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

Zhong Li

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

ResearcherUnclaimed source record
Computer VisionArtificial IntelligenceGraphicsMachine LearningCryptography and SecurityNetworking and Internet Architecturenlin.CDOther Computer Sciencephysics.soc-phSocial and Information Networks

Catalog footprint

What is connected

11works
10topics
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

11 published item(s)

preprint2026arXiv

MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling

Optimization modeling translates real decision-making problems into mathematical optimization models and solver-executable implementations. Although language models are increasingly used to generate optimization formulations and solver code, existing benchmarks are almost entirely text-only. This omits many optimization-modeling tasks that arise in operational practice, where requirements are described in text but instance information is conveyed through visual artifacts such as tables, graphs, maps, schedules, and dashboards. We introduce multimodal optimization modeling, a benchmark setting in which models must construct both a mathematical formulation and executable solver code from a text-and-visual problem specification. To evaluate this setting, we develop a solver-grounded framework that generates structured optimization instances, verifies each with an exact solver, and builds both the model-facing inputs and hidden reference files from the same verified source. We instantiate the framework as MM-OptBench, a benchmark of 780 solver-verified instances spanning 6 optimization families, 26 subcategories, and 3 structural difficulty levels. We evaluate 9 multimodal large language models (MLLMs), including 6 frontier general-purpose models and 3 math-specialized models, with aggregate, family-level, difficulty-level, and failure-mode analyses. The results show that the task remains far from solved: the best two models reach 52.1% and 51.3% pass@1, while on average across the six general-purpose MLLMs, pass@1 is 43.4% on easy instances and 15.9% on hard instances. All three math-specialized MLLMs solve 0/780 instances. Failure attribution shows that errors arise both when extracting instance data from text and visuals and when turning extracted data into solver-correct formulations and code. MM-OptBench provides a testbed for solver-grounded, decision-oriented multimodal intelligence.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization Modeling

Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an artifact may agree numerically while still changing the underlying optimization semantics. We formulate this issue as \emph{optimization-modeling hallucination detection}, namely structural consistency auditing over the problem description, symbolic model, and solver implementation. We develop, to our knowledge, the first fine-grained hallucination taxonomy specifically for optimization modeling, spanning objective, variable, constraint, and implementation failures. We use this taxonomy to design OptArgus, a multi-agent detector with conductor routing, specialist auditors, and evidence consolidation. To evaluate this setting, we introduce a three-part benchmark suite with $484$ clean artifacts, $1266$ controlled injected artifacts, and $6292$ natural LLM-generated artifacts. Against a matched single-agent baseline, OptArgus produces fewer false alarms on clean artifacts, more accurate top-ranked localization on controlled single-error cases, and stronger detection on natural model outputs. Together, these contributions turn optimization-modeling hallucination detection into a concrete empirical problem and suggest that modular, taxonomy-grounded auditing is a practical route to more reliable optimization modeling.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Incremental Unsupervised Feature Selection for Dynamic Incomplete Multi-view Data

Multi-view unsupervised feature selection has been proven to be efficient in reducing the dimensionality of multi-view unlabeled data with high dimensions. The previous methods assume all of the views are complete. However, in real applications, the multi-view data are often incomplete, i.e., some views of instances are missing, which will result in the failure of these methods. Besides, while the data arrive in form of streams, these existing methods will suffer the issues of high storage cost and expensive computation time. To address these issues, we propose an Incremental Incomplete Multi-view Unsupervised Feature Selection method (I$^2$MUFS) on incomplete multi-view streaming data. By jointly considering the consistent and complementary information across different views, I$^2$MUFS embeds the unsupervised feature selection into an extended weighted non-negative matrix factorization model, which can learn a consensus clustering indicator matrix and fuse different latent feature matrices with adaptive view weights. Furthermore, we introduce the incremental leaning mechanisms to develop an alternative iterative algorithm, where the feature selection matrix is incrementally updated, rather than recomputing on the entire updated data from scratch. A series of experiments are conducted to verify the effectiveness of the proposed method by comparing with several state-of-the-art methods. The experimental results demonstrate the effectiveness and efficiency of the proposed method in terms of the clustering metrics and the computational cost.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field

In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes. In our approach, a 3D scene is represented as a light field, i.e., a set of rays, each of which has a corresponding color when reaching the image plane. For efficient novel view rendering, we adopt a two-plane parameterization of the light field, where each ray is characterized by a 4D parameter. We then formulate the light field as a 4D function that maps 4D coordinates to corresponding color values. We train a deep fully connected network to optimize this implicit function and memorize the 3D scene. Then, the scene-specific model is used to synthesize novel views. Different from previous light field approaches which require dense view sampling to reliably render novel views, our method can render novel views by sampling rays and querying the color for each ray from the network directly, thus enabling high-quality light field rendering with a sparser set of training images. Per-ray depth can be optionally predicted by the network, thus enabling applications such as auto refocus. Our novel view synthesis results are comparable to the state-of-the-arts, and even superior in some challenging scenes with refraction and reflection. We achieve this while maintaining an interactive frame rate and a small memory footprint.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Complexity Measures for Neural Networks with General Activation Functions Using Path-based Norms

A simple approach is proposed to obtain complexity controls for neural networks with general activation functions. The approach is motivated by approximating the general activation functions with one-dimensional ReLU networks, which reduces the problem to the complexity controls of ReLU networks. Specifically, we consider two-layer networks and deep residual networks, for which path-based norms are derived to control complexities. We also provide preliminary analyses of the function spaces induced by these norms and a priori estimates of the corresponding regularized estimators.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

PIV-Based 3D Fluid Flow Reconstruction Using Light Field Camera

Particle Imaging Velocimetry (PIV) estimates the flow of fluid by analyzing the motion of injected particles. The problem is challenging as the particles lie at different depths but have similar appearance and tracking a large number of particles is particularly difficult. In this paper, we present a PIV solution that uses densely sampled light field to reconstruct and track 3D particles. We exploit the refocusing capability and focal symmetry constraint of the light field for reliable particle depth estimation. We further propose a new motion-constrained optical flow estimation scheme by enforcing local motion rigidity and the Navier-Stoke constraint. Comprehensive experiments on synthetic and real experiments show that using a single light field camera, our technique can recover dense and accurate 3D fluid flows in small to medium volumes.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Talking-head Generation with Rhythmic Head Motion

When people deliver a speech, they naturally move heads, and this rhythmic head motion conveys prosodic information. However, generating a lip-synced video while moving head naturally is challenging. While remarkably successful, existing works either generate still talkingface videos or rely on landmark/video frames as sparse/dense mapping guidance to generate head movements, which leads to unrealistic or uncontrollable video synthesis. To overcome the limitations, we propose a 3D-aware generative network along with a hybrid embedding module and a non-linear composition module. Through modeling the head motion and facial expressions1 explicitly, manipulating 3D animation carefully, and embedding reference images dynamically, our approach achieves controllable, photo-realistic, and temporally coherent talking-head videos with natural head movements. Thoughtful experiments on several standard benchmarks demonstrate that our method achieves significantly better results than the state-of-the-art methods in both quantitative and qualitative comparisons. The code is available on https://github.com/ lelechen63/Talking-head-Generation-with-Rhythmic-Head-Motion.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Privately Information Sharing with Delusive Paths for Data Forwarding in Vehicular Networks

We discuss how to efficiently forward data in vehicular networks. Existing solutions do not make full use of trajectory planning of nearby vehicles, or social attributes. The development of onboard navigation system provides drivers some traveling route information. The main novelty of our approach is to envision sharing partial traveling information to the encountered vehicles for better service. Our data forwarding algorithm utilizes this lightweight information under the delusive paths privacy preservation together with the social community structure in vehicular networks. We assume that data transmission is carried by vehicles and road side units (RSUs), while cellular network manages and coordinates relevant global information. The approximate destination set is the set of RSUs that are often passed by the destination vehicle. RSU importance is raised by summing encounter ratios of RSUs in the same connected component. We first define a concept of space-time approachability which is derived from shared partial traveling route and encounter information. It describes the capability of a vehicle to advance messages toward destination. Then, we design a novel data forwarding algorithm, called approachability based algorithm, which combines the space-time approachability with the social community attribute in vehicular networks. We evaluate our approachability based algorithm on data sets from San Francisco Cabspotting and Shanghai Taxi Movement. Results show that the partially shared traveling information plays a positive role in data forwarding in vehicular networks. Approachability based data forwarding algorithm achieves a better performance than existing social based algorithms in vehicular networks.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Rule Optimization for Real-Time Query Service in Software-Defined Internet of Vehicles

Internet of Vehicles (IoV) has recently gained considerable attentions from both industry and research communities since the development of communication technology and smart city. However, a proprietary and closed way of operating hardwares in network equipments slows down the progress of new services deployment and extension in IoV. Moreover, the tightly coupled control and data planes in traditional networks significantly increase the complexity and cost of network management. By proposing a novel architecture, called Software-Defined Internet of Vehicles (SDIV), we adopt the software-defined network (SDN) architecture to address these problems by leveraging its separation of the control plane from the data plane and a uniform way to configure heterogeneous switches. However, the characteristics of IoV introduce the very challenges in rule installation due to the limited size of Flow Tables at OpenFlow-enabled switches which are the main component of SDN. It is necessary to build compact Flow Tables for the scalability of IoV. Accordingly, we develop a rule optimization approach for real-time query service in SDIV. Specifically, we separate wired data plane from wireless data plane and use multicast address in wireless data plane. Furthermore, we introduce a destination-driven model in wired data plane for reducing the number of rules at switches. Experiments show that our rule optimization strategy reduces the number of rules while keeping the performance of data transmission.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Improving Data Forwarding in Mobile Social Networks with Infrastructure Support: A Space-Crossing Community Approach

In this paper, we study two tightly coupled issues: space-crossing community detection and its influence on data forwarding in Mobile Social Networks (MSNs) by taking the hybrid underlying networks with infrastructure support into consideration. The hybrid underlying network is composed of large numbers of mobile users and a small portion of Access Points (APs). Because APs can facilitate the communication among long-distance nodes, the concept of physical proximity community can be extended to be one across the geographical space. In this work, we first investigate a space-crossing community detection method for MSNs. Based on the detection results, we design a novel data forwarding algorithm SAAS (Social Attraction and AP Spreading), and show how to exploit the space-crossing communities to improve the data forwarding efficiency. We evaluate our SAAS algorithm on real-life data from MIT Reality Mining and UIM. Results show that space-crossing community plays a positive role in data forwarding in MSNs in terms of deliver ratio and delay. Based on this new type of community, SAAS achieves a better performance than existing social community-based data forwarding algorithms in practice, including Bubble Rap and Nguyen's Routing algorithms.

0 citations0 reviewsNo code linkedOpen access