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

Hongbin Liu

Hongbin Liu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionCryptography and SecurityMachine Learningquant-phArtificial Intelligencephysics.comp-phphysics.ins-detRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
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

12 published item(s)

preprint2026arXiv

BREATH-VL: Vision-Language-Guided 6-DoF Bronchoscopy Localization via Semantic-Geometric Fusion

Vision-language models (VLMs) have recently shown remarkable performance in navigation and localization tasks by leveraging large-scale pretraining for semantic understanding. However, applying VLMs to 6-DoF endoscopic camera localization presents several challenges: 1) the lack of large-scale, high-quality, densely annotated, and localization-oriented vision-language datasets in real-world medical settings; 2) limited capability for fine-grained pose regression; and 3) high computational latency when extracting temporal features from past frames. To address these issues, we first construct BREATH dataset, the largest in-vivo endoscopic localization dataset to date, collected in the complex human airway. Building on this dataset, we propose BREATH-VL, a hybrid framework that integrates semantic cues from VLMs with geometric information from vision-based registration methods for accurate 6-DoF pose estimation. Our motivation lies in the complementary strengths of both approaches: VLMs offer generalizable semantic understanding, while registration methods provide precise geometric alignment. To further enhance the VLM's ability to capture temporal context, we introduce a lightweight context-learning mechanism that encodes motion history as linguistic prompts, enabling efficient temporal reasoning without expensive video-level computation. Extensive experiments demonstrate that the vision-language module delivers robust semantic localization in challenging surgical scenes. Building on this, our BREATH-VL outperforms state-of-the-art vision-only localization methods in both accuracy and generalization, reducing translational error by 25.5% compared with the best-performing baseline, while achieving competitive computational latency.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

LP-LLM: End-to-End Real-World Degraded License Plate Text Recognition via Large Multimodal Models

Real-world License Plate Recognition (LPR) faces significant challenges from severe degradations such as motion blur, low resolution, and complex illumination. The prevailing "restoration-then-recognition" two-stage paradigm suffers from a fundamental flaw: the pixel-level optimization objectives of image restoration models are misaligned with the semantic goals of character recognition, leading to artifact interference and error accumulation. While Vision-Language Models (VLMs) have demonstrated powerful general capabilities, they lack explicit structural modeling for license plate character sequences (e.g., fixed length, specific order). To address this, we propose an end-to-end structure-aware multimodal reasoning framework based on Qwen3-VL. The core innovation lies in the Character-Aware Multimodal Reasoning Module (CMRM), which introduces a set of learnable Character Slot Queries. Through a cross-attention mechanism, these queries actively retrieve fine-grained evidence corresponding to character positions from visual features. Subsequently, we inject these character-aware representations back into the visual tokens via residual modulation, enabling the language model to perform autoregressive generation based on explicit structural priors. Furthermore, combined with the LoRA parameter-efficient fine-tuning strategy, the model achieves domain adaptation while retaining the generalization capabilities of the large model. Extensive experiments on both synthetic and real-world severely degraded datasets demonstrate that our method significantly outperforms existing restoration-recognition combinations and general VLMs, validating the superiority of incorporating structured reasoning into large models for low-quality text recognition tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection

Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment between text embeddings and shifted visual embeddings of region proposals. While recent test-time adaptive object detection methods for VLM-based either rely on costly backpropagation or bypass semantic misalignment via external memory, none directly and efficiently align text and vision in a training-free manner. To address this, we propose Reward-Guided Semantic Evolution (RGSE), a training-free framework that directly refines the text embeddings at test time. Inspired by evolutionary search, RGSE treats text embedding adaptation as a semantic search process: it perturbs text embeddings as candidate variants, evaluates them via cosine similarity with current and historical high-confidence visual proposals as a reward signal, and fuses them into a refined embedding through reward-weighted averaging. Without any backpropagation, RGSE achieves state-of-the-art performance across multiple detection benchmarks while adding minimal computational overhead. Our code will be open source upon publication.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning

Contrastive learning pre-trains an image encoder using a large amount of unlabeled data such that the image encoder can be used as a general-purpose feature extractor for various downstream tasks. In this work, we propose PoisonedEncoder, a data poisoning attack to contrastive learning. In particular, an attacker injects carefully crafted poisoning inputs into the unlabeled pre-training data, such that the downstream classifiers built based on the poisoned encoder for multiple target downstream tasks simultaneously classify attacker-chosen, arbitrary clean inputs as attacker-chosen, arbitrary classes. We formulate our data poisoning attack as a bilevel optimization problem, whose solution is the set of poisoning inputs; and we propose a contrastive-learning-tailored method to approximately solve it. Our evaluation on multiple datasets shows that PoisonedEncoder achieves high attack success rates while maintaining the testing accuracy of the downstream classifiers built upon the poisoned encoder for non-attacker-chosen inputs. We also evaluate five defenses against PoisonedEncoder, including one pre-processing, three in-processing, and one post-processing defenses. Our results show that these defenses can decrease the attack success rate of PoisonedEncoder, but they also sacrifice the utility of the encoder or require a large clean pre-training dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

Top-k predictions are used in many real-world applications such as machine learning as a service, recommender systems, and web searches. $\ell_0$-norm adversarial perturbation characterizes an attack that arbitrarily modifies some features of an input such that a classifier makes an incorrect prediction for the perturbed input. $\ell_0$-norm adversarial perturbation is easy to interpret and can be implemented in the physical world. Therefore, certifying robustness of top-$k$ predictions against $\ell_0$-norm adversarial perturbation is important. However, existing studies either focused on certifying $\ell_0$-norm robustness of top-$1$ predictions or $\ell_2$-norm robustness of top-$k$ predictions. In this work, we aim to bridge the gap. Our approach is based on randomized smoothing, which builds a provably robust classifier from an arbitrary classifier via randomizing an input. Our major theoretical contribution is an almost tight $\ell_0$-norm certified robustness guarantee for top-$k$ predictions. We empirically evaluate our method on CIFAR10 and ImageNet. For instance, our method can build a classifier that achieves a certified top-3 accuracy of 69.2\% on ImageNet when an attacker can arbitrarily perturb 5 pixels of a testing image.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning

Semi-supervised learning (SSL) leverages both labeled and unlabeled data to train machine learning (ML) models. State-of-the-art SSL methods can achieve comparable performance to supervised learning by leveraging much fewer labeled data. However, most existing works focus on improving the performance of SSL. In this work, we take a different angle by studying the training data privacy of SSL. Specifically, we propose the first data augmentation-based membership inference attacks against ML models trained by SSL. Given a data sample and the black-box access to a model, the goal of membership inference attack is to determine whether the data sample belongs to the training dataset of the model. Our evaluation shows that the proposed attack can consistently outperform existing membership inference attacks and achieves the best performance against the model trained by SSL. Moreover, we uncover that the reason for membership leakage in SSL is different from the commonly believed one in supervised learning, i.e., overfitting (the gap between training and testing accuracy). We observe that the SSL model is well generalized to the testing data (with almost 0 overfitting) but ''memorizes'' the training data by giving a more confident prediction regardless of its correctness. We also explore early stopping as a countermeasure to prevent membership inference attacks against SSL. The results show that early stopping can mitigate the membership inference attack, but with the cost of model's utility degradation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning

Pre-trained encoders are general-purpose feature extractors that can be used for many downstream tasks. Recent progress in self-supervised learning can pre-train highly effective encoders using a large volume of unlabeled data, leading to the emerging encoder as a service (EaaS). A pre-trained encoder may be deemed confidential because its training requires lots of data and computation resources as well as its public release may facilitate misuse of AI, e.g., for deepfakes generation. In this paper, we propose the first attack called StolenEncoder to steal pre-trained image encoders. We evaluate StolenEncoder on multiple target encoders pre-trained by ourselves and three real-world target encoders including the ImageNet encoder pre-trained by Google, CLIP encoder pre-trained by OpenAI, and Clarifai's General Embedding encoder deployed as a paid EaaS. Our results show that our stolen encoders have similar functionality with the target encoders. In particular, the downstream classifiers built upon a target encoder and a stolen one have similar accuracy. Moreover, stealing a target encoder using StolenEncoder requires much less data and computation resources than pre-training it from scratch. We also explore three defenses that perturb feature vectors produced by a target encoder. Our results show these defenses are not enough to mitigate StolenEncoder.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Prospects of Quantum Computing for Molecular Sciences

Molecular science is governed by the dynamics of electrons, atomic nuclei, and their interaction with electromagnetic fields. A reliable physicochemical understanding of these processes is crucial for the design and synthesis of chemicals and materials of economic value. Although some problems in this field are adequately addressed by classical mechanics, many require an explicit quantum mechanical description. Such quantum problems represented by exponentially large wave function should naturally benefit from quantum computation on a number of logical qubits that scales only linearly with system size. In this perspective, we focus on the potential of quantum computing for solving relevant problems in the molecular sciences -- molecular physics, chemistry, biochemistry, and materials science.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Design and integration of a parallel, soft robotic end-effector for extracorporeal ultrasound

Objective: In this work we address limitations in state-of-the-art ultrasound robots by designing and integrating a novel soft robotic system for ultrasound imaging. It employs the inherent qualities of soft fluidic actuators to establish safe, adaptable interaction between ultrasound probe and patient. Methods: We acquire clinical data to determine the movement ranges and force levels required in prenatal foetal ultrasound imaging and design the soft robotic end-effector accordingly. We verify its mechanical characteristics, derive and validate a kinetostatic model and demonstrate controllability and imaging capabilities on an ultrasound phantom. Results: The soft robot exhibits the desired stiffness characteristics and is able to reach 100% of the required workspace when no external force is present, and 95% of the workspace when considering its compliance. The model can accurately predict the end-effector pose with a mean error of 1.18+/-0.29mm in position and 0.92+/-0.47deg in orientation. The derived controller is, with an average position error of 0.39mm, able to track a target pose efficiently without and with externally applied loads. Ultrasound images acquired with the system are of equally good quality compared to a manual sonographer scan. Conclusion: The system is able to withstand loads commonly applied during foetal ultrasound scans and remains controllable with a motion range similar to manual scanning. Significance: The proposed soft robot presents a safe, cost-effective solution to offloading sonographers in day-to-day scanning routines. The design and modelling paradigms are greatly generalizable and particularly suitable for designing soft robots for physical interaction tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On the Intrinsic Differential Privacy of Bagging

Differentially private machine learning trains models while protecting privacy of the sensitive training data. The key to obtain differentially private models is to introduce noise/randomness to the training process. In particular, existing differentially private machine learning methods add noise to the training data, the gradients, the loss function, and/or the model itself. Bagging, a popular ensemble learning framework, randomly creates some subsamples of the training data, trains a base model for each subsample using a base learner, and takes majority vote among the base models when making predictions. Bagging has intrinsic randomness in the training process as it randomly creates subsamples. Our major theoretical results show that such intrinsic randomness already makes Bagging differentially private without the needs of additional noise. In particular, we prove that, for any base learner, Bagging with and without replacement respectively achieves $\left(N\cdot k \cdot \ln{\frac{n+1}{n}},1- (\frac{n-1}{n})^{N\cdot k}\right)$-differential privacy and $\left(\ln{\frac{n+1}{n+1-N\cdot k}}, \frac{N\cdot k}{n} \right)$-differential privacy, where $n$ is the training data size, $k$ is the subsample size, and $N$ is the number of base models. Moreover, we prove that if no assumptions about the base learner are made, our derived privacy guarantees are tight. We empirically evaluate Bagging on MNIST and CIFAR10. Our experimental results demonstrate that Bagging achieves significantly higher accuracies than state-of-the-art differentially private machine learning methods with the same privacy budgets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Performance of CMOS pixel sensor prototypes in ams H35 and aH18 technology for the ATLAS ITk upgrade

Pixel sensors based on commercial high-voltage CMOS processes are an exciting technology that is considered as an option for the outer layer of the ATLAS inner tracker upgrade at the High Luminosity LHC. Here, charged particles are detected using deep n-wells as sensor diodes with the depleted region extending into the silicon bulk. Both analog and digital readout electronics can be added to achieve different levels of integration up to a fully monolithic sensor. Small scale prototypes using the ams CMOS technology have previously demonstrated that it can achieve the required radiation tolerance of $10^{15}~\text{n}_\text{eq}/\text{cm}^2$ and detection efficiencies above $99.5~\%$. Recently, large area prototypes, comparable in size to a full sensor, have been produced that include most features required towards a final design: the H35demo prototype produced in ams H35 technology that supports both external and integrated readout and the monolithic ATLASPix1 pre-production design produced in ams aH18 technology. Both chips are based on large fill-factor pixel designs, but differ in readout structure. Performance results for H35DEMO with capacitively-coupled external readout and first results for the monolithic ATLASPix1 are shown.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards quantum computing for high-energy excited states in molecular systems: quantum phase estimations of core-level states

This paper explores the utility of the quantum phase estimation (QPE) in calculating high-energy excited states characterized by promotions of electrons occupying inner energy shells. These states have been intensively studied over the last few decades especially in supporting the experimental effort at light sources. Results obtained with the QPE are compared with various high-accuracy many-body techniques developed to describe core-level states. The feasibility of the quantum phase estimator in identifying classes of challenging shake-up states characterized by the presence of higher-order excitation effects is also discussed.

0 citations0 reviewsNo code linkedOpen access