Showing 1–50 of 90 results for author: An, G

Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation

Authors: Changcheng Li, Jiancan Wu, Hengheng Zhang, Zhengsu Chen, Guo An, Junxiang Qiu, Xiang Wang, Qi Tian

Abstract: Reliable deployment of large language models (LLMs) requires accurate uncertainty estimation. Existing methods are predominantly answer-first, producing confidence only after generating an answer, which measure the correctness of a specific response and limits practical usability. We study a confidence-first paradigm, where the model outputs its confidence before answering, interpreting this score… ▽ More Reliable deployment of large language models (LLMs) requires accurate uncertainty estimation. Existing methods are predominantly answer-first, producing confidence only after generating an answer, which measure the correctness of a specific response and limits practical usability. We study a confidence-first paradigm, where the model outputs its confidence before answering, interpreting this score as the model's probability of answering the question correctly under its current policy. We propose CoCA(Co-optimized Confidence and Answers), a GRPO reinforcement learning framework that jointly optimizes confidence calibration and answer accuracy via segmented credit assignment. By assigning separate rewards and group-relative advantages to confidence and answer segments, CoCA enables stable joint optimization and avoids reward hacking. Experiments across math, code, and factual QA benchmarks show improved calibration and uncertainty discrimination while preserving answer quality, thereby enabling a broader range of downstream applications. △ Less

Submitted 5 March, 2026; originally announced March 2026.

Learning to Generate Secure Code via Token-Level Rewards

Authors: Jiazheng Quan, Xiaodong Li, Bin Wang, Guo An, Like Liu, Degen Huang, Lin Liu, Chengbin Hou

Abstract: Large language models (LLMs) have demonstrated strong capabilities in code generation, yet they remain prone to producing security vulnerabilities. Existing approaches commonly suffer from two key limitations: the scarcity of high-quality security data and coarse-grained reinforcement learning reward signals. To address these challenges, we propose Vul2Safe, a new secure code generation framework… ▽ More Large language models (LLMs) have demonstrated strong capabilities in code generation, yet they remain prone to producing security vulnerabilities. Existing approaches commonly suffer from two key limitations: the scarcity of high-quality security data and coarse-grained reinforcement learning reward signals. To address these challenges, we propose Vul2Safe, a new secure code generation framework that leverages LLM self-reflection to construct high-confidence repair pairs from real-world vulnerabilities, and further generates diverse implicit prompts to build the PrimeVul+ dataset. Meanwhile, we introduce SRCode, a novel training framework that pioneers the use of token-level rewards in reinforcement learning for code security, which enables the model to continuously attend to and reinforce critical fine-grained security patterns during training. Compared with traditional instance-level reward schemes, our approach allows for more precise optimization of local security implementations. Extensive experiments show that PrimeVul+ and SRCode substantially reduce security vulnerabilities in generated code while improving overall code quality across multiple benchmarks. △ Less

Submitted 26 February, 2026; originally announced February 2026.

Comments: 18 pages, 3 figures

Accelerating Generative Recommendation via Simple Categorical User Sequence Compression

Authors: Qijiong Liu, Lu Fan, Zhongzhou Liu, Xiaoyu Dong, Yuankai Luo, Guoyuan An, Nuo Chen, Wei Guo, Yong Liu, Xiao-Ming Wu

Abstract: Although generative recommenders demonstrate improved performance with longer sequences, their real-time deployment is hindered by substantial computational costs. To address this challenge, we propose a simple yet effective method for compressing long-term user histories by leveraging inherent item categorical features, thereby preserving user interests while enhancing efficiency. Experiments on… ▽ More Although generative recommenders demonstrate improved performance with longer sequences, their real-time deployment is hindered by substantial computational costs. To address this challenge, we propose a simple yet effective method for compressing long-term user histories by leveraging inherent item categorical features, thereby preserving user interests while enhancing efficiency. Experiments on two large-scale datasets demonstrate that, compared to the influential HSTU model, our approach achieves up to a 6x reduction in computational cost and up to 39% higher accuracy at comparable cost (i.e., similar sequence length). △ Less

Submitted 26 January, 2026; originally announced January 2026.

Comments: WSDM'26 Accepted Paper

Unleashing the Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation

Authors: Yuhan Yang, Jie Zou, Guojia An, Jiwei Wei, Yang Yang, Heng Tao Shen

Abstract: Session-based recommendation aims to predict the next item that anonymous users may be interested in, based on their current session interactions. Recent studies have demonstrated that retrieving neighbor sessions to augment the current session can effectively alleviate the data sparsity issue and improve recommendation performance. However, existing methods typically rely on explicitly observed s… ▽ More Session-based recommendation aims to predict the next item that anonymous users may be interested in, based on their current session interactions. Recent studies have demonstrated that retrieving neighbor sessions to augment the current session can effectively alleviate the data sparsity issue and improve recommendation performance. However, existing methods typically rely on explicitly observed session data, neglecting latent neighbors - not directly observed but potentially relevant within the interest space - thereby failing to fully exploit the potential of neighbor sessions in recommendation. To address the above limitation, we propose a novel model of diffusion-based latent neighbor generation for session-based recommendation, named DiffSBR. Specifically, DiffSBR leverages two diffusion modules, including retrieval-augmented diffusion and self-augmented diffusion, to generate high-quality latent neighbors. In the retrieval-augmented diffusion module, we leverage retrieved neighbors as guiding signals to constrain and reconstruct the distribution of latent neighbors. Meanwhile, we adopt a training strategy that enables the retriever to learn from the feedback provided by the generator. In the self-augmented diffusion module, we explicitly guide the generation of latent neighbors by injecting the current session's multi-modal signals through contrastive learning. After obtaining the generated latent neighbors, we utilize them to enhance session representations for improving session-based recommendation. Extensive experiments on four public datasets show that DiffSBR generates effective latent neighbors and improves recommendation performance against state-of-the-art baselines. △ Less

Submitted 7 January, 2026; originally announced January 2026.

Comments: This paper has been accepted by KDD 2026

First measurement of reactor neutrino oscillations at JUNO

Authors: Angel Abusleme, Thomas Adam, Kai Adamowicz, David Adey, Shakeel Ahmad, Rizwan Ahmed, Timo Ahola, Sebastiano Aiello, Fengpeng An, Guangpeng An, Costas Andreopoulos, Giuseppe Andronico, João Pedro Athayde Marcondes de André, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, Burin Asavapibhop, Didier Auguste, Margherita Buizza Avanzini, Andrej Babic, Jingzhi Bai, Weidong Bai, Nikita Balashov, Roberto Barbera, Andrea Barresi , et al. (1114 additional authors not shown)

Abstract: Neutrino oscillations, a quantum effect manifesting at macroscopic scales, are governed by lepton flavor mixing angles and neutrino mass-squared differences that are fundamental parameters of particle physics, representing phenomena beyond the Standard Model. Precision measurements of these parameters are essential for testing the completeness of the three-flavor framework, determining the mass or… ▽ More Neutrino oscillations, a quantum effect manifesting at macroscopic scales, are governed by lepton flavor mixing angles and neutrino mass-squared differences that are fundamental parameters of particle physics, representing phenomena beyond the Standard Model. Precision measurements of these parameters are essential for testing the completeness of the three-flavor framework, determining the mass ordering of neutrinos, and probing possible new physics. The Jiangmen Underground Neutrino Observatory (JUNO) is a 20 kton liquid-scintillator detector located 52.5 km from multiple reactor cores, designed to resolve the interference pattern of reactor neutrinos with sub-percent precision. Here we report, using the first 59.1 days of data collected since detector completion in August 2025, the first simultaneous high-precision determination of two neutrino oscillation parameters, $\sin^2 θ_{12} = 0.3092\,\pm\,0.0087$ and $Δm^2_{21} = (7.50\,\pm\,0.12)\times10^{-5}\;{\rm eV}^2$ for the normal mass ordering scenario, improving the precision by a factor of 1.6 relative to the combination of all previous measurements. These results advance the basic understanding of neutrinos, validate the detector's design, and confirm JUNO's readiness for its primary goal of resolving the neutrino mass ordering with a larger dataset. The rapid achievement with a short exposure highlights JUNO's potential to push the frontiers of precision neutrino physics and paves the way for its broad scientific program. △ Less

Submitted 18 November, 2025; originally announced November 2025.

Comments: 30 pages, 11 figures

Initial performance results of the JUNO detector

Authors: Angel Abusleme, Thomas Adam, Kai Adamowicz, David Adey, Shakeel Ahmad, Rizwan Ahmed, Timo Ahola, Sebastiano Aiello, Fengpeng An, Guangpeng An, Costas Andreopoulos, Giuseppe Andronico, João Pedro Athayde Marcondes de André, Nikolay Anfimov, Vito Antonelli, Tatiana Antoshkina, Burin Asavapibhop, Didier Auguste, Margherita Buizza Avanzini, Andrej Babic, Jingzhi Bai, Weidong Bai, Nikita Balashov, Roberto Barbera, Andrea Barresi , et al. (1114 additional authors not shown)

Abstract: The Jiangmen Underground Neutrino Observatory (JUNO) started physics data taking on 26 August 2025. JUNO consists of a 20-kton liquid scintillator central detector, surrounded by a 35 kton water pool serving as a Cherenkov veto, and almost 1000 m$^2$ of plastic scintillator veto on top. The detector is located in a shallow underground laboratory with an overburden of 1800 m.w.e. This paper present… ▽ More The Jiangmen Underground Neutrino Observatory (JUNO) started physics data taking on 26 August 2025. JUNO consists of a 20-kton liquid scintillator central detector, surrounded by a 35 kton water pool serving as a Cherenkov veto, and almost 1000 m$^2$ of plastic scintillator veto on top. The detector is located in a shallow underground laboratory with an overburden of 1800 m.w.e. This paper presents the performance results of the detector, extensively studied during the commissioning of the water phase, the subsequent liquid scintillator filling phase, and the first physics runs. The liquid scintillator achieved an attenuation length of 20.6 m at 430 nm, while the high coverage PMT system and scintillator together yielded about 1785 photoelectrons per MeV of energy deposit at the detector centre, measured using the 2.223 MeV $γ$ from neutron captures on hydrogen with an Am-C calibration source. The reconstructed energy resolution is 3.4% for two 0.511 MeV $γ$ at the detector centre and 2.9% for the 0.93 MeV quenched Po-214 alpha decays from natural radioactive sources. The energy nonlinearity is calibrated to better than 1%. Intrinsic contaminations of U-238 and Th-232 in the liquid scintillator are below 10$^{-16}$ g/g, assuming secular equilibrium. The water Cherenkov detector achieves a muon detection efficiency better than 99.9% for muons traversing the liquid scintillator volume. During the initial science runs, the data acquisition duty cycle exceeded 97.8%, demonstrating the excellent stability and readiness of JUNO for high-precision neutrino physics. △ Less

Submitted 18 November, 2025; originally announced November 2025.

Comments: 38 pages, 23 figures

PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos

Authors: Dianbing Xi, Guoyuan An, Jingsen Zhu, Zhijian Liu, Yuan Liu, Ruiyuan Zhang, Jiayuan Lu, Yuchi Huo, Rui Wang

Abstract: We propose PFAvatar (Pose-Fusion Avatar), a new method that reconstructs high-quality 3D avatars from Outfit of the Day(OOTD) photos, which exhibit diverse poses, occlusions, and complex backgrounds. Our method consists of two stages: (1) fine-tuning a pose-aware diffusion model from few-shot OOTD examples and (2) distilling a 3D avatar represented by a neural radiance field (NeRF). In the first s… ▽ More We propose PFAvatar (Pose-Fusion Avatar), a new method that reconstructs high-quality 3D avatars from Outfit of the Day(OOTD) photos, which exhibit diverse poses, occlusions, and complex backgrounds. Our method consists of two stages: (1) fine-tuning a pose-aware diffusion model from few-shot OOTD examples and (2) distilling a 3D avatar represented by a neural radiance field (NeRF). In the first stage, unlike previous methods that segment images into assets (e.g., garments, accessories) for 3D assembly, which is prone to inconsistency, we avoid decomposition and directly model the full-body appearance. By integrating a pre-trained ControlNet for pose estimation and a novel Condition Prior Preservation Loss (CPPL), our method enables end-to-end learning of fine details while mitigating language drift in few-shot training. Our method completes personalization in just 5 minutes, achieving a 48x speed-up compared to previous approaches. In the second stage, we introduce a NeRF-based avatar representation optimized by canonical SMPL-X space sampling and Multi-Resolution 3D-SDS. Compared to mesh-based representations that suffer from resolution-dependent discretization and erroneous occluded geometry, our continuous radiance field can preserve high-frequency textures (e.g., hair) and handle occlusions correctly through transmittance. Experiments demonstrate that PFAvatar outperforms state-of-the-art methods in terms of reconstruction fidelity, detail preservation, and robustness to occlusions/truncations, advancing practical 3D avatar generation from real-world OOTD albums. In addition, the reconstructed 3D avatar supports downstream applications such as virtual try-on, animation, and human video reenactment, further demonstrating the versatility and practical value of our approach. △ Less

Submitted 18 November, 2025; v1 submitted 16 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI 2026

On the Boltzmann-Fermi-Dirac Equation for Hard Potential: Global Existence and Uniqueness, Gaussian Lower Bound, and Moment Estimates

Authors: Gayoung An, Sungbin Park

Abstract: In this paper, we study the global existence and uniqueness, Gaussian lower bound, and moment estimates in the spatially homogeneous Boltzmann equation for Fermi-Dirac particles for hard potential ($0\leq γ\leq 2$) with angular cutoff $b$. Our results extend classical results to the Boltzmann-Fermi-Dirac setting. In detail, (1) we show existence, uniqueness, and $L^1_2$ stability of global-in-time… ▽ More In this paper, we study the global existence and uniqueness, Gaussian lower bound, and moment estimates in the spatially homogeneous Boltzmann equation for Fermi-Dirac particles for hard potential ($0\leq γ\leq 2$) with angular cutoff $b$. Our results extend classical results to the Boltzmann-Fermi-Dirac setting. In detail, (1) we show existence, uniqueness, and $L^1_2$ stability of global-in-time solutions of the Boltzmann-Fermi-Dirac equation. (2) Assuming the solution is not a saturated equilibrium, we prove creation of a Gaussian lower bound for the solution. (3) We prove creation and propagation of $L^1$ polynomial and exponential moments of the solution under additional assumptions on the angular kernel $b$ and $0<γ\leq 2$. (4) Finally, we show propagation of $L^\infty$ Gaussian and polynomial upper bounds when $b$ is constant and $0<γ\leq 1$. △ Less

Submitted 5 November, 2025; v1 submitted 4 November, 2025; originally announced November 2025.

Comments: 82 pages, 5 figures, Omitted condition $0\leq f\leq 1$ in the definition of solution is revised

MSC Class: 35Q20; 35Q40; 82C40

Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts

Authors: Qiushi Pan, Hao Wang, Guoyuan An, Luankang Zhang, Wei Guo, Yong Liu

Abstract: In recommendation systems, how to effectively scale up recommendation models has been an essential research topic. While significant progress has been made in developing advanced and scalable architectures for sequential recommendation(SR) models, there are still challenges due to items' multi-faceted characteristics and dynamic item relevance in the user context. To address these issues, we propo… ▽ More In recommendation systems, how to effectively scale up recommendation models has been an essential research topic. While significant progress has been made in developing advanced and scalable architectures for sequential recommendation(SR) models, there are still challenges due to items' multi-faceted characteristics and dynamic item relevance in the user context. To address these issues, we propose Fuxi-MME, a framework that integrates a multi-embedding strategy with a Mixture-of-Experts (MoE) architecture. Specifically, to efficiently capture diverse item characteristics in a decoupled manner, we decompose the conventional single embedding matrix into several lower-dimensional embedding matrices. Additionally, by substituting relevant parameters in the Fuxi Block with an MoE layer, our model achieves adaptive and specialized transformation of the enriched representations. Empirical results on public datasets show that our proposed framework outperforms several competitive baselines. △ Less

Submitted 29 October, 2025; originally announced October 2025.

Finding the Needle in the Crash Stack: Industrial-Scale Crash Root Cause Localization with AutoCrashFL

Authors: Sungmin Kang, Sumi Yun, Jingun Hong, Shin Yoo, Gabin An

Abstract: Fault Localization (FL) aims to identify root causes of program failures. FL typically targets failures observed from test executions, and as such, often involves dynamic analyses to improve accuracy, such as coverage profiling or mutation testing. However, for large industrial software, measuring coverage for every execution is prohibitively expensive, making the use of such techniques difficult.… ▽ More Fault Localization (FL) aims to identify root causes of program failures. FL typically targets failures observed from test executions, and as such, often involves dynamic analyses to improve accuracy, such as coverage profiling or mutation testing. However, for large industrial software, measuring coverage for every execution is prohibitively expensive, making the use of such techniques difficult. To address these issues and apply FL in an industrial setting, this paper proposes AutoCrashFL, an LLM agent for the localization of crashes that only requires the crashdump from the Program Under Test (PUT) and access to the repository of the corresponding source code. We evaluate AutoCrashFL against real-world crashes of SAP HANA, an industrial software project consisting of more than 35 million lines of code. Experiments reveal that AutoCrashFL is more effective in localization, as it identified 30% crashes at the top, compared to 17% achieved by the baseline. Through thorough analysis, we find that AutoCrashFL has attractive practical properties: it is relatively more effective for complex bugs, and it can indicate confidence in its results. Overall, these results show the practicality of LLM agent deployment on an industrial scale. △ Less

Submitted 26 October, 2025; originally announced October 2025.

Comments: 11 pages, 8 figures, under review

BenCao: An Instruction-Tuned Large Language Model for Traditional Chinese Medicine

Authors: Jiacheng Xie, Yang Yu, Yibo Chen, Hanyao Zhang, Lening Zhao, Jiaxuan He, Lei Jiang, Xiaoting Tang, Guanghui An, Dong Xu

Abstract: Traditional Chinese Medicine (TCM), with a history spanning over two millennia, plays a role in global healthcare. However, applying large language models (LLMs) to TCM remains challenging due to its reliance on holistic reasoning, implicit logic, and multimodal diagnostic cues. Existing TCM-domain LLMs have made progress in text-based understanding but lack multimodal integration, interpretabilit… ▽ More Traditional Chinese Medicine (TCM), with a history spanning over two millennia, plays a role in global healthcare. However, applying large language models (LLMs) to TCM remains challenging due to its reliance on holistic reasoning, implicit logic, and multimodal diagnostic cues. Existing TCM-domain LLMs have made progress in text-based understanding but lack multimodal integration, interpretability, and clinical applicability. To address these limitations, we developed BenCao, a ChatGPT-based multimodal assistant for TCM, integrating structured knowledge bases, diagnostic data, and expert feedback refinement. BenCao was trained through natural language instruction tuning rather than parameter retraining, aligning with expert-level reasoning and ethical norms specific to TCM. The system incorporates a comprehensive knowledge base of over 1,000 classical and modern texts, a scenario-based instruction framework for diverse interactions, a chain-of-thought simulation mechanism for interpretable reasoning, and a feedback refinement process involving licensed TCM practitioners. BenCao connects to external APIs for tongue-image classification and multimodal database retrieval, enabling dynamic access to diagnostic resources. In evaluations across single-choice question benchmarks and multimodal classification tasks, BenCao achieved superior accuracy to general-domain and TCM-domain models, particularly in diagnostics, herb recognition, and constitution classification. The model was deployed as an interactive application on the OpenAI GPTs Store, accessed by nearly 1,000 users globally as of October 2025. This study demonstrates the feasibility of developing a TCM-domain LLM through natural language-based instruction tuning and multimodal integration, offering a practical framework for aligning generative AI with traditional medical reasoning and a scalable pathway for real-world deployment. △ Less

Submitted 20 October, 2025; originally announced October 2025.

Leveraging Group Relative Policy Optimization to Advance Large Language Models in Traditional Chinese Medicine

Authors: Jiacheng Xie, Shuai Zeng, Yang Yu, Xiaoting Tang, Guanghui An, Dong Xu

Abstract: Traditional Chinese Medicine (TCM) presents a rich and structurally unique knowledge system that challenges conventional applications of large language models (LLMs). Although previous TCM-specific LLMs have shown progress through supervised fine-tuning, they often face limitations in alignment, data quality, and evaluation consistency. In this study, we introduce Ladder-base, the first TCM-focuse… ▽ More Traditional Chinese Medicine (TCM) presents a rich and structurally unique knowledge system that challenges conventional applications of large language models (LLMs). Although previous TCM-specific LLMs have shown progress through supervised fine-tuning, they often face limitations in alignment, data quality, and evaluation consistency. In this study, we introduce Ladder-base, the first TCM-focused LLM trained with Group Relative Policy Optimization (GRPO), a reinforcement learning method that improves reasoning and factual consistency by optimizing response selection based on intra-group comparisons. Ladder-base is built upon the Qwen2.5-7B-Instruct foundation model and trained exclusively on the textual subset of the TCM-Ladder benchmark, using 80 percent of the data for training and the remaining 20 percent split evenly between validation and test sets. Through standardized evaluation, Ladder-base demonstrates superior performance across multiple reasoning metrics when compared to both state-of-the-art general-purpose LLMs such as GPT-4, Gemini 2.5, Claude 3, and Qwen3 and domain-specific TCM models including BenTsao, HuatuoGPT2, and Zhongjing. These findings suggest that GRPO provides an effective and efficient strategy for aligning LLMs with expert-level reasoning in traditional medical domains and supports the development of trustworthy and clinically grounded TCM artificial intelligence systems. △ Less

Submitted 20 October, 2025; originally announced October 2025.

TOM: An Open-Source Tongue Segmentation Method with Multi-Teacher Distillation and Task-Specific Data Augmentation

Authors: Jiacheng Xie, Ziyang Zhang, Biplab Poudel, Congyu Guo, Yang Yu, Guanghui An, Xiaoting Tang, Lening Zhao, Chunhui Xu, Dong Xu

Abstract: Tongue imaging serves as a valuable diagnostic tool, particularly in Traditional Chinese Medicine (TCM). The quality of tongue surface segmentation significantly affects the accuracy of tongue image classification and subsequent diagnosis in intelligent tongue diagnosis systems. However, existing research on tongue image segmentation faces notable limitations, and there is a lack of robust and use… ▽ More Tongue imaging serves as a valuable diagnostic tool, particularly in Traditional Chinese Medicine (TCM). The quality of tongue surface segmentation significantly affects the accuracy of tongue image classification and subsequent diagnosis in intelligent tongue diagnosis systems. However, existing research on tongue image segmentation faces notable limitations, and there is a lack of robust and user-friendly segmentation tools. This paper proposes a tongue image segmentation model (TOM) based on multi-teacher knowledge distillation. By incorporating a novel diffusion-based data augmentation method, we enhanced the generalization ability of the segmentation model while reducing its parameter size. Notably, after reducing the parameter count by 96.6% compared to the teacher models, the student model still achieves an impressive segmentation performance of 95.22% mIoU. Furthermore, we packaged and deployed the trained model as both an online and offline segmentation tool (available at https://itongue.cn/), allowing TCM practitioners and researchers to use it without any programming experience. We also present a case study on TCM constitution classification using segmented tongue patches. Experimental results demonstrate that training with tongue patches yields higher classification performance and better interpretability than original tongue images. To our knowledge, this is the first open-source and freely available tongue image segmentation tool. △ Less

Submitted 19 August, 2025; originally announced August 2025.

Comments: Tongue segmentation, data augmentation, synthetic data for AI training, prompt engineering, Segment Anything Model, knowledge distillation, tongue classification

Large Language Models Facilitate Vision Reflection in Image Classification

Authors: Guoyuan An, JaeYoon Kim, SungEui Yoon

Abstract: This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition accuracy, even on benchmarks like ImageNet, despite prior evidence that LMMs typically underperform dedicated vision encoders. Second, we analyze the internal beha… ▽ More This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition accuracy, even on benchmarks like ImageNet, despite prior evidence that LMMs typically underperform dedicated vision encoders. Second, we analyze the internal behavior of vision reflection and find that the vision-language connector maps visual features into explicit textual concepts, allowing the language model to reason about prediction plausibility using commonsense knowledge. We further observe that replacing a large number of vision tokens with only a few text tokens still enables LLaVA to generate similar answers, suggesting that LMMs may rely primarily on a compact set of distilled textual representations rather than raw vision features. Third, we show that a training-free connector can enhance LMM performance in fine-grained recognition tasks, without extensive feature-alignment training. Together, these findings offer new insights into the explainability of vision-language models and suggest that vision reflection is a promising strategy for achieving robust and interpretable visual recognition. △ Less

Submitted 1 August, 2025; originally announced August 2025.

Optimal $C^{\frac{1}{2}}$ regularity of the Boltzmann equation in non-convex domains

Authors: Gayoung An, Donghyun Lee

Abstract: Regularity of the Boltzmann equation, particularly in the presence of physical boundary conditions, heavily relies on the geometry of the boundaries. In the case of non-convex domains with specular reflection boundary conditions, the problem remained outstanding until recently due to the severe singularity of billiard trajectories near the grazing set, where the trajectory map is not differentiabl… ▽ More Regularity of the Boltzmann equation, particularly in the presence of physical boundary conditions, heavily relies on the geometry of the boundaries. In the case of non-convex domains with specular reflection boundary conditions, the problem remained outstanding until recently due to the severe singularity of billiard trajectories near the grazing set, where the trajectory map is not differentiable. This challenge was addressed in [32], where $C^{\frac{1}{2}-}_{x,v}$ Hölder regularity was proven. In this paper, we introduce a novel dynamical singular regime integration methodology to establish the optimal $C^{\frac{1}{2}}_{x,v}$ regularity for the Boltzmann equation past a convex obstacle. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Comments: 60 pages, 8 figures

TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine

Authors: Jiacheng Xie, Yang Yu, Ziyang Zhang, Shuai Zeng, Jiaxuan He, Ayush Vasireddy, Xiaoting Tang, Congyu Guo, Lening Zhao, Congcong Jing, Guanghui An, Dong Xu

Abstract: Traditional Chinese Medicine (TCM), as an effective alternative medicine, has been receiving increasing attention. In recent years, the rapid development of large language models (LLMs) tailored for TCM has highlighted the urgent need for an objective and comprehensive evaluation framework to assess their performance on real-world tasks. However, existing evaluation datasets are limited in scope a… ▽ More Traditional Chinese Medicine (TCM), as an effective alternative medicine, has been receiving increasing attention. In recent years, the rapid development of large language models (LLMs) tailored for TCM has highlighted the urgent need for an objective and comprehensive evaluation framework to assess their performance on real-world tasks. However, existing evaluation datasets are limited in scope and primarily text-based, lacking a unified and standardized multimodal question-answering (QA) benchmark. To address this issue, we introduce TCM-Ladder, the first comprehensive multimodal QA dataset specifically designed for evaluating large TCM language models. The dataset covers multiple core disciplines of TCM, including fundamental theory, diagnostics, herbal formulas, internal medicine, surgery, pharmacognosy, and pediatrics. In addition to textual content, TCM-Ladder incorporates various modalities such as images and videos. The dataset was constructed using a combination of automated and manual filtering processes and comprises over 52,000 questions. These questions include single-choice, multiple-choice, fill-in-the-blank, diagnostic dialogue, and visual comprehension tasks. We trained a reasoning model on TCM-Ladder and conducted comparative experiments against nine state-of-the-art general domain and five leading TCM-specific LLMs to evaluate their performance on the dataset. Moreover, we propose Ladder-Score, an evaluation method specifically designed for TCM question answering that effectively assesses answer quality in terms of terminology usage and semantic expression. To the best of our knowledge, this is the first work to systematically evaluate mainstream general domain and TCM-specific LLMs on a unified multimodal benchmark. The datasets and leaderboard are publicly available at https://tcmladder.com and will be continuously updated. △ Less

Submitted 24 October, 2025; v1 submitted 29 May, 2025; originally announced May 2025.

Beyond Whole Dialogue Modeling: Contextual Disentanglement for Conversational Recommendation

Authors: Guojia An, Jie Zou, Jiwei Wei, Chaoning Zhang, Fuming Sun, Yang Yang

Abstract: Conversational recommender systems aim to provide personalized recommendations by analyzing and utilizing contextual information related to dialogue. However, existing methods typically model the dialogue context as a whole, neglecting the inherent complexity and entanglement within the dialogue. Specifically, a dialogue comprises both focus information and background information, which mutually i… ▽ More Conversational recommender systems aim to provide personalized recommendations by analyzing and utilizing contextual information related to dialogue. However, existing methods typically model the dialogue context as a whole, neglecting the inherent complexity and entanglement within the dialogue. Specifically, a dialogue comprises both focus information and background information, which mutually influence each other. Current methods tend to model these two types of information mixedly, leading to misinterpretation of users' actual needs, thereby lowering the accuracy of recommendations. To address this issue, this paper proposes a novel model to introduce contextual disentanglement for improving conversational recommender systems, named DisenCRS. The proposed model DisenCRS employs a dual disentanglement framework, including self-supervised contrastive disentanglement and counterfactual inference disentanglement, to effectively distinguish focus information and background information from the dialogue context under unsupervised conditions. Moreover, we design an adaptive prompt learning module to automatically select the most suitable prompt based on the specific dialogue context, fully leveraging the power of large language models. Experimental results on two widely used public datasets demonstrate that DisenCRS significantly outperforms existing conversational recommendation models, achieving superior performance on both item recommendation and response generation tasks. △ Less

Submitted 24 April, 2025; originally announced April 2025.

Identifying Bug Inducing Commits by Combining Fault Localisation and Code Change Histories

Authors: Gabin An, Jinsu Choi, Jingun Hong, Naryeong Kim, Shin Yoo

Abstract: A Bug Inducing Commit (BIC) is a code change that introduces a bug into the codebase. Although the abnormal or unexpected behavior caused by the bug may not manifest immediately, it will eventually lead to program failures further down the line. When such a program failure is observed, identifying the relevant BIC can aid in the bug resolution process, because knowing the original intent and conte… ▽ More A Bug Inducing Commit (BIC) is a code change that introduces a bug into the codebase. Although the abnormal or unexpected behavior caused by the bug may not manifest immediately, it will eventually lead to program failures further down the line. When such a program failure is observed, identifying the relevant BIC can aid in the bug resolution process, because knowing the original intent and context behind the code change, as well as having a link to the author of that change, can facilitate bug triaging and debugging. However, existing BIC identification techniques have limitations. Bisection can be computationally expensive because it requires executing failing tests against previous versions of the codebase. Other techniques rely on the availability of specific post hoc artifacts, such as bug reports or bug fixes. In this paper, we propose a technique called Fonte that aims to identify the BIC with a core concept that a commit is more likely to be a BIC if it has more recently modified code elements that are highly suspicious of containing the bug. To realise this idea, Fonte leverages two fundamental relationships in software: the failure-to-code relationship, which can be quantified through fault localisation techniques, and the code-to-commit relationship, which can be obtained from version control systems. Our empirical evaluation using 206 real-world BICs from open-source Java projects shows that Fonte significantly outperforms state-of-the-art BIC identification techniques, achieving up to 45.8% higher MRR. We also report that the ranking scores produced by Fonte can be used to perform weighted bisection. Finally, we apply Fonte to a large-scale industry project with over 10M lines of code, and show that it can rank the actual BIC within the top five commits for 87% of the studied real batch-testing failures, and save the BIC inspection cost by 32% on average. △ Less

Submitted 19 February, 2025; v1 submitted 18 February, 2025; originally announced February 2025.

Comments: 14 pages, 10 figures. Extended version of Fonte (ICSE'23, arXiv:2212.06376)

COSMosFL: Ensemble of Small Language Models for Fault Localisation

Authors: Hyunjoon Cho, Sungmin Kang, Gabin An, Shin Yoo

Abstract: LLMs are rapidly being adopted to build powerful tools and agents for software engineering, but most of them rely heavily on extremely large closed-source models. This, in turn, can hinder wider adoption due to security issues as well as financial cost and environmental impact. Recently, a number of open source Small Language Models (SLMs) are being released and gaining traction. While SLMs are sm… ▽ More LLMs are rapidly being adopted to build powerful tools and agents for software engineering, but most of them rely heavily on extremely large closed-source models. This, in turn, can hinder wider adoption due to security issues as well as financial cost and environmental impact. Recently, a number of open source Small Language Models (SLMs) are being released and gaining traction. While SLMs are smaller, more energy-efficient, and therefore easier to locally deploy, they tend to show worse performance when compared to larger closed LLMs. We present COSMos, a task-level LLM ensemble technique that uses voting mechanism, to provide a broader range of choice between SLMs and LLMs. We instantiate COSMos with an LLM-based Fault Localisation technique, AutoFL, and report the cost-benefit trade-off between LLM accuracy and various costs such as energy consumption, inference time, and the number of tokens used. An empirical evaluation using Defects4J shows that COSMos can build effective ensembles that can achieve Pareto-optimality in terms of FL accuracy and inference cost, when compared to individual models. △ Less

Submitted 5 February, 2025; originally announced February 2025.

Comments: LLM4Code 2025 Workshop

METAMON: Finding Inconsistencies between Program Documentation and Behavior using Metamorphic LLM Queries

Authors: Hyeonseok Lee, Gabin An, Shin Yoo

Abstract: Code documentation can, if written precisely, help developers better understand the code they accompany. However, unlike code, code documentation cannot be automatically verified via execution, potentially leading to inconsistencies between documentation and the actual behavior. While such inconsistencies can be harmful for the developer's understanding of the code, checking and finding them remai… ▽ More Code documentation can, if written precisely, help developers better understand the code they accompany. However, unlike code, code documentation cannot be automatically verified via execution, potentially leading to inconsistencies between documentation and the actual behavior. While such inconsistencies can be harmful for the developer's understanding of the code, checking and finding them remains a costly task due to the involvement of human engineers. This paper proposes METAMON, which uses an existing search-based test generation technique to capture the current program behavior in the form of test cases, and subsequently uses LLM-based code reasoning to identify the generated regression test oracles that are not consistent with the program specifications in the documentation. METAMON is supported in this task by metamorphic testing and self-consistency. An empirical evaluation against 9,482 pairs of code documentation and code snippets, generated using five open-source projects from Defects4J v2.0.1, shows that METAMON can classify the code-and-documentation inconsistencies with a precision of 0.72 and a recall of 0.48. △ Less

Submitted 4 February, 2025; originally announced February 2025.

Comments: 8 pages and 7 figures, accepted to LLM4Code 2025

Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths

Authors: Naryeong Kim, Sungmin Kang, Gabin An, Shin Yoo

Abstract: Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency, i.e., the idea that the answer obtained from sampling and marginalising a number of multiple independent inferences is more likely to be correct, has received much attention as a simple validation technique. This paper… ▽ More Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency, i.e., the idea that the answer obtained from sampling and marginalising a number of multiple independent inferences is more likely to be correct, has received much attention as a simple validation technique. This paper aims to empirically verify this intuitive hypothesis by predicting the correctness of answers obtained using self-consistency from properties of the samples of reasoning paths. We introduce Lachesis, a predictive model for self-consistency based LLM inferences, and empirically evaluate it using AutoFL, a recently proposed LLM-based fault localisation technique, as the target technique that uses self-consistency. Lachesis converts collected reasoning paths from AutoFL using specifically designed reasoning path representations, and trains LSTM and GCN models to predict whether a given set of reasoning paths would result in a correct answer. The results suggest that Lachesis can predict the correctness of answers with a precision of up to 0.8136, highlighting the possibility of training a predictive model that can allow early termination of inferences that are not likely to be successful. △ Less

Submitted 11 December, 2024; originally announced December 2024.

Comments: To appear at DeepTest 2025

A variational quantum algorithm by Bayesian Inference with von Mises-Fisher distribution

Authors: Trung Huynh, Gwangil An, Minsu Kim, Yu-Seong Jeon, Jinhyoung Lee

Abstract: The variational quantum eigensolver algorithm has gained attentions due to its capability of locating the ground state and ground energy of a Hamiltonian, which is a fundamental task in many physical and chemical problems. Although it has demonstrated promising results, the use of various types of measurements remains a significant obstacle. Recently, a quantum phase estimation algorithm inspired… ▽ More The variational quantum eigensolver algorithm has gained attentions due to its capability of locating the ground state and ground energy of a Hamiltonian, which is a fundamental task in many physical and chemical problems. Although it has demonstrated promising results, the use of various types of measurements remains a significant obstacle. Recently, a quantum phase estimation algorithm inspired measurement scheme has been proposed to overcome this issue by introducing an additional ancilla system that is coupled to the primary system. Based on this measurement scheme, we present a novel approach that employs Bayesian inference principles together with von Mises-Fisher distribution and theoretically demonstrates the new algorithm's capability in identifying the ground state with certain for various random Hamiltonian matrices. This also opens a new way for exploring the von Mises-Fisher distribution potential in other quantum information science problems. △ Less

Submitted 3 October, 2024; originally announced October 2024.

OpenSlot: Mixed Open-Set Recognition with Object-Centric Learning

Authors: Xu Yin, Fei Pan, Guoyuan An, Yuchi Huo, Zixuan Xie, Sung-Eui Yoon

Abstract: Existing open-set recognition (OSR) studies typically assume that each image contains only one class label, with the unknown test set (negative) having a disjoint label space from the known test set (positive), a scenario referred to as full-label shift. This paper introduces the mixed OSR problem, where test images contain multiple class semantics, with both known and unknown classes co-occurring… ▽ More Existing open-set recognition (OSR) studies typically assume that each image contains only one class label, with the unknown test set (negative) having a disjoint label space from the known test set (positive), a scenario referred to as full-label shift. This paper introduces the mixed OSR problem, where test images contain multiple class semantics, with both known and unknown classes co-occurring in the negatives, leading to a more complex super-label shift that better reflects real-world scenarios. To tackle this challenge, we propose the OpenSlot framework, based on object-centric learning, which uses slot features to represent diverse class semantics and generate class predictions. The proposed anti-noise slot (ANS) technique helps mitigate the impact of noise (invalid or background) slots during classification training, addressing the semantic misalignment between class predictions and ground truth. We evaluate OpenSlot on both mixed and conventional OSR benchmarks. Without elaborate designs, our method not only excels existing approaches in detecting super-label shifts across OSR tasks, but also achieves state-of-the-art performance on conventional benchmarks. Meanwhile, OpenSlot can localize class objects without using bounding boxes during training, demonstrating competitive performance in open-set object detection and potential for generalization. △ Less

Submitted 4 January, 2025; v1 submitted 2 July, 2024; originally announced July 2024.

Comments: This study is under IEEE TMM review

Quantitative pointwise estimates of the cooling process for inelastic Boltzmann equation

Authors: Gayoung An, Jin Woo Jang, Donghyun Lee

Abstract: In this paper, we study the homogeneous inelastic Boltzmann equation for hard spheres. We first prove that the solution $f(t,v)$ is bounded pointwise from above by $C_{f_0}\langle t \rangle^3$ and establish that the cooling time is infinite $T_c = +\infty$ under the condition $f_0 \in L^1_2 \cap L^{\infty}_{s}$ for $s > 2$. Away from zero velocity, we further prove that… ▽ More In this paper, we study the homogeneous inelastic Boltzmann equation for hard spheres. We first prove that the solution $f(t,v)$ is bounded pointwise from above by $C_{f_0}\langle t \rangle^3$ and establish that the cooling time is infinite $T_c = +\infty$ under the condition $f_0 \in L^1_2 \cap L^{\infty}_{s}$ for $s > 2$. Away from zero velocity, we further prove that $f(t,v)\leq C_{f_0, |v|} \langle t \rangle$ for $v \neq 0$ at any time $t > 0$. This time-dependent pointwise upper bound is natural in the cooling process, as we expect the density near $v = 0$ to grow rapidly. We also establish an upper bound that depends on the coefficient of normal restitution constant, $α\in (0,1]$. This upper bound becomes constant when $α= 1$, restoring the known upper bound for elastic collisions [8]. Consequently, through these results, we obtain Maxwellian upper bounds on the solutions at each time. △ Less

Submitted 10 August, 2025; v1 submitted 21 June, 2024; originally announced June 2024.

Comments: 33 pages, 4 figures, Correct a typo

Journal ref: Journal of Statistical Physics 192, 112 (2025)

Accurate and Fast Pixel Retrieval with Spatial and Uncertainty Aware Hypergraph Diffusion

Authors: Guoyuan An, Yuchi Huo, Sung-Eui Yoon

Abstract: This paper presents a novel method designed to enhance the efficiency and accuracy of both image retrieval and pixel retrieval. Traditional diffusion methods struggle to propagate spatial information effectively in conventional graphs due to their reliance on scalar edge weights. To overcome this limitation, we introduce a hypergraph-based framework, uniquely capable of efficiently propagating spa… ▽ More This paper presents a novel method designed to enhance the efficiency and accuracy of both image retrieval and pixel retrieval. Traditional diffusion methods struggle to propagate spatial information effectively in conventional graphs due to their reliance on scalar edge weights. To overcome this limitation, we introduce a hypergraph-based framework, uniquely capable of efficiently propagating spatial information using local features during query time, thereby accurately retrieving and localizing objects within a database. Additionally, we innovatively utilize the structural information of the image graph through a technique we term "community selection". This approach allows for the assessment of the initial search result's uncertainty and facilitates an optimal balance between accuracy and speed. This is particularly crucial in real-world applications where such trade-offs are often necessary. Our experimental results, conducted on the (P)ROxford and (P)RParis datasets, demonstrate the significant superiority of our method over existing diffusion techniques. We achieve state-of-the-art (SOTA) accuracy in both image-level and pixel-level retrieval, while also maintaining impressive processing speed. This dual achievement underscores the effectiveness of our hypergraph-based framework and community selection technique, marking a notable advancement in the field of content-based image retrieval. △ Less

Submitted 17 June, 2024; originally announced June 2024.

A design specification for Critical Illness Digital Twins to cure sepsis: responding to the National Academies of Sciences, Engineering and Medicine Report: Foundational Research Gaps and Future Directions for Digital Twins

Authors: Gary An, Chase Cockrell

Abstract: On December 15, 2023, The National Academies of Sciences, Engineering and Medicine (NASEM) released a report entitled: Foundational Research Gaps and Future Directions for Digital Twins. The ostensible purpose of this report was to bring some structure to the burgeoning field of digital twins by providing a working definition and a series of research challenges that need to be addressed to allow t… ▽ More On December 15, 2023, The National Academies of Sciences, Engineering and Medicine (NASEM) released a report entitled: Foundational Research Gaps and Future Directions for Digital Twins. The ostensible purpose of this report was to bring some structure to the burgeoning field of digital twins by providing a working definition and a series of research challenges that need to be addressed to allow this technology to fulfill its full potential. In the work presented herein we focus on five specific findings from the NASEM Report: 1) definition of a Digital Twin, 2) using fit-for-purpose guidance, 3) developing novel approaches to Verification, Validation and Uncertainty Quantification (VVUQ) of Digital Twins, 4) incorporating control as an explicit purpose for a Digital Twin and 5) using a Digital Twin to guide data collection and sensor development, and describe how these findings are addressed through the design specifications for a Critical Illness Digital Twin (CIDT) aimed at curing sepsis. △ Less

Submitted 16 June, 2024; v1 submitted 8 May, 2024; originally announced May 2024.

Comments: 31 pages, 13 Figures, 1 Table

Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection

Authors: Hao Shen, Lu Shi, Wanru Xu, Yigang Cen, Linna Zhang, Gaoyun An

Abstract: Video Anomaly Detection (VAD), aiming to identify abnormalities within a specific context and timeframe, is crucial for intelligent Video Surveillance Systems. While recent deep learning-based VAD models have shown promising results by generating high-resolution frames, they often lack competence in preserving detailed spatial and temporal coherence in video frames. To tackle this issue, we propos… ▽ More Video Anomaly Detection (VAD), aiming to identify abnormalities within a specific context and timeframe, is crucial for intelligent Video Surveillance Systems. While recent deep learning-based VAD models have shown promising results by generating high-resolution frames, they often lack competence in preserving detailed spatial and temporal coherence in video frames. To tackle this issue, we propose a self-supervised learning approach for VAD through an inter-patch relationship prediction task. Specifically, we introduce a two-branch vision transformer network designed to capture deep visual features of video frames, addressing spatial and temporal dimensions responsible for modeling appearance and motion patterns, respectively. The inter-patch relationship in each dimension is decoupled into inter-patch similarity and the order information of each patch. To mitigate memory consumption, we convert the order information prediction task into a multi-label learning problem, and the inter-patch similarity prediction task into a distance matrix regression problem. Comprehensive experiments demonstrate the effectiveness of our method, surpassing pixel-generation-based methods by a significant margin across three public benchmarks. Additionally, our approach outperforms other self-supervised learning-based methods. △ Less

Submitted 27 March, 2024; originally announced March 2024.

Inverse Nonlinearity Compensation of Hyperelastic Deformation in Dielectric Elastomer for Acoustic Actuation

Authors: Jin Woo Lee, Gwang Seok An, Jeong-Yun Sun, Kyogu Lee

Abstract: This paper presents an in-depth examination of the nonlinear deformation induced by dielectric actuation in pre-stressed ideal dielectric elastomers. A nonlinear ordinary differential equation that governs this deformation is formulated based on the hyperelastic model under dielectric stress. By means of numerical integration and neural network approximations, the relationship between voltage and… ▽ More This paper presents an in-depth examination of the nonlinear deformation induced by dielectric actuation in pre-stressed ideal dielectric elastomers. A nonlinear ordinary differential equation that governs this deformation is formulated based on the hyperelastic model under dielectric stress. By means of numerical integration and neural network approximations, the relationship between voltage and stretch is established. Neural networks are utilized to approximate solutions for voltage-to-stretch and stretch-to-voltage transformations obtained via an explicit Runge-Kutta method. The efficacy of these approximations is illustrated by their use in compensating for nonlinearity through the waveshaping of the input signal. The comparative analysis demonstrates that the approximated solutions are more accurate than baseline methods, resulting in reduced harmonic distortions when dielectric elastomers are used as acoustic actuators. This study highlights the effectiveness of the proposed approach in mitigating nonlinearities and enhancing the performance of dielectric elastomers in acoustic actuation applications. △ Less

Submitted 4 November, 2024; v1 submitted 8 January, 2024; originally announced January 2024.

Journal ref: IEEE Access 2024

The Mixed Convex-Concave effect on the regularity of a Boltzmann solution

Authors: Gayoung An, Donghyun Lee

Abstract: The geometric properties of domains are well-known to be crucial factors influencing the regularity of Boltzmann boundary problems. In the presence of non-convex physical boundaries, highly singular behaviors are investigated including the propagation of discontinuities \cite{Kim11} and Hölder regularity \cite{CD2022}. In this paper, we focus on studying the $C^{0,\frac{1}{4}-}$ Hölder regularity… ▽ More The geometric properties of domains are well-known to be crucial factors influencing the regularity of Boltzmann boundary problems. In the presence of non-convex physical boundaries, highly singular behaviors are investigated including the propagation of discontinuities \cite{Kim11} and Hölder regularity \cite{CD2022}. In this paper, we focus on studying the $C^{0,\frac{1}{4}-}$ Hölder regularity of the Boltzmann equation within concentric cylinders where both convex and concave features are present on the boundaries. Our findings extend the previous results of \cite{CD2022}, which primarily addressed concavity while considering the exterior of convex objects. △ Less

Submitted 6 March, 2024; v1 submitted 17 November, 2023; originally announced November 2023.

Comments: 47 pages, 11 figures ; Remark 1.5 and 1.6 were added for Theorem 1.3. Some proofs have been shortened and simplified

MSC Class: 35Q20

Journal ref: SIAM J. Math. Anal. 57 (2025), no. 1, 1086-1136

Characterization of FBK NUV-HD-Cryo SiPMs near LHe temperature

Authors: Fengbo Gu, Junhui Liao, Jiangfeng Zhou, Meiyuenan Ma, Yuanning Gao, Zhaohua Peng, Jian Zheng, Guangpeng An, Lifeng Zhang, Lei Zhang, Zhuo Liang, Xiuliang Zhao, Fabio Acerbi, Andrea Ficorella, Alberto Gola, Laura Parellada Monreal

Abstract: Five FBK ``NUV-HD-Cryo'' SiPMs have been characterized at 7 K and 10 K, with 405 nm and 530 nm LED light, respectively. The dark count rate (DCR) was measured to be $\sim$ 1 Hz for the $\sim$ 100 mm$^2$-size SiPMs, or 0.01 Hz/mm$^2$, which is $\sim$ 7 orders lower than the DCR at room temperature (RT). Given the very low DCR at these cryogenic temperatures, we measured the SiPMs' I-V curves with s… ▽ More Five FBK ``NUV-HD-Cryo'' SiPMs have been characterized at 7 K and 10 K, with 405 nm and 530 nm LED light, respectively. The dark count rate (DCR) was measured to be $\sim$ 1 Hz for the $\sim$ 100 mm$^2$-size SiPMs, or 0.01 Hz/mm$^2$, which is $\sim$ 7 orders lower than the DCR at room temperature (RT). Given the very low DCR at these cryogenic temperatures, we measured the SiPMs' I-V curves with such a method: illuminated the SiPMs with weak light, which differs from the conventional measurements at RT. Then, we measured the photo-detection efficiency (PDE), after-pulse (AP), and cross-talk (CT) with a bias voltage ranging from overvoltage (OV) 5 to 11 V. At the OV interval (5 to 11 V), the PDE was between 20\% - 45\%, and the AP and CT were both between $\sim$ 5\% and $\sim$ 20\%. With an OV higher than 10 V, the PDE would be $\ge$ 40\%, and the AP and CT are $\sim$ 20\%. Combining all of the measurements, we are confident that the SiPMs can be equipped as the photosensors on liquid helium detectors, including but not limited to the time projection chambers, which we have proposed in hunting for low-mass dark matter directly and beyond. △ Less

Submitted 3 January, 2026; v1 submitted 17 November, 2023; originally announced November 2023.

Journal ref: NIM(A) 2026

Forum on immune digital twins: a meeting report

Authors: Reinhard Laubenbacher, Fred Adler, Gary An, Filippo Castiglione, Stephen Eubank, Luis L. Fonseca, James Glazier, Tomas Helikar, Marti Jett-Tilton, Denise Kirschner, Paul Macklin, Borna Mehrad, Beth Moore, Virginia Pasour, Ilya Shmulevich, Amber Smith, Isabel Voigt, Thomas E. Yankeelov, Tjalf Ziemssen

Abstract: Medical digital twins are computational models of human biology relevant to a given medical condition, which can be tailored to an individual patient, thereby predicting the course of disease and individualized treatments, an important goal of personalized medicine. The immune system, which has a central role in many diseases, is highly heterogeneous between individuals, and thus poses a major cha… ▽ More Medical digital twins are computational models of human biology relevant to a given medical condition, which can be tailored to an individual patient, thereby predicting the course of disease and individualized treatments, an important goal of personalized medicine. The immune system, which has a central role in many diseases, is highly heterogeneous between individuals, and thus poses a major challenge for this technology. If medical digital twins are to faithfully capture the characteristics of a patient's immune system, we need to answer many questions, such as: What do we need to know about the immune system to build mathematical models that reflect features of an individual? What data do we need to collect across the different scales of immune system action? What are the right modeling paradigms to properly capture immune system complexity? In February 2023, an international group of experts convened in Lake Nona, FL for two days to discuss these and other questions related to digital twins of the immune system. The group consisted of clinicians, immunologists, biologists, and mathematical modelers, representative of the interdisciplinary nature of medical digital twin development. A video recording of the entire event is available. This paper presents a synopsis of the discussions, brief descriptions of ongoing digital twin projects at different stages of progress. It also proposes a 5-year action plan for further developing this technology. The main recommendations are to identify and pursue a small number of promising use cases, to develop stimulation-specific assays of immune function in a clinical setting, and to develop a database of existing computational immune models, as well as advanced modeling technology and infrastructure. △ Less

Submitted 26 October, 2023; originally announced October 2023.

Journal ref: npj Syst Biol Appl 10, 19 (2024). PMID: 38365857

Conceptual design and progress of transmitting $\sim$ MV DC HV into 4 K LHe detectors

Authors: Zhuo Liang, Fengbo Gu, Jiangfeng Zhou, Junhui Liao, Yuanning Gao, Zhaohua Peng, Jian Zheng, Guangpeng An, Meiyuenan Ma, Lifeng Zhang, Lei Zhang, Xiuliang Zhao, Junfeng Xia, Gang Liu, Shangmao Hu

Abstract: A dual-phase TPC (Time Projection Chamber) is more advanced in characterizing an event than a single-phase one because it can, in principle, reconstruct the 3D (X-Y-Z) image of the event, while a single-phase detector can only show a 2D (X-Y) picture. As a result, more enriched physics is expected for a dual-phase detector than a single-phase one. However, to build such a detector, DC HV (High Vol… ▽ More A dual-phase TPC (Time Projection Chamber) is more advanced in characterizing an event than a single-phase one because it can, in principle, reconstruct the 3D (X-Y-Z) image of the event, while a single-phase detector can only show a 2D (X-Y) picture. As a result, more enriched physics is expected for a dual-phase detector than a single-phase one. However, to build such a detector, DC HV (High Voltage) must be delivered into the chamber (to have a static electric field), which is a challenging task, especially for an LHe detector due to the extremely low temperature, $\sim$ 4 K, and the very high voltage, $\sim$ MV (Million Volts). This article introduces a convincing design for transmitting $\sim$ MV DC into a 4 K LHe detector. We also report the progress of manufacturing a 100 kV DC feedthrough capable of working at 4 K. Surprisingly, we realized that the technology we developed here might be a valuable reference to the scientists and engineers aiming to build residential bases on the Moon or Mars. △ Less

Submitted 19 October, 2023; originally announced October 2023.

Topological RANSAC for instance verification and retrieval without fine-tuning

Authors: Guoyuan An, Juhyung Seon, Inkyu An, Yuchi Huo, Sung-Eui Yoon

Abstract: This paper presents an innovative approach to enhancing explainable image retrieval, particularly in situations where a fine-tuning set is unavailable. The widely-used SPatial verification (SP) method, despite its efficacy, relies on a spatial model and the hypothesis-testing strategy for instance recognition, leading to inherent limitations, including the assumption of planar structures and negle… ▽ More This paper presents an innovative approach to enhancing explainable image retrieval, particularly in situations where a fine-tuning set is unavailable. The widely-used SPatial verification (SP) method, despite its efficacy, relies on a spatial model and the hypothesis-testing strategy for instance recognition, leading to inherent limitations, including the assumption of planar structures and neglect of topological relations among features. To address these shortcomings, we introduce a pioneering technique that replaces the spatial model with a topological one within the RANSAC process. We propose bio-inspired saccade and fovea functions to verify the topological consistency among features, effectively circumventing the issues associated with SP's spatial model. Our experimental results demonstrate that our method significantly outperforms SP, achieving state-of-the-art performance in non-fine-tuning retrieval. Furthermore, our approach can enhance performance when used in conjunction with fine-tuned features. Importantly, our method retains high explainability and is lightweight, offering a practical and adaptable solution for a variety of real-world applications. △ Less

Submitted 10 October, 2023; originally announced October 2023.

Just-in-Time Flaky Test Detection via Abstracted Failure Symptom Matching

Authors: Gabin An, Juyeon Yoon, Thomas Bach, Jingun Hong, Shin Yoo

Abstract: We report our experience of using failure symptoms, such as error messages or stack traces, to identify flaky test failures in a Continuous Integration (CI) pipeline for a large industrial software system, SAP HANA. Although failure symptoms are commonly used to identify similar failures, they have not previously been employed to detect flaky test failures. Our hypothesis is that flaky failures wi… ▽ More We report our experience of using failure symptoms, such as error messages or stack traces, to identify flaky test failures in a Continuous Integration (CI) pipeline for a large industrial software system, SAP HANA. Although failure symptoms are commonly used to identify similar failures, they have not previously been employed to detect flaky test failures. Our hypothesis is that flaky failures will exhibit symptoms distinct from those of non-flaky failures. Consequently, we can identify recurring flaky failures, without rerunning the tests, by matching the failure symptoms to those of historical flaky runs. This can significantly reduce the need for test reruns, ultimately resulting in faster delivery of test results to developers. To facilitate the process of matching flaky failures across different execution instances, we abstract newer test failure symptoms before matching them to the known patterns of flaky failures, inspired by previous research in the fields of failure deduplication and log analysis. We evaluate our symptom-based flakiness detection method using actual failure symptoms gathered from CI data of SAP HANA during a six-month period. Our method shows the potential of using failure symptoms to identify recurring flaky failures, achieving a precision of at least 96%, while saving approximately 58% of the machine time compared to the traditional rerun strategy. Analysis of the false positives and the feedback from developers underscore the importance of having descriptive and informative failure symptoms for both the effective deployment of this symptom-based approach and the debugging of flaky tests. △ Less

Submitted 4 November, 2023; v1 submitted 10 October, 2023; originally announced October 2023.

Comments: 10 pages

Towards Content-based Pixel Retrieval in Revisited Oxford and Paris

Authors: Guoyuan An, Woo Jae Kim, Saelyne Yang, Rong Li, Yuchi Huo, Sung-Eui Yoon

Abstract: This paper introduces the first two pixel retrieval benchmarks. Pixel retrieval is segmented instance retrieval. Like semantic segmentation extends classification to the pixel level, pixel retrieval is an extension of image retrieval and offers information about which pixels are related to the query object. In addition to retrieving images for the given query, it helps users quickly identify the q… ▽ More This paper introduces the first two pixel retrieval benchmarks. Pixel retrieval is segmented instance retrieval. Like semantic segmentation extends classification to the pixel level, pixel retrieval is an extension of image retrieval and offers information about which pixels are related to the query object. In addition to retrieving images for the given query, it helps users quickly identify the query object in true positive images and exclude false positive images by denoting the correlated pixels. Our user study results show pixel-level annotation can significantly improve the user experience. Compared with semantic and instance segmentation, pixel retrieval requires a fine-grained recognition capability for variable-granularity targets. To this end, we propose pixel retrieval benchmarks named PROxford and PRParis, which are based on the widely used image retrieval datasets, ROxford and RParis. Three professional annotators label 5,942 images with two rounds of double-checking and refinement. Furthermore, we conduct extensive experiments and analysis on the SOTA methods in image search, image matching, detection, segmentation, and dense matching using our pixel retrieval benchmarks. Results show that the pixel retrieval task is challenging to these approaches and distinctive from existing problems, suggesting that further research can advance the content-based pixel-retrieval and thus user search experience. The datasets can be downloaded from \href{https://github.com/anguoyuan/Pixel_retrieval-Segmented_instance_retrieval}{this link}. △ Less

Submitted 11 September, 2023; originally announced September 2023.

A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization

Authors: Sungmin Kang, Gabin An, Shin Yoo

Abstract: Fault Localization (FL), in which a developer seeks to identify which part of the code is malfunctioning and needs to be fixed, is a recurring challenge in debugging. To reduce developer burden, many automated FL techniques have been proposed. However, prior work has noted that existing techniques fail to provide rationales for the suggested locations, hindering developer adoption of these techniq… ▽ More Fault Localization (FL), in which a developer seeks to identify which part of the code is malfunctioning and needs to be fixed, is a recurring challenge in debugging. To reduce developer burden, many automated FL techniques have been proposed. However, prior work has noted that existing techniques fail to provide rationales for the suggested locations, hindering developer adoption of these techniques. With this in mind, we propose AutoFL, a Large Language Model (LLM)-based FL technique that generates an explanation of the bug along with a suggested fault location. AutoFL prompts an LLM to use function calls to navigate a repository, so that it can effectively localize faults over a large software repository and overcome the limit of the LLM context length. Extensive experiments on 798 real-world bugs in Java and Python reveal AutoFL improves method-level acc@1 by up to 233.3% over baselines. Furthermore, developers were interviewed on their impression of AutoFL-generated explanations, showing that developers generally liked the natural language explanations of AutoFL, and that they preferred reading a few, high-quality explanations instead of many. △ Less

Submitted 2 July, 2024; v1 submitted 10 August, 2023; originally announced August 2023.

Comments: Accepted to ACM International Conference on the Foundations of Software Engineering (FSE 2024)

Learning Test-Mutant Relationship for Accurate Fault Localisation

Authors: Jinhan Kim, Gabin An, Robert Feldt, Shin Yoo

Abstract: Context: Automated fault localisation aims to assist developers in the task of identifying the root cause of the fault by narrowing down the space of likely fault locations. Simulating variants of the faulty program called mutants, several Mutation Based Fault Localisation (MBFL) techniques have been proposed to automatically locate faults. Despite their success, existing MBFL techniques suffer fr… ▽ More Context: Automated fault localisation aims to assist developers in the task of identifying the root cause of the fault by narrowing down the space of likely fault locations. Simulating variants of the faulty program called mutants, several Mutation Based Fault Localisation (MBFL) techniques have been proposed to automatically locate faults. Despite their success, existing MBFL techniques suffer from the cost of performing mutation analysis after the fault is observed. Method: To overcome this shortcoming, we propose a new MBFL technique named SIMFL (Statistical Inference for Mutation-based Fault Localisation). SIMFL localises faults based on the past results of mutation analysis that has been done on the earlier version in the project history, allowing developers to make predictions on the location of incoming faults in a just-in-time manner. Using several statistical inference methods, SIMFL models the relationship between test results of the mutants and their locations, and subsequently infers the location of the current faults. Results: The empirical study on Defects4J dataset shows that SIMFL can localise 113 faults on the first rank out of 224 faults, outperforming other MBFL techniques. Even when SIMFL is trained on the predicted kill matrix, SIMFL can still localise 95 faults on the first rank out of 194 faults. Moreover, removing redundant mutants significantly improves the localisation accuracy of SIMFL by the number of faults localised at the first rank up to 51. Conclusion: This paper proposes a new MBFL technique called SIMFL, which exploits ahead-of-time mutation analysis to localise current faults. SIMFL is not only cost-effective, as it does not need a mutation analysis after the fault is observed, but also capable of localising faults accurately. △ Less

Submitted 4 June, 2023; originally announced June 2023.

Comments: Paper accepted for publication at IST. arXiv admin note: substantial text overlap with arXiv:1902.09729

Generating synthetic multi-dimensional molecular-mediator time series data for artificial intelligence-based disease trajectory forecasting and drug development digital twins: Considerations

Authors: Gary An, Chase Cockrell

Abstract: The use of synthetic data is recognized as a crucial step in the development of neural network-based Artificial Intelligence (AI) systems. While the methods for generating synthetic data for AI applications in other domains have a role in certain biomedical AI systems, primarily related to image processing, there is a critical gap in the generation of time series data for AI tasks where it is nece… ▽ More The use of synthetic data is recognized as a crucial step in the development of neural network-based Artificial Intelligence (AI) systems. While the methods for generating synthetic data for AI applications in other domains have a role in certain biomedical AI systems, primarily related to image processing, there is a critical gap in the generation of time series data for AI tasks where it is necessary to know how the system works. This is most pronounced in the ability to generate synthetic multi-dimensional molecular time series data (SMMTSD); this is the type of data that underpins research into biomarkers and mediator signatures for forecasting various diseases and is an essential component of the drug development pipeline. We argue the insufficiency of statistical and data-centric machine learning (ML) means of generating this type of synthetic data is due to a combination of factors: perpetual data sparsity due to the Curse of Dimensionality, the inapplicability of the Central Limit Theorem, and the limits imposed by the Causal Hierarchy Theorem. Alternatively, we present a rationale for using complex multi-scale mechanism-based simulation models, constructed and operated on to account for epistemic incompleteness and the need to provide maximal expansiveness in concordance with the Principle of Maximal Entropy. These procedures provide for the generation of SMMTD that minimizes the known shortcomings associated with neural network AI systems, namely overfitting and lack of generalizability. The generation of synthetic data that accounts for the identified factors of multi-dimensional time series data is an essential capability for the development of mediator-biomarker based AI forecasting systems, and therapeutic control development and optimization through systems like Drug Development Digital Twins. △ Less

Submitted 15 March, 2023; originally announced March 2023.

Comments: 16 pages, 2 Figures

ACM Class: I.2.m; J.3

Search for ER and/or NR-like dark matter signals with the especially low background liquid helium TPCs

Authors: Junhui Liao, Yuanning Gao, Guangpeng An, Fengbo Gu, Shangmao Hu, Zhuo Liang, Gang Liu, Meiyuenan Ma, Zhaohua Peng, Junfeng Xia, Lei Zhang, Lifeng Zhang, Xiuliang Zhao, Jian Zheng, Jiangfeng Zhou

Abstract: In the Dark Matter (DM) direct detection community, the absence of convincing signals has become a "new normal" for decades. Among other possibilities, the "new normal" might indicate that DM-matter interactions could generate not only the hypothetical NR (Nuclear Recoil) events but also the ER (Electron Recoil) ones, which have often been tagged as backgrounds historically. Further, we argue that… ▽ More In the Dark Matter (DM) direct detection community, the absence of convincing signals has become a "new normal" for decades. Among other possibilities, the "new normal" might indicate that DM-matter interactions could generate not only the hypothetical NR (Nuclear Recoil) events but also the ER (Electron Recoil) ones, which have often been tagged as backgrounds historically. Further, we argue that ER and NR-like DM signals could co-exist in a DM detector's same dataset. So in total, there would be three scenarios we can search for DM signals: (i) ER excess only, (ii) NR excess only, and (iii) ER and NR excesses combined. To effectively identify any possible DM signal under the three scenarios, a DM detector should (a) have the minimum ER and NR backgrounds and (b) be capable of discriminating ER events from NR ones. Accordingly, we introduce the newly established project, ALETHEIA, which implements liquid helium-filled TPCs (Time Projection Chambers) in hunting for DM. Thanks to the nearly single-digit number of ER and NR backgrounds on 1 ton*yr exposure, presumably, the ALETHEIA detectors could identify any form of DM-induced excess in its ROI (Research Of Interest). As far as we know, ALETHEIA is the first DM direct detection experiment claiming such an inclusive search; conventional detectors search DM mainly on the "ER excess only" and/or the "NR excess only" channel, not the "ER and NR excesses combined" channel. △ Less

Submitted 19 October, 2023; v1 submitted 23 February, 2023; originally announced February 2023.

Direct Preference-based Policy Optimization without Reward Modeling

Authors: Gaon An, Junhyeok Lee, Xingdong Zuo, Norio Kosaka, Kyung-Min Kim, Hyun Oh Song

Abstract: Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is challenging. Existing PbRL methods generally involve a two-step procedure: they first learn a reward model based on given preference data and then employ off-the-shelf reinforcement learning algorithms using the learned re… ▽ More Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is challenging. Existing PbRL methods generally involve a two-step procedure: they first learn a reward model based on given preference data and then employ off-the-shelf reinforcement learning algorithms using the learned reward model. However, obtaining an accurate reward model solely from preference information, especially when the preference is from human teachers, can be difficult. Instead, we propose a PbRL algorithm that directly learns from preference without requiring any reward modeling. To achieve this, we adopt a contrastive learning framework to design a novel policy scoring metric that assigns a high score to policies that align with the given preferences. We apply our algorithm to offline RL tasks with actual human preference labels and show that our algorithm outperforms or is on par with the existing PbRL methods. Notably, on high-dimensional control tasks, our algorithm surpasses offline RL methods that learn with ground-truth reward information. Finally, we show that our algorithm can be successfully applied to fine-tune large language models. △ Less

Submitted 27 October, 2023; v1 submitted 30 January, 2023; originally announced January 2023.

Comments: NeurIPS 2023

Fonte: Finding Bug Inducing Commits from Failures

Authors: Gabin An, Jingun Hong, Naryeong Kim, Shin Yoo

Abstract: A Bug Inducing Commit (BIC) is a commit that introduces a software bug into the codebase. Knowing the relevant BIC for a given bug can provide valuable information for debugging as well as bug triaging. However, existing BIC identification techniques are either too expensive (because they require the failing tests to be executed against previous versions for bisection) or inapplicable at the debug… ▽ More A Bug Inducing Commit (BIC) is a commit that introduces a software bug into the codebase. Knowing the relevant BIC for a given bug can provide valuable information for debugging as well as bug triaging. However, existing BIC identification techniques are either too expensive (because they require the failing tests to be executed against previous versions for bisection) or inapplicable at the debugging time (because they require post hoc artefacts such as bug reports or bug fixes). We propose Fonte, an efficient and accurate BIC identification technique that only requires test coverage. Fonte combines Fault Localisation (FL) with BIC identification and ranks commits based on the suspiciousness of the code elements that they modified. Fonte reduces the search space of BICs using failure coverage as well as a filter that detects commits that are merely style changes. Our empirical evaluation using 130 real-world BICs shows that Fonte significantly outperforms state-of-the-art BIC identification techniques based on Information Retrieval as well as neural code embedding models, achieving at least 39% higher MRR. We also report that the ranking scores produced by Fonte can be used to perform weighted bisection, further reducing the cost of BIC identification. Finally, we apply Fonte to a large-scale industry project with over 10M lines of code, and show that it can rank the actual BIC within the top five commits for 87% of the studied real batch-testing failures, and save the BIC inspection cost by 32% on average. △ Less

Submitted 14 February, 2023; v1 submitted 13 December, 2022; originally announced December 2022.

Comments: 13 pages, 10 figures, 5 tables (to be published in ICSE'23)

High-velocity tails of the inelastic and the multi-species mixture Boltzmann equations

Authors: Gayoung An, Donghyun Lee

Abstract: We study high-velocity tails of some homogeneous Boltzmann equations on $v \in \mathbb{R}_{v}^d$. First, we consider spatially homogeneous inelastic Boltzmann equation with noncutoff collision kernel, in the case of moderately soft potentials. We also study spatially homogeneous mixture Boltzmann equations : for both noncutoff collision kernel with moderately soft potentials and cutoff collision k… ▽ More We study high-velocity tails of some homogeneous Boltzmann equations on $v \in \mathbb{R}_{v}^d$. First, we consider spatially homogeneous inelastic Boltzmann equation with noncutoff collision kernel, in the case of moderately soft potentials. We also study spatially homogeneous mixture Boltzmann equations : for both noncutoff collision kernel with moderately soft potentials and cutoff collision kernel with hard potentials. In the case of noncutoff inelastic Boltzmann, we obtain \[ f(t,v) \geq a(t) e^{-b(t)|v|^p}, \quad 2 < p < 6.213 \] by extending Cancellation lemma and spreading lemma and assuming $f\in C^{\infty}$. For the Mixture type Boltzmann equations, we prove Maxwellian $p=2$. △ Less

Submitted 18 October, 2022; originally announced October 2022.

Journal ref: SIAM J. Math. Anal. 55 (2023), no. 5, 4297-4336

Facilitating automated conversion of scientific knowledge into scientific simulation models with the Machine Assisted Generation, Calibration, and Comparison (MAGCC) Framework

Authors: Chase Cockrell, Scott Christley, Gary An

Abstract: The Machine Assisted Generation, Comparison, and Calibration (MAGCC) framework provides machine assistance and automation of recurrent crucial steps and processes in the development, implementation, testing, and use of scientific simulation models. MAGCC bridges systems for knowledge extraction via natural language processing or extracted from existing mathematical models and provides a comprehens… ▽ More The Machine Assisted Generation, Comparison, and Calibration (MAGCC) framework provides machine assistance and automation of recurrent crucial steps and processes in the development, implementation, testing, and use of scientific simulation models. MAGCC bridges systems for knowledge extraction via natural language processing or extracted from existing mathematical models and provides a comprehensive workflow encompassing the composition of scientific models and artificial intelligence (AI) assisted code generation. MAGCC accomplishes this through: 1) the development of a comprehensively expressive formal knowledge representation knowledgebase, the Structured Scientific Knowledge Representation (SSKR) that encompasses all the types of information needed to make any simulation model, 2) the use of an artificially intelligent logic reasoning system, the Computational Modeling Assistant (CMA), that takes information from the SSKR and generates, in a traceable fashion, model specifications across a range of simulation modeling methods, and 3) the use of the CMA to generate executable code for a simulation model from those model specifications. The MAGCC framework can be customized any scientific domain, and future work will integrate newly developed code-generating AI systems. △ Less

Submitted 21 April, 2022; originally announced April 2022.

Comments: 20 Pages, 8 Figures, 5 Tables

Quantum phase transition of the two-dimensional Rydberg atom array in an optical cavity

Authors: Gao-Qi An, Tao Wang, Xue-Feng Zhang

Abstract: We study the two-dimensional Rydberg atom array in an optical cavity with help of the meanfield theory and the large-scale quantum Monte Carlo simulations. The strong dipole-dipole interactions between Rydberg atoms can make the system exhibit the crystal structure, and the coupling between two-level atom and cavity photon mode can result in the formation of the polariton. The interplay between th… ▽ More We study the two-dimensional Rydberg atom array in an optical cavity with help of the meanfield theory and the large-scale quantum Monte Carlo simulations. The strong dipole-dipole interactions between Rydberg atoms can make the system exhibit the crystal structure, and the coupling between two-level atom and cavity photon mode can result in the formation of the polariton. The interplay between them provides a rich quantum phase diagram including the Mott, solid-1/2, superradiant and superradiant solid phases. As the two-order co-existed phase, the superradiant solid phase breaks both translational and U(1) symmetries. Based on both numerical and analytic results, we found the region of superradiant solid is much larger than one dimensional case, so that it can be more easily observed in the experiment. Finally, we discuss how the energy gap of the Rydberg atom can affect the type of the quantum phase transition and the number of triple points. △ Less

Submitted 19 April, 2022; originally announced April 2022.

Journal ref: Phys. Rev. B 106, 134506(2022)

Derivations, local and 2-local derivations of standard operator algebras

Authors: Jun He, Haixia Zhao, Guangyu An

Abstract: Let X be a Banach space over field F (R or C). Denote by B(X) the set of all bounded linear operators on X and by F(X) the set of all finite rank operators on X. A subalgebra A of B(X) is called a standard operator algebra if A contain F(X). We give a brief proof of a well-known result that every derivation from A into B(X) is inner. There is another classical result that every local derivation on… ▽ More Let X be a Banach space over field F (R or C). Denote by B(X) the set of all bounded linear operators on X and by F(X) the set of all finite rank operators on X. A subalgebra A of B(X) is called a standard operator algebra if A contain F(X). We give a brief proof of a well-known result that every derivation from A into B(X) is inner. There is another classical result that every local derivation on B(X) is a derivation. We extend the result by proving that every local derivation from A into B(X) is a derivation. Based on these two results, we prove that every 2-local derivation from A into B(X) is a derivation. △ Less

Submitted 10 March, 2022; originally announced March 2022.

A high-precision underwater object detection based on joint self-supervised deblurring and improved spatial transformer network

Authors: Xiuyuan Li, Fengchao Li, Jiangang Yu, Guowen An

Abstract: Deep learning-based underwater object detection (UOD) remains a major challenge due to the degraded visibility and difficulty to obtain sufficient underwater object images captured from various perspectives for training. To address these issues, this paper presents a high-precision UOD based on joint self-supervised deblurring and improved spatial transformer network. A self-supervised deblurring… ▽ More Deep learning-based underwater object detection (UOD) remains a major challenge due to the degraded visibility and difficulty to obtain sufficient underwater object images captured from various perspectives for training. To address these issues, this paper presents a high-precision UOD based on joint self-supervised deblurring and improved spatial transformer network. A self-supervised deblurring subnetwork is introduced into the designed multi-task learning aided object detection architecture to force the shared feature extraction module to output clean features for detection subnetwork. Aiming at alleviating the limitation of insufficient photos from different perspectives, an improved spatial transformer network is designed based on perspective transformation, adaptively enriching image features within the network. The experimental results show that the proposed UOD approach achieved 47.9 mAP in URPC2017 and 70.3 mAP in URPC2018, outperforming many state-of-the-art UOD methods and indicating the designed method is more suitable for UOD. △ Less

Submitted 9 March, 2022; originally announced March 2022.

A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation

Authors: Xiuyuan Li, Jiangang Yu, Fengchao Li, Guowen An

Abstract: This paper proposes a high-precision self-supervised monocular VO, which is specifically designed for navigation in foggy weather. A cycled generative adversarial network is designed to obtain high-quality self-supervised loss via forcing the forward and backward half-cycle to output consistent estimation. Moreover, gradient-based loss and perceptual loss are introduced to eliminate the interferen… ▽ More This paper proposes a high-precision self-supervised monocular VO, which is specifically designed for navigation in foggy weather. A cycled generative adversarial network is designed to obtain high-quality self-supervised loss via forcing the forward and backward half-cycle to output consistent estimation. Moreover, gradient-based loss and perceptual loss are introduced to eliminate the interference of complex photometric change on self-supervised loss in foggy weather. To solve the ill-posed problem of depth estimation, a self-supervised multi-task learning aided depth estimation module is designed based on the strong correlation between the depth estimation and transmission map calculation of hazy images in foggy weather. The experimental results on the synthetic foggy KITTI dataset show that the proposed self-supervised monocular VO performs better in depth and pose estimation than other state-of-the-art monocular VO in the literature, indicating the designed method is more suitable for foggy weather. △ Less

Submitted 9 March, 2022; originally announced March 2022.

Optimal channel selection with discrete QCQP

Authors: Yeonwoo Jeong, Deokjae Lee, Gaon An, Changyong Son, Hyun Oh Song

Abstract: Reducing the high computational cost of large convolutional neural networks is crucial when deploying the networks to resource-constrained environments. We first show the greedy approach of recent channel pruning methods ignores the inherent quadratic coupling between channels in the neighboring layers and cannot safely remove inactive weights during the pruning procedure. Furthermore, due to thes… ▽ More Reducing the high computational cost of large convolutional neural networks is crucial when deploying the networks to resource-constrained environments. We first show the greedy approach of recent channel pruning methods ignores the inherent quadratic coupling between channels in the neighboring layers and cannot safely remove inactive weights during the pruning procedure. Furthermore, due to these inactive weights, the greedy methods cannot guarantee to satisfy the given resource constraints and deviate with the true objective. In this regard, we propose a novel channel selection method that optimally selects channels via discrete QCQP, which provably prevents any inactive weights and guarantees to meet the resource constraints tightly in terms of FLOPs, memory usage, and network size. We also propose a quadratic model that accurately estimates the actual inference time of the pruned network, which allows us to adopt inference time as a resource constraint option. Furthermore, we generalize our method to extend the selection granularity beyond channels and handle non-sequential connections. Our experiments on CIFAR-10 and ImageNet show our proposed pruning method outperforms other fixed-importance channel pruning methods on various network architectures. △ Less

Submitted 24 February, 2022; originally announced February 2022.

Comments: aistats2022 accepted paper

2D+3D facial expression recognition via embedded tensor manifold regularization

Authors: Yunfang Fu, Qiuqi Ruan, Ziyan Luo, Gaoyun An, Yi Jin, Jun Wan

Abstract: In this paper, a novel approach via embedded tensor manifold regularization for 2D+3D facial expression recognition (FERETMR) is proposed. Firstly, 3D tensors are constructed from 2D face images and 3D face shape models to keep the structural information and correlations. To maintain the local structure (geometric information) of 3D tensor samples in the low-dimensional tensors space during the di… ▽ More In this paper, a novel approach via embedded tensor manifold regularization for 2D+3D facial expression recognition (FERETMR) is proposed. Firstly, 3D tensors are constructed from 2D face images and 3D face shape models to keep the structural information and correlations. To maintain the local structure (geometric information) of 3D tensor samples in the low-dimensional tensors space during the dimensionality reduction, the $\ell_0$-norm of the core tensors and a tensor manifold regularization scheme embedded on core tensors are adopted via a low-rank truncated Tucker decomposition on the generated tensors. As a result, the obtained factor matrices will be used for facial expression classification prediction. To make the resulting tensor optimization more tractable, $\ell_1$-norm surrogate is employed to relax $\ell_0$-norm and hence the resulting tensor optimization problem has a nonsmooth objective function due to the $\ell_1$-norm and orthogonal constraints from the orthogonal Tucker decomposition. To efficiently tackle this tensor optimization problem, we establish the first-order optimality condition in terms of stationary points, and then design a block coordinate descent (BCD) algorithm with convergence analysis and the computational complexity. Numerical results on BU-3DFE database and Bosphorus databases demonstrate the effectiveness of our proposed approach. △ Less

Submitted 29 January, 2022; originally announced January 2022.

Prototype Guided Network for Anomaly Segmentation

Authors: Yiqing Hao, Yi Jin, Gaoyun An

Abstract: Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD) objects and output the anomaly probability for pixels. In this paper, a Prototype Guided Anomaly segmentation Network (PGAN) is proposed to extract semantic prototypes for in-dist… ▽ More Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD) objects and output the anomaly probability for pixels. In this paper, a Prototype Guided Anomaly segmentation Network (PGAN) is proposed to extract semantic prototypes for in-distribution training data from limited annotated images. In the model, prototypes are used to model the hierarchical category semantic information and distinguish OOD pixels. The proposed PGAN model includes a semantic segmentation network and a prototype extraction network. Similarity measures are adopted to optimize the prototypes. The learned semantic prototypes are used as category semantics to compare the similarity with features extracted from test images and then to generate semantic segmentation prediction. The proposed prototype extraction network can also be integrated into most semantic segmentation networks and recognize OOD pixels. On the StreetHazards dataset, the proposed PGAN model produced mIoU of 53.4% for anomaly segmentation. The experimental results demonstrate PGAN may achieve the SOTA performance in the anomaly segmentation tasks. △ Less

Submitted 15 March, 2022; v1 submitted 15 January, 2022; originally announced January 2022.

Comments: Need for edit,and improve the method for better performance