipulation experiments on a real robotic platform. Our results show that the recovery policy enables the agent to complete tasks while the behavioral cloning alone fails because of the distributional shift problem.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Enabling Visual Action Planning for Object Manipulation through Latent Space Roadmap

We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces, focusing on manipulation of deformable objects. We propose a Latent Space Roadmap (LSR) for task planning which is a graph-based structure globally capturing the system dynamics in a low-dimensional latent space. Our framework consists of three parts: (1) a Mapping Module (MM) that maps observations given in the form of images into a structured latent space extracting the respective states as well as generates observations from the latent states, (2) the LSR which builds and connects clusters containing similar states in order to find the latent plans between start and goal states extracted by MM, and (3) the Action Proposal Module that complements the latent plan found by the LSR with the corresponding actions. We present a thorough investigation of our framework on simulated box stacking and rope/box manipulation tasks, and a folding task executed on a real robot.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents

This work addresses the problem of sensing the world: how to learn a multimodal representation of a reinforcement learning agent's environment that allows the execution of tasks under incomplete perceptual conditions. To address such problem, we argue for hierarchy in the design of representation models and contribute with a novel multimodal representation model, MUSE. The proposed model learns hierarchical representations: low-level modality-specific representations, encoded from raw observation data, and a high-level multimodal representation, encoding joint-modality information to allow robust state estimation. We employ MUSE as the sensory representation model of deep reinforcement learning agents provided with multimodal observations in Atari games. We perform a comparative study over different designs of reinforcement learning agents, showing that MUSE allows agents to perform tasks under incomplete perceptual experience with minimal performance loss. Finally, we evaluate the performance of MUSE in literature-standard multimodal scenarios with higher number and more complex modalities, showing that it outperforms state-of-the-art multimodal variational autoencoders in single and cross-modality generation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ultra-fast synthesis and thermodynamic analysis of MoAlB by self-propagating high temperature combustion synthesis

MoAlB as a typical member of the MAB phases has attracted much growing attention due to its unique properties. However, the low production of MoAlB powders limits its further development and potential applications. To respond this challenge, the ultra-fast preparation of high-purity MoAlB powders is achieved in a few seconds by self-propagating high temperature combustion synthesis (SHS) using the raw powder mixture at the atomic ratio of 1Mo/1.3Al/1B. The reaction mechanism in SHS process was obtained by analyzing the corresponding composition changes of starting materials. Furthermore, the thermodynamic prediction for the SHS reaction of Mo + (1+y)Al + B = MoAlB + yAl is consistent with the present experiments, where the preparation of MoAlB also conforms to two common self-propagating conditions of SHS. Enthalpy vs temperature curve shows that the adiabatic temperature of the reaction decreases with increasing the amount of excuse Al, but increase when pre-heating the reactants. The thermodynamic calculation method also provides a new idea for the preparation of other MAB phases by SHS.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Explainable Deep Behavioral Sequence Clustering for Transaction Fraud Detection

In e-commerce industry, user behavior sequence data has been widely used in many business units such as search and merchandising to improve their products. However, it is rarely used in financial services not only due to its 3V characteristics - i.e. Volume, Velocity and Variety - but also due to its unstructured nature. In this paper, we propose a Financial Service scenario Deep learning based Behavior data representation method for Clustering (FinDeepBehaviorCluster) to detect fraudulent transactions. To utilize the behavior sequence data, we treat click stream data as event sequence, use time attention based Bi-LSTM to learn the sequence embedding in an unsupervised fashion, and combine them with intuitive features generated by risk experts to form a hybrid feature representation. We also propose a GPU powered HDBSCAN (pHDBSCAN) algorithm, which is an engineering optimization for the original HDBSCAN algorithm based on FAISS project, so that clustering can be carried out on hundreds of millions of transactions within a few minutes. The computation efficiency of the algorithm has increased 500 times compared with the original implementation, which makes flash fraud pattern detection feasible. Our experimental results show that the proposed FinDeepBehaviorCluster framework is able to catch missed fraudulent transactions with considerable business values. In addition, rule extraction method is applied to extract patterns from risky clusters using intuitive features, so that narrative descriptions can be attached to the risky clusters for case investigation, and unknown risk patterns can be mined for real-time fraud detection. In summary, FinDeepBehaviorCluster as a complementary risk management strategy to the existing real-time fraud detection engine, can further increase our fraud detection and proactive risk defense capabilities.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Gaussian Mixture Graphical Lasso with Application to Edge Detection in Brain Networks

Sparse inverse covariance estimation (i.e., edge de-tection) is an important research problem in recent years, wherethe goal is to discover the direct connections between a set ofnodes in a networked system based upon the observed nodeactivities. Existing works mainly focus on unimodal distributions,where it is usually assumed that the observed activities aregenerated from asingleGaussian distribution (i.e., one graph).However, this assumption is too strong for many real-worldapplications. In many real-world applications (e.g., brain net-works), the node activities usually exhibit much more complexpatterns that are difficult to be captured by one single Gaussiandistribution. In this work, we are inspired by Latent DirichletAllocation (LDA) [4] and consider modeling the edge detectionproblem as estimating a mixture ofmultipleGaussian distribu-tions, where each corresponds to a separate sub-network. Toaddress this problem, we propose a novel model called GaussianMixture Graphical Lasso (MGL). It learns the proportionsof signals generated by each mixture component and theirparameters iteratively via an EM framework. To obtain moreinterpretable networks, MGL imposes a special regularization,called Mutual Exclusivity Regularization (MER), to minimize theoverlap between different sub-networks. MER also addresses thecommon issues in read-world data sets,i.e., noisy observationsand small sample size. Through the extensive experiments onsynthetic and real brain data sets, the results demonstrate thatMGL can effectively discover multiple connectivity structuresfrom the observed node activities

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Graph-based Task-specific Prediction Models for Interactions between Deformable and Rigid Objects

Capturing scene dynamics and predicting the future scene state is challenging but essential for robotic manipulation tasks, especially when the scene contains both rigid and deformable objects. In this work, we contribute a simulation environment and generate a novel dataset for task-specific manipulation, involving interactions between rigid objects and a deformable bag. The dataset incorporates a rich variety of scenarios including different object sizes, object numbers and manipulation actions. We approach dynamics learning by proposing an object-centric graph representation and two modules which are Active Prediction Module (APM) and Position Prediction Module (PPM) based on graph neural networks with an encode-process-decode architecture. At the inference stage, we build a two-stage model based on the learned modules for single time step prediction. We combine modules with different prediction horizons into a mixed-horizon model which addresses long-term prediction. In an ablation study, we show the benefits of the two-stage model for single time step prediction and the effectiveness of the mixed-horizon model for long-term prediction tasks. Supplementary material is available at https://github.com/wengzehang/deformable_rigid_interaction_prediction

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Impact of LHCb 13 TeV $W$ and $Z$ pseudo-data on the Parton Distribution Functions

We study the potential of the LHCb 13 TeV single $W^{\pm}$ and $Z$ boson pseudo-data for constraining the parton distribution functions (PDFs) of the proton. As an example, we demonstrate the sensitivity of the LHCb 13 TeV data, collected with integrated luminosities of 5 fb$^{-1}$ and 300 fb$^{-1}$, to reducing the PDF uncertainty bands of the CT14HERA2 PDFs, using the error PDF updating package {\sc ePump}. The sensitivities of various experimental observables are compared. Generally, sizable reductions in PDF uncertainties can be observed in the 300 fb$^{-1}$ data sample, particularly in the small-$x$ region. The double-differential cross section measurement of $Z$ boson $p_T$ and rapidity can greatly reduce the uncertainty bands of $u$ and $d$ quarks in almost the whole $x$ range, as compared to various single observable measurements.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Learning Stable Normalizing-Flow Control for Robotic Manipulation

Reinforcement Learning (RL) of robotic manipulation skills, despite its impressive successes, stands to benefit from incorporating domain knowledge from control theory. One of the most important properties that is of interest is control stability. Ideally, one would like to achieve stability guarantees while staying within the framework of state-of-the-art deep RL algorithms. Such a solution does not exist in general, especially one that scales to complex manipulation tasks. We contribute towards closing this gap by introducing $\textit{normalizing-flow}$ control structure, that can be deployed in any latest deep RL algorithms. While stable exploration is not guaranteed, our method is designed to ultimately produce deterministic controllers with provable stability. In addition to demonstrating our method on challenging contact-rich manipulation tasks, we also show that it is possible to achieve considerable exploration efficiency--reduced state space coverage and actuation efforts--without losing learning efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

On the Impact of Spurious Correlation for Out-of-distribution Detection

Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments. While much research attention has been placed on designing new out-of-distribution (OOD) detection methods, the precise definition of OOD is often left in vagueness and falls short of the desired notion of OOD in reality. In this paper, we present a new formalization and model the data shifts by taking into account both the invariant and environmental (spurious) features. Under such formalization, we systematically investigate how spurious correlation in the training set impacts OOD detection. Our results suggest that the detection performance is severely worsened when the correlation between spurious features and labels is increased in the training set. We further show insights on detection methods that are more effective in reducing the impact of spurious correlation and provide theoretical analysis on why reliance on environmental features leads to high OOD detection error. Our work aims to facilitate a better understanding of OOD samples and their formalization, as well as the exploration of methods that enhance OOD detection.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Reduction of the electroweak correlation in the PDF updating by using the forward-backward asymmetry of Drell-Yan process

We propose a new observable for the measurement of the forward-backward asymmetry $(A_{FB})$ in Drell-Yan lepton production. At hadron colliders, the $A_{FB}$ distribution is sensitive to both the electroweak (EW) fundamental parameter $\sin^2 θ_{W}$, the weak mixing angle, and the parton distribution functions (PDFs). Hence, the determination of $\sin^2 θ_{W}$ and the updating of PDFs by directly using the same $A_{FB}$ spectrum are strongly correlated. This correlation would introduce large bias or uncertainty into both precise measurements of EW and PDF sectors. In this article, we show that the sensitivity of $A_{FB}$ on $\sin^2 θ_{W}$ is dominated by its average value around the $Z$ pole region, while the shape (or gradient) of the $A_{FB}$ spectrum is insensitive to $\sin^2 θ_{W}$ and contains important information on the PDF modeling. Accordingly, a new observable related to the gradient of the spectrum is introduced, and demonstrated to be able to significantly reduce the potential bias on the determination of $\sin^2 θ_{W}$ when updating the PDFs using the same $A_{FB}$ data.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Analyses of residual accelerations for TianQin based on the global MHD simulation

TianQin is a proposed space-based gravitational wave observatory. It is designed to detect the gravitational wave signals in the frequency range of 0.1 mHz -- 1 Hz. At a geocentric distance of $10^5$ km, the plasma in the earth magnetosphere will contribute as the main source of environmental noises. Here, we analyze the acceleration noises that are caused by the magnetic field of space plasma for the test mass of TianQin. The real solar wind data observed by the Advanced Composition Explorer are taken as the input of the magnetohydrodynamic simulation. The Space Weather Modeling Framework is used to simulate the global magnetosphere of the earth, from which we obtain the plasma and magnetic field parameters on the detector's orbits. We calculate the time series of the residual accelerations and the corresponding amplitude spectral densities on these orbit configurations. We find that the residual acceleration produced by the interaction between the TM's magnetic moment induced by the space magnetic field and the spacecraft magnetic field ($\bm{a}_{\rm M1}$) is the dominant term, which can approach $10^{-15}$ m/s$^2$/Hz$^{1/2}$ at $f \approx$ 0.2 mHz for the nominal values of the magnetic susceptibility ($χ_{\rm m} = 10^{-5}$) and the magnetic shielding factor ($ξ_{\rm m} = 10$) of the test mass. The ratios between the amplitude spectral density of the acceleration noise caused by the space magnetic field and the preliminary goal of the inertial sensor are 0.38 and 0.08 at 1 mHz and 10 mHz, respectively. We discuss the further reduction of this acceleration noise by decreasing $χ_{\rm m}$ and/or increasing $ξ_{\rm m}$ in the future instrumentation development for TianQin.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Cost-effectiveness Analysis of Antiepidemic Policies and Global Situation Assessment of COVID-19

With a two-layer contact-dispersion model and data in China, we analyze the cost-effectiveness of three types of antiepidemic measures for COVID-19: regular epidemiological control, local social interaction control, and inter-city travel restriction. We find that: 1) intercity travel restriction has minimal or even negative effect compared to the other two at the national level; 2) the time of reaching turning point is independent of the current number of cases, and only related to the enforcement stringency of epidemiological control and social interaction control measures; 3) strong enforcement at the early stage is the only opportunity to maximize both antiepidemic effectiveness and cost-effectiveness; 4) mediocre stringency of social interaction measures is the worst choice. Subsequently, we cluster countries/regions into four groups based on their control measures and provide situation assessment and policy suggestions for each group.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation

We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces such as manipulation of deformable objects. Planning is performed in a low-dimensional latent state space that embeds images. We define and implement a Latent Space Roadmap (LSR) which is a graph-based structure that globally captures the latent system dynamics. Our framework consists of two main components: a Visual Foresight Module (VFM) that generates a visual plan as a sequence of images, and an Action Proposal Network (APN) that predicts the actions between them. We show the effectiveness of the method on a simulated box stacking task as well as a T-shirt folding task performed with a real robot.

0 citations0 reviewsNo code linkedOpen access