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

Fang Wang

Fang Wang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and LanguageArtificial IntelligenceMachine LearningComputer VisionCryptography and Securityeess.SYHardware Architecturemath.APmath.NANeural and Evolutionary ComputingNumerical Analysisphysics.opticsSystems and Control

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
0followers
13topics
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

12 published item(s)

preprint2026arXiv

Convergence Analysis of Weighted Median Opinion Dynamics with Higher-Order Effects

The weighted median mechanism provides a robust alternative to weighted averaging in opinion dynamics. Existing models, however, are predominantly formulated on pairwise interaction graphs, which limits their ability to represent higher-order environmental effects. In this work, a generalized weighted median opinion dynamics model is proposed by incorporating high-order interactions through a simplicial complex representation. The resulting dynamics are formulated as a nonlinear discrete-time system with synchronous opinion updates, in which intrinsic agent interactions and external environmental influences are jointly modeled. Sufficient conditions for asymptotic consensus are established for heterogeneous systems composed of opinionated and unopinionated agents. For homogeneous opinionated systems, convergence and convergence rates are rigorously analyzed using the Banach fixed-point theorem. Theoretical results demonstrate the stability of the proposed dynamics under mild conditions, and numerical simulations are provided to corroborate the analysis. This work extends median-based opinion dynamics to high-order interaction settings and provides a system-level framework for stability and consensus analysis.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

EndPrompt: Efficient Long-Context Extension via Terminal Anchoring

Extending the context window of large language models typically requires training on sequences at the target length, incurring quadratic memory and computational costs that make long-context adaptation expensive and difficult to reproduce. We propose EndPrompt, a method that achieves effective context extension using only short training sequences. The core insight is that exposing a model to long-range relative positional distances does not require constructing full-length inputs: we preserve the original short context as an intact first segment and append a brief terminal prompt as a second segment, assigning it positional indices near the target context length. This two-segment construction introduces both local and long-range relative distances within a short physical sequence while maintaining the semantic continuity of the training text--a property absent in chunk-based simulation approaches that split contiguous context. We provide a theoretical analysis grounded in Rotary Position Embedding and the Bernstein inequality, showing that position interpolation induces a rigorous smoothness constraint over the attention function, with shared Transformer parameters further suppressing unstable extrapolation to unobserved intermediate distances. Applied to LLaMA-family models extending the context window from 8K to 64K, EndPrompt achieves an average RULER score of 76.03 and the highest average on LongBench, surpassing LCEG (72.24), LongLoRA (72.95), and full-length fine-tuning (69.23) while requiring substantially less computation. These results demonstrate that long-context generalization can be induced from sparse positional supervision, challenging the prevailing assumption that dense long-sequence training is necessary for reliable context-window extension. The code is available at https://github.com/clx1415926/EndPrompt.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Logic-Guided Multistage Inference for Explainable Multidefendant Judgment Prediction

Crime disrupts societal stability, making law essential for balance. In multidefendant cases, assigning responsibility is complex and challenges fairness, requiring precise role differentiation. However, judicial phrasing often obscures the roles of the defendants, hindering effective AI-driven analyses. To address this issue, we incorporate sentencing logic into a pretrained Transformer encoder framework to enhance the intelligent assistance in multidefendant cases while ensuring legal interpretability. Within this framework an oriented masking mechanism clarifies roles and a comparative data construction strategy improves the model's sensitivity to culpability distinctions between principals and accomplices. Predicted guilt labels are further incorporated into a regression model through broadcasting, consolidating crime descriptions and court views. Our proposed masked multistage inference (MMSI) framework, evaluated on the custom IMLJP dataset for intentional injury cases, achieves significant accuracy improvements, outperforming baselines in role-based culpability differentiation. This work offers a robust solution for enhancing intelligent judicial systems, with publicly code available.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Measuring Maximum Activations in Open Large Language Models

The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and massive activations on pre-2024 LLaMA-style models, and the downstream activation-quantization stack inherits that picture without revisiting it for the post-LLaMA open-model boom. We ask the deployment-oriented question: how large can activations get in modern open LLMs, and how does this magnitude vary across families, generations, and training stages? Under a unified pipeline (5,000-sample multi-domain corpus, family-specific tokenization, identical hooks across embeddings, hidden states, attention, MLP/MoE, SwiGLU gates, and final norm), we measure global and layerwise maxima on 27 checkpoints from 8 open families spanning dense, MoE, vision-language, intermediate-training, and instruction-tuned variants. We find that (i) global maxima span over nearly four orders of magnitude at comparable parameter counts, with Qwen3.5 and MoE checkpoints in the 10^2 to 10^3 range and Gemma3-27B-it reaching ~7 x 10^5; (ii) cross-family and cross-generation comparisons break simple monotonic scaling; and (iii) MoE checkpoints exhibit 14.0-23.4x lower peaks than matched-scale dense counterparts, while the residual stream carries the global maximum in 22/24 checkpoints. A lightweight INT-8 sanity check shows that measured maxima co-vary with low-bit reconstruction error via activation-scale selection. We conclude that maximum activation magnitude is a model property tied to family, architecture, and training stage - not a simple byproduct of size - and should be measured and reported alongside any open-weight release before low-bit deployment. The code is publicly available at https://github.com/clx1415926/Max_act_llm.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

GPBiLQ and GPQMR: Two iterative methods for unsymmetric partitioned linear systems

We introduce two iterative methods, GPBiLQ and GPQMR, for solving unsymmetric partitioned linear systems. The basic mechanism underlying GPBiLQ and GPQMR is a novel simultaneous tridiagonalization via biorthogonality that allows for short-recurrence iterative schemes. Similar to the biconjugate gradient method, it is possible to develop another method, GPBiCG, whose iterate (if it exists) can be obtained inexpensively from the GPBiLQ iterate. Whereas the iterate of GPBiCG may not exist, the iterates of GPBiLQ and GPQMR are always well defined as long as the biorthogonal tridiagonal reduction process does not break down. We discuss connections between the proposed methods and some existing methods, and give numerical experiments to illustrate the performance of the proposed methods.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Graph Neural Prompting with Large Language Models

Large language models (LLMs) have shown remarkable generalization capability with exceptional performance in various language modeling tasks. However, they still exhibit inherent limitations in precisely capturing and returning grounded knowledge. While existing work has explored utilizing knowledge graphs (KGs) to enhance language modeling via joint training and customized model architectures, applying this to LLMs is problematic owing to their large number of parameters and high computational cost. Therefore, how to enhance pre-trained LLMs using grounded knowledge, e.g., retrieval-augmented generation, remains an open question. In this work, we propose Graph Neural Prompting (GNP), a novel plug-and-play method to assist pre-trained LLMs in learning beneficial knowledge from KGs. GNP encompasses various designs, including a standard graph neural network encoder, a cross-modality pooling module, a domain projector, and a self-supervised link prediction objective. Extensive experiments on multiple datasets demonstrate the superiority of GNP on both commonsense and biomedical reasoning tasks across different LLM sizes and settings. Code is available at https://github.com/meettyj/GNP.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Investigation of Bare-bones Algorithms from Quantum Perspective: A Quantum Dynamical Global Optimizer

Recent decades, the emergence of numerous novel algorithms makes it a gimmick to propose an intelligent optimization system based on metaphor, and hinders researchers from exploring the essence of search behavior in algorithms. However, it is difficult to directly discuss the search behavior of an intelligent optimization algorithm, since there are so many kinds of intelligent schemes. To address this problem, an intelligent optimization system is regarded as a simulated physical optimization system in this paper. The dynamic search behavior of such a simplified physical optimization system are investigated with quantum theory. To achieve this goal, the Schroedinger equation is employed as the dynamics equation of the optimization algorithm, which is used to describe dynamic search behaviours in the evolution process with quantum theory. Moreover, to explore the basic behaviour of the optimization system, the optimization problem is assumed to be decomposed and approximated. Correspondingly, the basic search behaviour is derived, which constitutes the basic iterative process of a simple optimization system. The basic iterative process is compared with some classical bare-bones schemes to verify the similarity of search behavior under different metaphors. The search strategies of these bare bones algorithms are analyzed through experiments.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Training Entire-Space Models for Target-oriented Opinion Words Extraction

Target-oriented opinion words extraction (TOWE) is a subtask of aspect-based sentiment analysis (ABSA). Given a sentence and an aspect term occurring in the sentence, TOWE extracts the corresponding opinion words for the aspect term. TOWE has two types of instance. In the first type, aspect terms are associated with at least one opinion word, while in the second type, aspect terms do not have corresponding opinion words. However, previous researches trained and evaluated their models with only the first type of instance, resulting in a sample selection bias problem. Specifically, TOWE models were trained with only the first type of instance, while these models would be utilized to make inference on the entire space with both the first type of instance and the second type of instance. Thus, the generalization performance will be hurt. Moreover, the performance of these models on the first type of instance cannot reflect their performance on entire space. To validate the sample selection bias problem, four popular TOWE datasets containing only aspect terms associated with at least one opinion word are extended and additionally include aspect terms without corresponding opinion words. Experimental results on these datasets show that training TOWE models on entire space will significantly improve model performance and evaluating TOWE models only on the first type of instance will overestimate model performance.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans

Accurately segmenting teeth and identifying the corresponding anatomical landmarks on dental mesh models are essential in computer-aided orthodontic treatment. Manually performing these two tasks is time-consuming, tedious, and, more importantly, highly dependent on orthodontists' experiences due to the abnormality and large-scale variance of patients' teeth. Some machine learning-based methods have been designed and applied in the orthodontic field to automatically segment dental meshes (e.g., intraoral scans). In contrast, the number of studies on tooth landmark localization is still limited. This paper proposes a two-stage framework based on mesh deep learning (called TS-MDL) for joint tooth labeling and landmark identification on raw intraoral scans. Our TS-MDL first adopts an end-to-end \emph{i}MeshSegNet method (i.e., a variant of the existing MeshSegNet with both improved accuracy and efficiency) to label each tooth on the downsampled scan. Guided by the segmentation outputs, our TS-MDL further selects each tooth's region of interest (ROI) on the original mesh to construct a light-weight variant of the pioneering PointNet (i.e., PointNet-Reg) for regressing the corresponding landmark heatmaps. Our TS-MDL was evaluated on a real-clinical dataset, showing promising segmentation and localization performance. Specifically, \emph{i}MeshSegNet in the first stage of TS-MDL reached an averaged Dice similarity coefficient (DSC) at \textcolor[rgb]{0,0,0}{$0.964\pm0.054$}, significantly outperforming the original MeshSegNet. In the second stage, PointNet-Reg achieved a mean absolute error (MAE) of $0.597\pm0.761 \, mm$ in distances between the prediction and ground truth for $66$ landmarks, which is superior compared with other networks for landmark detection. All these results suggest the potential usage of our TS-MDL in orthodontics.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Estimation of transmitted wavefronts at defocused positions in a broad bandwidth range

Wavefront aberrations can reflect the imaging quality of high-performance optical systems better than geometric aberrations. Although laser interferometers have emerged as the main tool for measurement of transmitted wavefronts, their application is greatly limited, as they are typically designed for operation at specific wavelengths. In a previous study, we proposed a method for determining the wavefront transmitted by an optical system at any wavelength in a certain band. Although this method works well for most monochromatic systems, where the image plane is at the focal point for the transmission wavelength, for general multi-color systems, it is more practical to measure the wavefront at the defocused image plane. Hence, in this paper, we have developed a complete method for determining transmitted wavefronts in a broad bandwidth at any defocused position, enabling wavefront measurements for multi-color systems. Here, we assume that in small ranges, the Zernike coefficients have a linear relationship with position, such that Zernike coefficients at defocused positions can be derived from measurements performed at the focal point. We conducted experiments to verify these assumptions, validating the new method. The experimental setup has been improved so that it can handle multi-color systems, and a detailed experimental process is summarized. With this technique, application of broadband transmission wavefront measurement can be extended to most general optical systems, which is of great significance for characterization of achromatic and apochromatic optical lenses.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

IRO: Integrity and Reliability Enhanced Ring ORAM

Memory security and reliability are two of the major design concerns in cloud computing systems. State-of-the-art memory security-reliability co-designs (e.g. Synergy) have achieved a good balance on performance, confidentiality, integrity, and reliability. However, these works merely rely on encryption to ensure data confidentiality, which has been proven unable to prevent information leakage from memory access patterns. Ring ORAM is an attractive confidential protection protocol to hide memory access patterns to the untrusted storage system. Unfortunately, it does not compatible with the security-reliability co-designs. A forced combination would result in more severe performance loss. In this paper, we propose IRO, an Integrity and Reliability enhanced Ring ORAM design. To reduce the overhead of integrity verification, we propose a low overhead integrity tree RIT and use a Minimum Update Subtree Tree (MUST) to reduce metadata update overhead. To improve memory reliability, we present Secure Replication to provide channel-level error resilience for the ORAM tree and use the mirrored channel technique to guarantee the reliability of the MUST. Last, we use the error correction pointer (ECP) to repair permanent memory cell fault to further improve device reliability and lifetime. A compact metadata design is used to reduce the storage and consulting overhead of the ECP. IRO provides strong security and reliability guarantees, while the resulting storage and performance overhead is very small. Our evaluation shows that IRO only increases 7.54% execution time on average over the Baseline under two channels four AES-GCM units setting. With enough AES-GCM units to perform concurrent MAC computing, IRO can reduce 2.14% execution time of the Baseline.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Large Time Behavior and Diffusion Limit for a System of Balance Laws From Chemotaxis in Multi-dimensions

We consider the Cauchy problem for a system of balance laws derived from a chemotaxis model with singular sensitivity in multiple space dimensions. Utilizing energy methods, we first prove the global well-posedness of classical solutions to the Cauchy problem when only the energy of the first order spatial derivatives of the initial data is sufficiently small, and the solutions are shown to converge to the prescribed constant equilibrium states as time goes to infinity. Then we prove that the solutions of the fully dissipative model converge to those of the corresponding partially dissipative model when the chemical diffusion coefficient tends to zero.

0 citations0 reviewsNo code linkedOpen access