BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Tian Gao

Tian Gao appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Machine LearningArtificial IntelligenceComputation and Languagecond-mat.otherphysics.chem-phComputationComputer Visioncond-mat.supr-conInformation Retrievalmath.OCquant-ph

Catalog footprint

What is connected

13works
11topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

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

Published work

13 published item(s)

preprint2026arXiv

Reflections and New Directions for Human-Centered Large Language Models

Large Language Models (LLMs) are increasingly shaping the private and professional lives of users, with numerous applications in business, education, finance, healthcare, law, and science. With this rise in global influence comes greater urgency to build, evaluate, and deploy these systems in a manner that prioritizes not only technical capabilities but also human priorities. This work presents a framework for developing Human-Centered Large Language Models (HCLLMs), which integrates perspectives from Natural Language Processing (NLP), Human-Computer Interaction (HCI), and responsible AI. Considering the ethics, economics, and technical objectives of language modeling, we argue that model developers need to address human concerns, preferences, values, and goals, not only during a cursory post-training stage, but rather with rigor and care at every stage of the pipeline. This paper offers human-centered insights and recommendations for developers at each stage, from system design to data sourcing, model training, evaluation, and responsible deployment. Then we conclude with a case study, applying these insights to understand the future of work with HCLLMs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Image Feature Information Extraction for Interest Point Detection: A Review

Interest point detection is one of the most fundamental and critical problems in computer vision and image processing. In this paper, we carry out a comprehensive review on image feature information (IFI) extraction techniques for interest point detection. To systematically introduce how the existing interest point detection methods extract IFI from an input image, we propose a taxonomy of the IFI extraction techniques for interest point detection. According to this taxonomy, we discuss different types of IFI extraction techniques for interest point detection. Furthermore, we identify the main unresolved issues related to the existing IFI extraction techniques for interest point detection and any interest point detection methods that have not been discussed before. The existing popular datasets and evaluation standards are provided and the performances for eighteen state-of-the-art approaches are evaluated and discussed. Moreover, future research directions on IFI extraction techniques for interest point detection are elaborated.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network

Neural operators have recently become popular tools for designing solution maps between function spaces in the form of neural networks. Differently from classical scientific machine learning approaches that learn parameters of a known partial differential equation (PDE) for a single instance of the input parameters at a fixed resolution, neural operators approximate the solution map of a family of PDEs. Despite their success, the uses of neural operators are so far restricted to relatively shallow neural networks and confined to learning hidden governing laws. In this work, we propose a novel nonlocal neural operator, which we refer to as nonlocal kernel network (NKN), that is resolution independent, characterized by deep neural networks, and capable of handling a variety of tasks such as learning governing equations and classifying images. Our NKN stems from the interpretation of the neural network as a discrete nonlocal diffusion reaction equation that, in the limit of infinite layers, is equivalent to a parabolic nonlocal equation, whose stability is analyzed via nonlocal vector calculus. The resemblance with integral forms of neural operators allows NKNs to capture long-range dependencies in the feature space, while the continuous treatment of node-to-node interactions makes NKNs resolution independent. The resemblance with neural ODEs, reinterpreted in a nonlocal sense, and the stable network dynamics between layers allow for generalization of NKN's optimal parameters from shallow to deep networks. This fact enables the use of shallow-to-deep initialization techniques. Our tests show that NKNs outperform baseline methods in both learning governing equations and image classification tasks and generalize well to different resolutions and depths.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning

It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods. We propose a novel phasic approach by alternating online RL and offline SL for tackling sparse-reward goal-conditioned problems. In the online phase, we perform RL training and collect rollout data while in the offline phase, we perform SL on those successful trajectories from the dataset. To further improve sample efficiency, we adopt additional techniques in the online phase including task reduction to generate more feasible trajectories and a value-difference-based intrinsic reward to alleviate the sparse-reward issue. We call this overall algorithm, PhAsic self-Imitative Reduction (PAIR). PAIR substantially outperforms both non-phasic RL and phasic SL baselines on sparse-reward goal-conditioned robotic control problems, including a challenging stacking task. PAIR is the first RL method that learns to stack 6 cubes with only 0/1 success rewards from scratch.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Type-augmented Relation Prediction in Knowledge Graphs

Knowledge graphs (KGs) are of great importance to many real world applications, but they generally suffer from incomplete information in the form of missing relations between entities. Knowledge graph completion (also known as relation prediction) is the task of inferring missing facts given existing ones. Most of the existing work is proposed by maximizing the likelihood of observed instance-level triples. Not much attention, however, is paid to the ontological information, such as type information of entities and relations. In this work, we propose a type-augmented relation prediction (TaRP) method, where we apply both the type information and instance-level information for relation prediction. In particular, type information and instance-level information are encoded as prior probabilities and likelihoods of relations respectively, and are combined by following Bayes' rule. Our proposed TaRP method achieves significantly better performance than state-of-the-art methods on four benchmark datasets: FB15K, FB15K-237, YAGO26K-906, and DB111K-174. In addition, we show that TaRP achieves significantly improved data efficiency. More importantly, the type information extracted from a specific dataset can generalize well to other datasets through the proposed TaRP model.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

"And the Winner Is...": Dynamic Lotteries for Multi-group Fairness-Aware Recommendation

As recommender systems are being designed and deployed for an increasing number of socially-consequential applications, it has become important to consider what properties of fairness these systems exhibit. There has been considerable research on recommendation fairness. However, we argue that the previous literature has been based on simple, uniform and often uni-dimensional notions of fairness assumptions that do not recognize the real-world complexities of fairness-aware applications. In this paper, we explicitly represent the design decisions that enter into the trade-off between accuracy and fairness across multiply-defined and intersecting protected groups, supporting multiple fairness metrics. The framework also allows the recommender to adjust its performance based on the historical view of recommendations that have been delivered over a time horizon, dynamically rebalancing between fairness concerns. Within this framework, we formulate lottery-based mechanisms for choosing between fairness concerns, and demonstrate their performance in two recommendation domains.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Multi-Channel Neural Graphical Event Model with Negative Evidence

Event datasets are sequences of events of various types occurring irregularly over the time-line, and they are increasingly prevalent in numerous domains. Existing work for modeling events using conditional intensities rely on either using some underlying parametric form to capture historical dependencies, or on non-parametric models that focus primarily on tasks such as prediction. We propose a non-parametric deep neural network approach in order to estimate the underlying intensity functions. We use a novel multi-channel RNN that optimally reinforces the negative evidence of no observable events with the introduction of fake event epochs within each consecutive inter-event interval. We evaluate our method against state-of-the-art baselines on model fitting tasks as gauged by log-likelihood. Through experiments on both synthetic and real-world datasets, we find that our proposed approach outperforms existing baselines on most of the datasets studied.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Characterization of Overlap in Observational Studies

Overlap between treatment groups is required for non-parametric estimation of causal effects. If a subgroup of subjects always receives the same intervention, we cannot estimate the effect of intervention changes on that subgroup without further assumptions. When overlap does not hold globally, characterizing local regions of overlap can inform the relevance of causal conclusions for new subjects, and can help guide additional data collection. To have impact, these descriptions must be interpretable for downstream users who are not machine learning experts, such as policy makers. We formalize overlap estimation as a problem of finding minimum volume sets subject to coverage constraints and reduce this problem to binary classification with Boolean rule classifiers. We then generalize this method to estimate overlap in off-policy policy evaluation. In several real-world applications, we demonstrate that these rules have comparable accuracy to black-box estimators and provide intuitive and informative explanations that can inform policy making.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation

Introducing common sense to natural language understanding systems has received increasing research attention. It remains a fundamental question on how to evaluate whether a system has a sense making capability. Existing benchmarks measures commonsense knowledge indirectly and without explanation. In this paper, we release a benchmark to directly test whether a system can differentiate natural language statements that make sense from those that do not make sense. In addition, a system is asked to identify the most crucial reason why a statement does not make sense. We evaluate models trained over large-scale language modeling tasks as well as human performance, showing that there are different challenges for system sense making.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A Derivative-Free Trust-Region Algorithm for Reliability-Based Optimization

In this note, we present a derivative-free trust-region (TR) algorithm for reliability based optimization (RBO) problems. The proposed algorithm consists of solving a set of subproblems, in which simple surrogate models of the reliability constraints are constructed and used in solving the subproblems. Taking advantage of the special structure of the RBO problems, we employ a sample reweighting method to evaluate the failure probabilities, which constructs the surrogate for the reliability constraints by performing only a single full reliability evaluation in each iteration. With numerical experiments, we illustrate that the proposed algorithm is competitive against existing methods.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Mn-doping induced ferromagnetism and enhanced superconductivity in Bi_4-x Mn_x O_4 S_3 (0.075 < = x < = 0.15)

We demonstrate that Mn-doping in the layered sulfides Bi_4O_4S_3 leads to stable Bi_4-x Mn_x O_4 S_3 compounds that exhibit both long-range ferromagnetism and enhanced superconductivity for 0.075 < = x < = 0.15, with a possible record superconducting transition temperature (T_c) = 15 K among all BiS_2-based superconductors. We conjecture that the coexistence of superconductivity and ferromagnetism may be attributed to Mn-doping in the spacer Bi2O2 layers away from the superconducting BiS_2 layers, whereas the enhancement of T_c may be due to excess electron transfer to BiS_2 from the Mn4+/Mn3+-substitutions in Bi_2O_2. This notion is empirically corroborated by the increased electron-carrier densities upon Mn doping, and by further studies of the Bi_4-x A_x O_4 S_3 compounds (A = Co, Ni; x = 0.1, 0.125), where the T_c values remain comparable to that of the undoped Bi_4O_4S_3 system (= 4.5 K) due to lack of 4+ valences in either Co or Ni ions for excess electron transfer to the BiS_2 layers. These findings therefore shed new light on feasible pathways to enhance the T_c values of BiS_2-based superconductors.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Possible magnetism based on orbital motion of protons in ice

A peak anomaly is observed in the magnetic susceptibility as a function of temperature in solid H2O near Tp=60 K. At external magnetic fields below 2 kOe, Tp becomes positive in the temperature range between 45 and 66 K. The magnetic field dependence of the susceptibility in the same temperature range exhibits an inverted ferromagnetic hysteretic loop superimposed on top of the diamagnetic signature of ice at fields below 600 Oe. We suggest that a fraction of protons that are capable of undergoing correlated tunneling in a hexagonal path without disrupting the stoichiometry of the lattice create an induced magnetic field opposite to the induced magnetic field created by the electrons upon application of an external field which counters the overall diamagnetism of the material.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Dielectric Anomaly in Ice near 20 K; Evidence of Macroscopic Quantum Phenomena

H2O is one of the most important substances needed in sustaining life; but yet not much is known about its ground state. Here, a previously unidentified anomaly is identified in the form of a minimum in the imaginary part of the dielectric constant with respect to temperature near 20 K while the real part remains monotonic. Isothermal dispersion and absorption measurements show coinciding results. For the case of heavy ice (D2O), no anomaly was identified confirming an apparent isotope effect. Concerted quantum tunneling of protons is believed to be the main cause behind the reported anomaly. Our findings identify another system that exhibits macroscopic quantum phenomena of which rarely occur in nature.

0 citations0 reviewsNo code linkedOpen access