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

Zhicheng Liu

Zhicheng Liu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningComputation and LanguageComputer VisionData Structures and AlgorithmsDatabasesHuman-Computer Interactionphysics.soc-phSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
6works
0followers
8topics
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

6 published item(s)

preprint2026arXiv

NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics

The ability to derive precise spatial and physical insights is a cornerstone of vision-language models (VLMs), yet their poor performances in related spatial intelligence tasks such as physical reasoning remain a fundamental barrier. The community critically lacks a scientific analysis revealing whether VLMs faithfully reach answers or plausibly make guesses. This work aims to provide a fundamental understanding of how VLMs perceive the physical world, and utilize physical laws, while assessing the reliability of model confidence. We propose NICE and FACT, a dual-diagnostic paradigm that explicitly decomposes quantitative reasoning for kinematic physics: FACT diagnoses visual fidelity, physical law comprehension, and temporal grounding. NICE studies our novel neighborhood-informed calibration method and novel metrics to evaluate and calibrate confidence reliability. Evaluated across 6 latest state-of-the-art VLMs, we uncover that models fail to identify visual preconditions or utilize necessary physical laws to reach answers. This work highlights and establishes a standardized diagnostic paradigm to guide the development of faithful, physically-grounded VLMs.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

PanGu-$π$: Enhancing Language Model Architectures via Nonlinearity Compensation

The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which is definitely proved by a lot of work such as the famous GPT and Llama. However, large models often involve massive computational costs, and practical applications cannot afford such high prices. However, the method of constructing a strong model architecture for LLMs is rarely discussed. We first analyze the state-of-the-art language model architectures and observe the feature collapse problem. Based on the theoretical analysis, we propose that the nonlinearity is also very important for language models, which is usually studied in convolutional neural networks for vision tasks. The series informed activation function is then introduced with tiny calculations that can be ignored, and an augmented shortcut is further used to enhance the model nonlinearity. We then demonstrate that the proposed approach is significantly effective for enhancing the model nonlinearity through carefully designed ablations; thus, we present a new efficient model architecture for establishing modern, namely, PanGu-$π$. Experiments are then conducted using the same dataset and training strategy to compare PanGu-$π$ with state-of-the-art LLMs. The results show that PanGu-$π$-7B can achieve a comparable performance to that of benchmarks with about 10\% inference speed-up, and PanGu-$π$-1B can achieve state-of-the-art performance in terms of accuracy and efficiency. In addition, we have deployed PanGu-$π$-7B in the high-value domains of finance and law, developing an LLM named YunShan for practical application. The results show that YunShan can surpass other models with similar scales on benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

An improved approximation algorithm for maximizing a DR-submodular function over a convex set

Maximizing a DR-submodular function subject to a general convex set is an NP-hard problem arising from many applications in combinatorial optimization and machine learning. While it is highly desirable to design efficient approximation algorithms under this general setting where neither the objective function is monotonic nor the feasible set is down-closed, our main contribution is to present a 0.25-approximation Frank-Wolfe type of algorithm with a sub-exponential time-complexity under the value oracle model.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Survey on Sampling and Profiling over Big Data (Technical Report)

Due to the development of internet technology and computer science, data is exploding at an exponential rate. Big data brings us new opportunities and challenges. On the one hand, we can analyze and mine big data to discover hidden information and get more potential value. On the other hand, the 5V characteristic of big data, especially Volume which means large amount of data, brings challenges to storage and processing. For some traditional data mining algorithms, machine learning algorithms and data profiling tasks, it is very difficult to handle such a large amount of data. The large amount of data is highly demanding hardware resources and time consuming. Sampling methods can effectively reduce the amount of data and help speed up data processing. Hence, sampling technology has been widely studied and used in big data context, e.g., methods for determining sample size, combining sampling with big data processing frameworks. Data profiling is the activity that finds metadata of data set and has many use cases, e.g., performing data profiling tasks on relational data, graph data, and time series data for anomaly detection and data repair. However, data profiling is computationally expensive, especially for large data sets. Therefore, this paper focuses on researching sampling and profiling in big data context and investigates the application of sampling in different categories of data profiling tasks. From the experimental results of these studies, the results got from the sampled data are close to or even exceed the results of the full amount of data. Therefore, sampling technology plays an important role in the era of big data, and we also have reason to believe that sampling technology will become an indispensable step in big data processing in the future.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

ICE: Identify and Compare Event Sequence Sets through Multi-Scale Matrix and Unit Visualizations

Comparative analysis of event sequence data is essential in many application domains, such as website design and medical care. However, analysts often face two challenges: they may not always know which sets of event sequences in the data are useful to compare, and the comparison needs to be achieved at different granularity, due to the volume and complexity of the data. This paper presents, ICE, an interactive visualization that allows analysts to explore an event sequence dataset, and identify promising sets of event sequences to compare at both the pattern and sequence levels. More specifically, ICE incorporates a multi-level matrix-based visualization for browsing the entire dataset based on the prefixes and suffixes of sequences. To support comparison at multiple levels, ICE employs the unit visualization technique, and we further explore the design space of unit visualizations for event sequence comparison tasks. Finally, we demonstrate the effectiveness of ICE with three real-world datasets from different domains.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning Geo-Contextual Embeddings for Commuting Flow Prediction

Predicting commuting flows based on infrastructure and land-use information is critical for urban planning and public policy development. However, it is a challenging task given the complex patterns of commuting flows. Conventional models, such as gravity model, are mainly derived from physics principles and limited by their predictive power in real-world scenarios where many factors need to be considered. Meanwhile, most existing machine learning-based methods ignore the spatial correlations and fail to model the influence of nearby regions. To address these issues, we propose Geo-contextual Multitask Embedding Learner (GMEL), a model that captures the spatial correlations from geographic contextual information for commuting flow prediction. Specifically, we first construct a geo-adjacency network containing the geographic contextual information. Then, an attention mechanism is proposed based on the framework of graph attention network (GAT) to capture the spatial correlations and encode geographic contextual information to embedding space. Two separate GATs are used to model supply and demand characteristics. A multitask learning framework is used to introduce stronger restrictions and enhance the effectiveness of the embedding representation. Finally, a gradient boosting machine is trained based on the learned embeddings to predict commuting flows. We evaluate our model using real-world datasets from New York City and the experimental results demonstrate the effectiveness of our proposal against the state of the art.

0 citations0 reviewsNo code linkedOpen access