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

Jun Huang

Jun Huang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningComputation and LanguageComputer VisionArtificial IntelligenceNetworking and Internet Architecturephysics.app-phDistributed, Parallel, and Cluster Computingecon.EMeess.ASeess.IVMultimediaphysics.chem-phphysics.plasm-phProgramming Languagesq-fin.CPq-fin.RMSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
19works
0followers
17topics
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

19 published item(s)

preprint2026arXiv

Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models

Emerging multi-modal world models attempt to jointly generate videos across diverse modalities (e.g., RGB, depth, and mask), yet they fail to fully exploit the rich priors of existing foundation models. We propose $M^2$-REPA, the first representation alignment method tailored for multi-modal video generation. Our key insight is that foundation models trained on different modality spaces naturally capture distinct domain-specific priors, acting as complementary "experts." Specifically, we first decouple modality-specific features from the diffusion model's intermediate representations, then align each with its corresponding expert foundation model. To this end, we design two synergistic objectives: a multi-modal representation alignment loss that enforces feature-to-expert matching, and a modality-specific decoupling regularization that encourages complementarity across different modalities. This design enables joint optimization, fully exploiting priors from multiple foundation models. Extensive experiments demonstrate that our method significantly outperforms baselines in visual quality and long-term consistency.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Dynamic Risk in the U.S. Banking System: An Analysis of Sentiment, Policy Shocks, and Spillover Effects

The 2023 U.S. banking crisis propagated not through direct financial linkages but through a high-frequency, information-based contagion channel. This paper moves beyond exploration analysis to test the "too-similar-to-fail" hypothesis, arguing that risk spillovers were driven by perceived similarities in bank business models under acute interest rate pressure. Employing a Time-Varying Parameter Vector Autoregression (TVP-VAR) model with 30-day rolling windows, a method uniquely suited for capturing the rapid network shifts inherent in a panic, we analyze daily stock returns for the four failed institutions and a systematically selected peer group of surviving banks vulnerable to the same risks from March 18, 2022, to March 15, 2023. Our results provide strong evidence for this contagion channel: total system connectedness surged dramatically during the crisis peak, and we identify SIVB, FRC, and WAL as primary net transmitters of risk while their perceived peers became significant net receivers, a key dynamic indicator of systemic vulnerability that cannot be captured by asset-by-asset analysis. We further demonstrate that these spillovers were significantly amplified by market sentiment (as measured by the VIX) and economic policy uncertainty (EPU). By providing a clear conceptual framework and robust empirical validation, our findings confirm the persistence of systemic risks within the banking network and highlight the importance of real-time monitoring in strengthening financial stability.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure

Federated Multimodal Learning (FML) trains multimodal models across decentralized clients while keeping their image-text pairs private. However, joint embedding training entangles forgotten knowledge across both modalities and client gradient subspaces, hindering federated unlearning. Previous federated unlearning approaches neither sever the cross-modal reconstruction channel mediated by bilinear coupling nor separate forget-exclusive update directions from those shared with retained clients. We identify an Anchor Principle for federated multimodal contrastive unlearning: forgotten alignments persist through three residual anchors arising from bilinear cross-modal coupling, principal-angle subspace entanglement, and continued federated updates. At the modality level, we show that bilateral displacement of both visual and language branches closes the cross-modal reconstruction channel. Correspondingly, our method addresses subspace entanglement through Cosine--Sine decomposition of client-update subspaces, isolating forget-exclusive directions from retain support. Moreover, we propose a direction-selective Forget Lock that bounds residual drift across rounds. Combining these strategies, we present EASE, an Entanglement-Aware Subspace Excision framework that closes all three anchor channels under a unified design. EASE demonstrates consistent superiority across multiple datasets and unlearning scenarios, for instance, matching the retrain reference to within 0.2 and 4.2 R@1 points on the forget and retain sides under client unlearning on Flickr30K with CLIP-B/32.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Inference-Time Budget Control for LLM Search Agents

LLM search agents increasingly rely on tools at inference time, but their trajectories are often constrained by hard limits on both tool calls and generated tokens. Under such dual budgets, better answers require not only stronger models, but also explicit control over which search action should receive the next budget unit and when the accumulated evidence is sufficient to commit a final answer. We study this problem in multi-hop question answering (QA) and formulate it as two-stage inference-time budget control. At search time, our controller assigns each feasible action a task-level Value-of-Information (VOI) score, defined as an operational estimate of marginal task value per unit budget under the current search state and remaining dual budget, and uses this score to choose among retrieval, decomposition, and answer commitment. After search, a selective evidence-grounded finalizer compares the trajectory answer with a refined candidate and rewrites only when the residual error appears to be a low-risk answer-form error. Across four multi-hop QA benchmarks, three LLM backbones, and four budget levels, the method yields positive aggregate gains over four audited baselines under the same hard dual-budget protocol. Ablations show that search-time budget control, especially budget-dependent penalty, provides the main performance gain, while answer-time control helps mainly when the retrieval path is already adequate. These results suggest that inference-time budget control for LLM search agents should govern both how budget is spent during search and how the final answer is committed.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models

Recent multimodal large language models (MLLMs) have shown strong chain-of-thought (CoT) reasoning ability on vision-language tasks, but their direct deployment in real-world systems is often limited by latency and resource constraints. In practice, smaller MLLMs are preferred for online serving, yet their reasoning performance is bottlenecked by the lack of large-scale, high-quality multimodal CoT supervision. In this paper, we present OmniThoughtVis, a scalable data curation and distillation pipeline for transferring multimodal reasoning capabilities from high-capacity teacher models to smaller, deployment-oriented MLLMs. Starting from a diverse open-source seed pool, our pipeline generates structured CoT traces and performs joint annotation of reasoning difficulty, answer quality, and semantic task tags. To maintain data quality at scale, we combine rule-based filtering, difficulty-aware selection, and tag-based diversity sampling, resulting in a curated corpus of 1.8M samples that supports controllable subset construction for downstream training. We use OmniThoughtVis to distill Qwen3-VL models from 2B to 8B parameters and evaluate them on nine multimodal reasoning benchmarks. The resulting distilled models show consistent gains across model scales, including improvements of up to +16.8 points on MathVerse and +5.6 points on MMMU-Pro for the 4B model. Notably, the distilled 4B model matches or surpasses the undistilled 8B baseline on several tasks, highlighting the practical value of scalable reasoning distillation for deployment-oriented MLLMs.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

On Exact Editing of Flow-Based Diffusion Models

Recent methods in flow-based diffusion editing have enabled direct transformations between source and target image distribution without explicit inversion. However, the latent trajectories in these methods often exhibit accumulated velocity errors, leading to semantic inconsistency and loss of structural fidelity. We propose Conditioned Velocity Correction (CVC), a principled framework that reformulates flow-based editing as a distribution transformation problem driven by a known source prior. CVC rethinks the role of velocity in inter-distribution transformation by introducing a dual-perspective velocity conversion mechanism. This mechanism explicitly decomposes the latent evolution into two components: a structure-preserving branch that remains consistent with the source trajectory, and a semantically-guided branch that drives a controlled deviation toward the target distribution. The conditional velocity field exhibits an absolute velocity error relative to the true underlying distribution trajectory, which inherently introduces potential instability and trajectory drift in the latent space. To address this quantifiable deviation and maintain fidelity to the true flow, we apply a posterior-consistent update to the resulting conditional velocity field. This update is derived from Empirical Bayes Inference and Tweedie correction, which ensures a mathematically grounded error compensation over time. Our method yields stable and interpretable latent dynamics, achieving faithful reconstruction alongside smooth local semantic conversion. Comprehensive experiments demonstrate that CVC consistently achieves superior fidelity, better semantic alignment, and more reliable editing behavior across diverse tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Breaking the Computation and Communication Abstraction Barrier in Distributed Machine Learning Workloads

Recent trend towards increasing large machine learning models require both training and inference tasks to be distributed. Considering the huge cost of training these models, it is imperative to unlock optimizations in computation and communication to obtain best performance. However, current logical separation between computation and communication kernels in deep learning frameworks misses the optimization opportunities across such barrier. Breaking this abstraction with a holistic consideration can provide many optimizations to provide performance improvements in distributed workloads. Manually applying these optimizations needs modifications in underlying computation and communication libraries for each scenario, which is time consuming and error-prone. Therefore, we present CoCoNeT, with a DSL to express a program with both computation and communication. CoCoNeT contains several machine learning aware transformations to optimize a program and a compiler to generate high performance kernels. Providing both computation and communication as first class constructs allows users to work on a high-level abstraction and apply powerful optimizations, such as fusion or overlapping of communication and computation. CoCoNeT enables us to optimize data-, model-and pipeline-parallel workloads in large language models with only a few lines of code. Experiments show CoCoNeT significantly outperforms state-of-the-art distributed machine learning implementations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering

Extractive Question Answering (EQA) is one of the most important tasks in Machine Reading Comprehension (MRC), which can be solved by fine-tuning the span selecting heads of Pre-trained Language Models (PLMs). However, most existing approaches for MRC may perform poorly in the few-shot learning scenario. To solve this issue, we propose a novel framework named Knowledge Enhanced Contrastive Prompt-tuning (KECP). Instead of adding pointer heads to PLMs, we introduce a seminal paradigm for EQA that transform the task into a non-autoregressive Masked Language Modeling (MLM) generation problem. Simultaneously, rich semantics from the external knowledge base (KB) and the passage context are support for enhancing the representations of the query. In addition, to boost the performance of PLMs, we jointly train the model by the MLM and contrastive learning objectives. Experiments on multiple benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in few-shot settings by a large margin.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning

Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on labeled training data. For low-resource scenarios, prompt-based learning for PLMs exploits prompts as task guidance and turns downstream tasks into masked language problems for effective few-shot fine-tuning. In most existing approaches, the high performance of prompt-based learning heavily relies on handcrafted prompts and verbalizers, which may limit the application of such approaches in real-world scenarios. To solve this issue, we present CP-Tuning, the first end-to-end Contrastive Prompt Tuning framework for fine-tuning PLMs without any manual engineering of task-specific prompts and verbalizers. It is integrated with the task-invariant continuous prompt encoding technique with fully trainable prompt parameters. We further propose the pair-wise cost-sensitive contrastive learning procedure to optimize the model in order to achieve verbalizer-free class mapping and enhance the task-invariance of prompts. It explicitly learns to distinguish different classes and makes the decision boundary smoother by assigning different costs to easy and hard cases. Experiments over a variety of language understanding tasks used in IR systems and different PLMs show that CP-Tuning outperforms state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search

Large pre-trained language models such as BERT have shown their effectiveness in various natural language processing tasks. However, the huge parameter size makes them difficult to be deployed in real-time applications that require quick inference with limited resources. Existing methods compress BERT into small models while such compression is task-independent, i.e., the same compressed BERT for all different downstream tasks. Motivated by the necessity and benefits of task-oriented BERT compression, we propose a novel compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks. We incorporate a task-oriented knowledge distillation loss to provide search hints and an efficiency-aware loss as search constraints, which enables a good trade-off between efficiency and effectiveness for task-adaptive BERT compression. We evaluate AdaBERT on several NLP tasks, and the results demonstrate that those task-adaptive compressed models are 12.7x to 29.3x faster than BERT in inference time and 11.5x to 17.0x smaller in terms of parameter size, while comparable performance is maintained.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Novel Global Spatial Attention Mechanism in Convolutional Neural Network for Medical Image Classification

Spatial attention has been introduced to convolutional neural networks (CNNs) for improving both their performance and interpretability in visual tasks including image classification. The essence of the spatial attention is to learn a weight map which represents the relative importance of activations within the same layer or channel. All existing attention mechanisms are local attentions in the sense that weight maps are image-specific. However, in the medical field, there are cases that all the images should share the same weight map because the set of images record the same kind of symptom related to the same object and thereby share the same structural content. In this paper, we thus propose a novel global spatial attention mechanism in CNNs mainly for medical image classification. The global weight map is instantiated by a decision boundary between important pixels and unimportant pixels. And we propose to realize the decision boundary by a binary classifier in which the intensities of all images at a pixel are the features of the pixel. The binary classification is integrated into an image classification CNN and is to be optimized together with the CNN. Experiments on two medical image datasets and one facial expression dataset showed that with the proposed attention, not only the performance of four powerful CNNs which are GoogleNet, VGG, ResNet, and DenseNet can be improved, but also meaningful attended regions can be obtained, which is beneficial for understanding the content of images of a domain.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Series of Plasma Innovation Technologies by Double Glow Discharge Phenomenon

In order to break the limitation of plasma nitriding technology,which can be applied to a few nonmetallic gaseous elements, the "Double Glow Discharge Phenomenon" was found and then invented the "Double Glow Plasma Surface Metallurgy Technology". This double glow plasma surface metallurgy technology can use any element in the periodic table of chemical elements for surface alloying of metal materials. Countless surface alloys with special physical and chemical properties have been produced on the surfaces of conductive materials.By using double glow discharge phenomenon,a series of new plasma technologies,such as the double glow plasma graphene technology, double glow plasma brazing technology,double glow plasma sintering technology, double glow plasma nanotechnology,double glow plasma cleaning technology, double glow plasma carburizing without hydrogen and so on, have been invented.A very simple phenomenon of double glow discharge can generate about 10 plasma innovation technologies, which fully shows that there is still a lot of innovation space on the basis of classical physics.This paper briefly introduces the basic principles,functions and characteristics of each technology. The application prospects and development directions of plasma in metal materials and machinery manufacturing industry will also be discussed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Attack-Aware Data Timestamping in Low-Power Synchronization-Free LoRaWAN

Low-power wide-area network technologies such as LoRaWAN are promising for collecting low-rate monitoring data from geographically distributed sensors, in which timestamping the sensor data is a critical system function. This paper considers a synchronization-free approach to timestamping LoRaWAN uplink data based on signal arrival time at the gateway, which well matches LoRaWAN's one-hop star topology and releases bandwidth from transmitting timestamps and synchronizing end devices' clocks at all times. However, we show that this approach is susceptible to a {\em frame delay attack} consisting of malicious frame collision and delayed replay. Real experiments show that the attack can affect the end devices in large areas up to about $50,000\,\text{m}^2$. In a broader sense, the attack threatens any system functions requiring timely deliveries of LoRaWAN frames. To address this threat, we propose a $\mathsf{LoRaTS}$ gateway design that integrates a commodity LoRaWAN gateway and a low-power software-defined radio receiver to track the inherent frequency biases of the end devices. Based on an analytic model of LoRa's chirp spread spectrum modulation, we develop signal processing algorithms to estimate the frequency biases with high accuracy beyond that achieved by LoRa's default demodulation. The accurate frequency bias tracking capability enables the detection of the attack that introduces additional frequency biases. Extensive experiments show the effectiveness of our approach.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Enforced freedom: electric-field-induced declustering of ionic-liquid ions in the double layer

Whereas the majority of ions in the bulk of a solvent-free ionic liquid is bound into clusters, this is expected to change in the electrical double layer (EDL), in which the resulting electric field 'prefers' to interact with electrical monopoles-free, unclustered ions. The competition between the propensity of ions to stay in a clustered state and the reduction of the energy of ions in electric field in the free state determines the resulting portion of free ions in the EDL. We present a study of this effect, based on the simplest possible mean-field theory. 'Cracking' of ion clusters into individual ions in electric field is accompanied by the change of the dielectric response of ionic liquid which is different in clustered and unclustered states. The predictions of the theory are verified and further explored by specially performed molecular dynamics simulations. A particular finding of the theory is that the differential capacitance vs potential curve displays a bell shape despite low concentration of free charge carriers, because the dielectric response of bound ions reduces the threshold concentration of the bell- to camel-shape transition. Whereas qualitatively these findings make perfect sense, in reality the exact numbers and criteria might be different as the presented simple theory does not take into account overscreening and oscillating charge and electrostatic potential distributions near the electrode. This is why testing the theory with computer simulations is essential, but the latter basically reproduce the qualitative conclusions of the theory.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining

Pre-trained neural language models bring significant improvement for various NLP tasks, by fine-tuning the models on task-specific training sets. During fine-tuning, the parameters are initialized from pre-trained models directly, which ignores how the learning process of similar NLP tasks in different domains is correlated and mutually reinforced. In this paper, we propose an effective learning procedure named Meta Fine-Tuning (MFT), served as a meta-learner to solve a group of similar NLP tasks for neural language models. Instead of simply multi-task training over all the datasets, MFT only learns from typical instances of various domains to acquire highly transferable knowledge. It further encourages the language model to encode domain-invariant representations by optimizing a series of novel domain corruption loss functions. After MFT, the model can be fine-tuned for each domain with better parameter initializations and higher generalization ability. We implement MFT upon BERT to solve several multi-domain text mining tasks. Experimental results confirm the effectiveness of MFT and its usefulness for few-shot learning.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information Extraction

Structured information extraction from document images usually consists of three steps: text detection, text recognition, and text field labeling. While text detection and text recognition have been heavily studied and improved a lot in literature, text field labeling is less explored and still faces many challenges. Existing learning based methods for text labeling task usually require a large amount of labeled examples to train a specific model for each type of document. However, collecting large amounts of document images and labeling them is difficult and sometimes impossible due to privacy issues. Deploying separate models for each type of document also consumes a lot of resources. Facing these challenges, we explore one-shot learning for the text field labeling task. Existing one-shot learning methods for the task are mostly rule-based and have difficulty in labeling fields in crowded regions with few landmarks and fields consisting of multiple separate text regions. To alleviate these problems, we proposed a novel deep end-to-end trainable approach for one-shot text field labeling, which makes use of attention mechanism to transfer the layout information between document images. We further applied conditional random field on the transferred layout information for the refinement of field labeling. We collected and annotated a real-world one-shot field labeling dataset with a large variety of document types and conducted extensive experiments to examine the effectiveness of the proposed model. To stimulate research in this direction, the collected dataset and the one-shot model will be released1.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Plasma Surface Metallurgy of Materials Based on Double Glow Discharge Phenomenon

Plasma Surface Metallurgy/Alloying is a kind of surface metallurgy/alloying to employ low temperature plasma produced by glow discharge to diffuse alloying elements into the surface of substrate material to form an alloy layer. The first plasma surface metallurgy technology is plasma nitriding invented by German scientist Dr. Bernard Berghuas in 1930. He was the first person to apply glow discharge to realize the surface alloying. In order to break the limitation of plasma nitriding technology, which can only be applied to a few non-metallic gaseous elements such as nitrogen, carbon, sulfur, the "Double Glow Discharge Phenomenon"was found in 1978. Based on this phenomenon the "Double Glow Plasma Surface Metallurgy Technology", also known as the "Xu-Tec Process" was invented in 1980. It can utilize any chemical elements in the periodic table including solid metallic, gas non-metallic elements and their combination to realize plasma surface alloying, hence greatly expanded the field of surface alloying. Countless surface alloys with high hardness, wear resistance and corrosion resistance, such as high speed steels, nickel base alloys and burn resistant alloys have been produced on the surfaces of a variety of materials. This technology may greatly improve the surface properties of metal materials, comprehensively improve the quality of mechanical products, save a lot of precious alloy elements for human beings. Based on the plasma nitriding technology, the Xu-Tec Process has opened up a new material engineering field of "Plasma Surface Metallurgy". This Review Article briefly presents the history of glow discharge and surface alloying, double glow discharge phenomenon, basic principle and current status of Double Glow Plasma Surface Metallurgy/Alloying. Industrial applications, advantages and future potential of the Xu-Tec process are also presented.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

SwapText: Image Based Texts Transfer in Scenes

Swapping text in scene images while preserving original fonts, colors, sizes and background textures is a challenging task due to the complex interplay between different factors. In this work, we present SwapText, a three-stage framework to transfer texts across scene images. First, a novel text swapping network is proposed to replace text labels only in the foreground image. Second, a background completion network is learned to reconstruct background images. Finally, the generated foreground image and background image are used to generate the word image by the fusion network. Using the proposing framework, we can manipulate the texts of the input images even with severe geometric distortion. Qualitative and quantitative results are presented on several scene text datasets, including regular and irregular text datasets. We conducted extensive experiments to prove the usefulness of our method such as image based text translation, text image synthesis, etc.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Weakly Supervised Construction of ASR Systems with Massive Video Data

Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several unsupervised pre-training models have been proposed, applying such models directly might still be sub-optimal if more labeled, training data could be obtained without a large cost. In this paper, we present a weakly supervised framework for constructing ASR systems with massive video data. As videos often contain human-speech audios aligned with subtitles, we consider videos as an important knowledge source, and propose an effective approach to extract high-quality audios aligned with transcripts from videos based on Optical Character Recognition (OCR). The underlying ASR model can be fine-tuned to fit any domain-specific target training datasets after weakly supervised pre-training. Extensive experiments show that our framework can easily produce state-of-the-art results on six public datasets for Mandarin speech recognition.

0 citations0 reviewsNo code linkedOpen access