Search

Despite the advancements in training Large Language Models (LLMs) with alignment techniques to enhance the safety of generated content, these models remain susceptible to jailbreak, an adversarial attack method that exposes security vulnerabilities in LLMs. Notably, the Greedy Coordinate Gradient (GCG) method has demonstrated the ability to automatically generate adversarial suffixes that jailbreak state-of-the-art LLMs. However, the optimization process involved in GCG is highly time-consuming, rendering the jailbreaking pipeline inefficient. In this paper, we investigate the process of GCG and identify an issue of Indirect Effect, the key bottleneck of the GCG optimization. To this end, we propose the Model Attack Gradient Index GCG (MAGIC), that addresses the Indirect Effect by exploiting the gradient information of the suffix tokens, thereby accelerating the procedure by having less computation and fewer iterations. Our experiments on AdvBench show that MAGIC achieves up to a 1.5x speedup, while maintaining Attack Success Rates (ASR) on par or even higher than other baselines. Our MAGIC achieved an ASR of 74% on the Llama-2 and an ASR of 54% when conducting transfer attacks on GPT-3.5. Code is available at https://github.com/jiah-li/magic., Comment: 13 pages,2 figures, accepted by The 31st International Conference on Computational Linguistics

AI-driven models have demonstrated significant potential in automating radiology report generation for chest X-rays. However, there is no standardized benchmark for objectively evaluating their performance. To address this, we present ReXrank, https://rexrank.ai, a public leaderboard and challenge for assessing AI-powered radiology report generation. Our framework incorporates ReXGradient, the largest test dataset consisting of 10,000 studies, and three public datasets (MIMIC-CXR, IU-Xray, CheXpert Plus) for report generation assessment. ReXrank employs 8 evaluation metrics and separately assesses models capable of generating only findings sections and those providing both findings and impressions sections. By providing this standardized evaluation framework, ReXrank enables meaningful comparisons of model performance and offers crucial insights into their robustness across diverse clinical settings. Beyond its current focus on chest X-rays, ReXrank's framework sets the stage for comprehensive evaluation of automated reporting across the full spectrum of medical imaging.

Binary black holes are one of the important sources for the TianQin gravitational wave project. Our research has revealed that, for TianQin, the signal-to-noise ratio of inspiral binary black holes can be computed analytically. This finding is expected to greatly simplify the estimation of detection capabilities for binary black holes. In this paper, we demonstrated the signal-to-noise ratio relationships from stellar-mass black holes to massive black holes. With the all-sky average condition, the signal-to-noise ratio for most binary black hole signals can be determined with a relative error of $\lesssim10\%$, with notable deviations only for chirp masses near $1000~M_\odot$. In contrast, the signal-to-noise ratio without the average includes an additional term, which we refer to as the response factor. Although this term is not easily calculated analytically, we provide a straightforward estimation method with an error margin of $1\sigma$ within 2\%., Comment: 9 pages, 6 figures, comments welcome

Large language models (LLMs) have shown impressive performance in \emph{code} understanding and generation, making coding tasks a key focus for researchers due to their practical applications and value as a testbed for LLM evaluation. Data synthesis and filtering techniques have been widely adopted and shown to be highly effective in this context. In this paper, we present a focused survey and taxonomy of these techniques, emphasizing recent advancements. We highlight key challenges, explore future research directions, and offer practical guidance for new researchers entering the field.

The opening of the gravitational wave window has significantly enhanced our capacity to explore the universe's most extreme and dynamic sector. In the mHz frequency range, a diverse range of compact objects, from the most massive black holes at the farthest reaches of the Universe to the lightest white dwarfs in our cosmic backyard, generate a complex and dynamic symphony of gravitational wave signals. Once recorded by gravitational wave detectors, these unique fingerprints have the potential to decipher the birth and growth of cosmic structures over a wide range of scales, from stellar binaries and stellar clusters to galaxies and large-scale structures. The TianQin space-borne gravitational wave mission is scheduled for launch in the 2030s, with an operational lifespan of five years. It will facilitate pivotal insights into the history of our universe. This document presents a concise overview of the detectable sources of TianQin, outlining their characteristics, the challenges they present, and the expected impact of the TianQin observatory on our understanding of them., Comment: TianQin Gravitational Wave Whitepaper, 72 pages, 30 figures

When observing the chip-to-free-space light beams from silicon photonics (SiPh) to free-space, manual adjustment of camera lens is often required to obtain a focused image of the light beams. In this letter, we demonstrated an auto-focusing system based on you-only-look-once (YOLO) model. The trained YOLO model exhibits high classification accuracy of 99.7% and high confidence level >0.95 when detecting light beams from SiPh gratings. A video demonstration of real-time light beam detection, real-time computation of beam width, and auto focusing of light beams are also included.

We present Head CT Ontology Normalized Evaluation (HeadCT-ONE), a metric for evaluating head CT report generation through ontology-normalized entity and relation extraction. HeadCT-ONE enhances current information extraction derived metrics (such as RadGraph F1) by implementing entity normalization through domain-specific ontologies, addressing radiological language variability. HeadCT-ONE compares normalized entities and relations, allowing for controllable weighting of different entity types or specific entities. Through experiments on head CT reports from three health systems, we show that HeadCT-ONE's normalization and weighting approach improves the capture of semantically equivalent reports, better distinguishes between normal and abnormal reports, and aligns with radiologists' assessment of clinically significant errors, while offering flexibility to prioritize specific aspects of report content. Our results demonstrate how HeadCT-ONE enables more flexible, controllable, and granular automated evaluation of head CT reports.

Spin and valley are two fundamental properties of electrons in crystals. The similarity between them is well understood in valley-contrasting physics established decades ago in two-dimensional (2D) materials like graphene--with broken inversion symmetry, the two valleys in graphene exhibit opposite orbital magnetic moments, similar to the spin-1/2 behaviors of electrons, and opposite Berry curvature that leads to a half topological charge. However, valley-contrasting physics has never been explored in 3D crystals. Here, we develop a 3D acoustic crystal exhibiting 3D valley-contrasting physics. Unlike spin that is fundamentally binary, valley in 3D can take six different values, each carrying a vortex in a distinct direction. The topological valley transport is generalized from the edge states of 2D materials to the surface states of 3D materials, with interesting features including robust propagation, topological refraction, and valley-cavity localization. Our results open a new route for wave manipulation in 3D space., Comment: 8 pages, 5 figures

Volumetric video represents a transformative advancement in visual media, enabling users to freely navigate immersive virtual experiences and narrowing the gap between digital and real worlds. However, the need for extensive manual intervention to stabilize mesh sequences and the generation of excessively large assets in existing workflows impedes broader adoption. In this paper, we present a novel Gaussian-based approach, dubbed \textit{DualGS}, for real-time and high-fidelity playback of complex human performance with excellent compression ratios. Our key idea in DualGS is to separately represent motion and appearance using the corresponding skin and joint Gaussians. Such an explicit disentanglement can significantly reduce motion redundancy and enhance temporal coherence. We begin by initializing the DualGS and anchoring skin Gaussians to joint Gaussians at the first frame. Subsequently, we employ a coarse-to-fine training strategy for frame-by-frame human performance modeling. It includes a coarse alignment phase for overall motion prediction as well as a fine-grained optimization for robust tracking and high-fidelity rendering. To integrate volumetric video seamlessly into VR environments, we efficiently compress motion using entropy encoding and appearance using codec compression coupled with a persistent codebook. Our approach achieves a compression ratio of up to 120 times, only requiring approximately 350KB of storage per frame. We demonstrate the efficacy of our representation through photo-realistic, free-view experiences on VR headsets, enabling users to immersively watch musicians in performance and feel the rhythm of the notes at the performers' fingertips., Comment: Accepted at SIGGRAPH Asia 2024. Project page: https://nowheretrix.github.io/DualGS/

Recent advancements in artificial intelligence have significantly improved the automatic generation of radiology reports. However, existing evaluation methods fail to reveal the models' understanding of radiological images and their capacity to achieve human-level granularity in descriptions. To bridge this gap, we introduce a system, named ReXKG, which extracts structured information from processed reports to construct a comprehensive radiology knowledge graph. We then propose three metrics to evaluate the similarity of nodes (ReXKG-NSC), distribution of edges (ReXKG-AMS), and coverage of subgraphs (ReXKG-SCS) across various knowledge graphs. We conduct an in-depth comparative analysis of AI-generated and human-written radiology reports, assessing the performance of both specialist and generalist models. Our study provides a deeper understanding of the capabilities and limitations of current AI models in radiology report generation, offering valuable insights for improving model performance and clinical applicability., Comment: Code is available at: https://github.com/rajpurkarlab/ReXKG

Over the past decade, there has been extensive work in developing integrated silicon photonics (SiPh) gratings for the optical addressing of trapped ion qubits in the ion trap quantum computing community. However, when viewing beam profiles from infrared (IR) cameras, it is often difficult to determine the corresponding heights where the beam profiles are located. In this work, we developed transformer models to recognize the corresponding height categories of beam profiles of light from SiPh gratings. The model is trained using two techniques: (1) input patches, and (2) input sequence. For model trained with input patches, the model achieved recognition accuracy of 0.938. Meanwhile, model trained with input sequence shows lower accuracy of 0.895. However, when repeating the model-training 150 cycles, model trained with input patches shows inconsistent accuracy ranges between 0.445 to 0.959, while model trained with input sequence exhibit higher accuracy values between 0.789 to 0.936. The obtained outcomes can be expanded to various applications, including auto-focusing of light beam and auto-adjustment of z-axis stage to acquire desired beam profiles.

P-wave superconductors hold immense promise for both fundamental physics and practical applications due to their unusual pairing symmetry and potential topological superconductivity. However, the exploration of the p-wave superconductors has proved to be a complex endeavor. Not only are they rare in nature but also the identification of p-wave superconductors has been an arduous task in history. For example, phase-sensitive measurement, an experimental technique which can provide conclusive evidence for unconventional pairing, has not been implemented successfully to identify p-wave superconductors. Here, we study a recently discovered family of superconductors, A2Cr3As3 (A = K, Rb, Cs), which were proposed theoretically to be a candidate of p-wave superconductors. We fabricate superconducting quantum interference devices (SQUIDs) on exfoliated K2Cr3As3, and perform the phase-sensitive measurement. We observe that such SQUIDs exhibit a pronounced second-order harmonic component sin(2{\phi}) in the current-phase relation, suggesting the admixture of 0- and {\pi}-phase. By carefully examining the magnetic field dependence of the oscillation patterns of critical current and Shapiro steps under microwave irradiation, we reveal a crossover from 0- to {\pi}-dominating phase state and conclude that the existence of the {\pi}-phase is in favor of the p-wave pairing symmetry in K2Cr3As3.

This paper introduces MedTrinity-25M, a comprehensive, large-scale multimodal dataset for medicine, covering over 25 million images across 10 modalities, with multigranular annotations for more than 65 diseases. These enriched annotations encompass both global textual information, such as disease/lesion type, modality, region-specific descriptions, and inter-regional relationships, as well as detailed local annotations for regions of interest (ROIs), including bounding boxes, segmentation masks. Unlike existing approach which is limited by the availability of image-text pairs, we have developed the first automated pipeline that scales up multimodal data by generating multigranular visual and texual annotations (in the form of image-ROI-description triplets) without the need for any paired text descriptions. Specifically, data from over 90 different sources have been collected, preprocessed, and grounded using domain-specific expert models to identify ROIs related to abnormal regions. We then build a comprehensive knowledge base and prompt multimodal large language models to perform retrieval-augmented generation with the identified ROIs as guidance, resulting in multigranular texual descriptions. Compared to existing datasets, MedTrinity-25M provides the most enriched annotations, supporting a comprehensive range of multimodal tasks such as captioning and report generation, as well as vision-centric tasks like classification and segmentation. Pretraining on MedTrinity-25M, our model achieves state-of-the-art performance on VQA-RAD and PathVQA, surpassing both multimodal large language models and other representative SoTA approaches. This dataset can also be utilized to support large-scale pre-training of multimodal medical AI models, contributing to the development of future foundation models in the medical domain., Comment: The project page is at https://yunfeixie233.github.io/MedTrinity-25M

Budget allocation of marketplace levers, such as incentives for drivers and promotions for riders, has long been a technical and business challenge at Uber; understanding lever budget changes' impact and estimating cost efficiency to achieve predefined budgets is crucial, with the goal of optimal allocations that maximize business value; we introduce an end-to-end machine learning and optimization procedure to automate budget decision-making for cities, relying on feature store, model training and serving, optimizers, and backtesting; proposing state-of-the-art deep learning (DL) estimator based on S-Learner and a novel tensor B-Spline regression model, we solve high-dimensional optimization with ADMM and primal-dual interior point convex optimization, substantially improving Uber's resource allocation efficiency., Comment: To be published in the 2nd Workshop on Causal Inference and Machine Learning in Practice, KDD 2024, August 25 to 29, 2024, Barcelona, Spain, 10 pages

Large Language Models (LLMs) show promise for natural language generation in healthcare, but risk hallucinating factually incorrect information. Deploying LLMs for medical question answering necessitates reliable uncertainty estimation (UE) methods to detect hallucinations. In this work, we benchmark popular UE methods with different model sizes on medical question-answering datasets. Our results show that current approaches generally perform poorly in this domain, highlighting the challenge of UE for medical applications. We also observe that larger models tend to yield better results, suggesting a correlation between model size and the reliability of UE. To address these challenges, we propose Two-phase Verification, a probability-free Uncertainty Estimation approach. First, an LLM generates a step-by-step explanation alongside its initial answer, followed by formulating verification questions to check the factual claims in the explanation. The model then answers these questions twice: first independently, and then referencing the explanation. Inconsistencies between the two sets of answers measure the uncertainty in the original response. We evaluate our approach on three biomedical question-answering datasets using Llama 2 Chat models and compare it against the benchmarked baseline methods. The results show that our Two-phase Verification method achieves the best overall accuracy and stability across various datasets and model sizes, and its performance scales as the model size increases.

This paper investigates the cross-lingual inconsistencies observed in Large Language Models (LLMs), such as ChatGPT, Llama, and Baichuan, which have shown exceptional performance in various Natural Language Processing (NLP) tasks. Despite their successes, these models often exhibit significant inconsistencies when processing the same concepts across different languages. This study focuses on three primary questions: the existence of cross-lingual inconsistencies in LLMs, the specific aspects in which these inconsistencies manifest, and the correlation between cross-lingual consistency and multilingual capabilities of LLMs.To address these questions, we propose an innovative evaluation method for Cross-lingual Semantic Consistency (xSC) using the LaBSE model. We further introduce metrics for Cross-lingual Accuracy Consistency (xAC) and Cross-lingual Timeliness Consistency (xTC) to comprehensively assess the models' performance regarding semantic, accuracy, and timeliness inconsistencies. By harmonizing these metrics, we provide a holistic measurement of LLMs' cross-lingual consistency. Our findings aim to enhance the understanding and improvement of multilingual capabilities and interpretability in LLMs, contributing to the development of more robust and reliable multilingual language models.

Recent advances in generative vision-language models (VLMs) have exciting potential implications for AI in radiology, yet VLMs are also known to produce hallucinations, nonsensical text, and other unwanted behaviors that can waste clinicians' time and cause patient harm. Drawing on recent work on direct preference optimization (DPO), we propose a simple method for modifying the behavior of pretrained VLMs performing radiology report generation by suppressing unwanted types of generations. We apply our method to the prevention of hallucinations of prior exams, addressing a long-established problem behavior in models performing chest X-ray report generation. Across our experiments, we find that DPO fine-tuning achieves a 3.2-4.8x reduction in lines hallucinating prior exams while maintaining model performance on clinical accuracy metrics. Our work is, to the best of our knowledge, the first work to apply DPO to medical VLMs, providing a data- and compute- efficient way to suppress problem behaviors while maintaining overall clinical accuracy., Comment: Added acknowledgemnts

In recent decades, there has been a persistent pursuit of applications for surface/edge states in topological systems, driven by their dissipationless transport effects. However, there have been limited tangible breakthroughs in this field. This work demonstrates the remarkable properties of the topological insulator Ta2Pd3Te5, as a thermometer. This material exhibits a power-law correlation in temperature-dependent resistance at low temperatures, stemming from its Luttinger liquid behavior of edge states, while exhibiting semiconductor behavior at high temperatures. The power-law behavior effectively addresses the issue of infinite resistance in semiconductor thermometers at ultra-low temperatures, thereby playing a crucial role in enabling efficient thermometry in refrigerators supporting millikelvin temperatures or below. By employing chemical doping, adjusting thickness, and controlling gate voltage, its power-law behavior and semiconductor behavior can be effectively modulated. This enables efficient thermometry spanning from millikelvin temperatures to room temperature, and allows for precise local temperature measurement. Furthermore, this thermometer exhibits excellent temperature sensitivity and resolution, and can be fine-tuned to show small magnetoresistance. In summary, the Ta2Pd3Te5 thermometer, also referred to as a topological thermometer, exhibits outstanding performance and significant potential for measuring a wider range of temperatures compared to conventional low-temperature thermometers., Comment: 15 pages, 9 figures

Medical image analysis suffers from a shortage of data, whether annotated or not. This becomes even more pronounced when it comes to 3D medical images. Self-Supervised Learning (SSL) can partially ease this situation by using unlabeled data. However, most existing SSL methods can only make use of data in a single dimensionality (e.g. 2D or 3D), and are incapable of enlarging the training dataset by using data with differing dimensionalities jointly. In this paper, we propose a new cross-dimensional SSL framework based on a pseudo-3D transformation (CDSSL-P3D), that can leverage both 2D and 3D data for joint pre-training. Specifically, we introduce an image transformation based on the im2col algorithm, which converts 2D images into a format consistent with 3D data. This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis. We run extensive experiments on 13 downstream tasks, including 2D and 3D classification and segmentation. The results indicate that our CDSSL-P3D achieves superior performance, outperforming other advanced SSL methods., Comment: MICCAI 2024 accept

GWnext 2024 was a meeting held in the Kavli Institute for Astronomy and Astrophysics at Peking University in March $4^\text{th} - 8^\text{th}$, 2024. In the meeting researchers at different career stages -- with a particular focus on early career scientists -- working on the different aspects of gravitational wave (GW) astronomy gathered to discuss the current status as well as prospects of the field. The meeting was divided into three core sessions: Astrophysics, GW Theory, and Detection. Each session consisted of introductory talks and extended discussion sessions. Moreover, there was a poster session where students could present their results. In this paper, we summarize the results presented during the meeting and present the most important outcomes.

Space-borne gravitational wave detectors like TianQin might encounter data gaps due to factors like micro-meteoroid collisions or hardware failures. Such glitches will cause discontinuity in the data and have been observed in the LISA Pathfinder. The existence of such data gaps presents challenges to the data analysis for TianQin, especially for massive black hole binary mergers, since its signal-to-noise ratio (SNR) accumulates in a non-linear way, a gap near the merger could lead to significant loss of SNR. It could introduce bias in the estimate of noise properties, and furthermore the results of the parameter estimation. In this work, using simulated TianQin data with injected a massive black hole binary merger, we study the window function method, and for the first time, the inpainting method to cope with the data gap, and an iterative estimate scheme is designed to properly estimate the noise spectrum. We find that both methods can properly estimate noise and signal parameters. The easy-to-implement window function method can already perform well, except that it will sacrifice some SNR due to the adoption of the window. The inpainting method is slower, but it can minimize the impact of the data gap., Comment: 12 pages, 5 figures, comments welcome

Current medical artificial intelligence systems are often limited to narrow applications, hindering their widespread adoption in clinical practice. To address this limitation, we propose MedVersa, a generalist learner that enables flexible learning and tasking for medical image interpretation. By leveraging a large language model as a learnable orchestrator, MedVersa can learn from both visual and linguistic supervision, support multimodal inputs, and perform real-time task specification. This versatility allows MedVersa to adapt to various clinical scenarios and perform multifaceted medical image analysis. We introduce MedInterp, the largest multimodal dataset to date for medical image interpretation, consisting of over 13 million annotated instances spanning 11 tasks across 3 modalities, to support the development of MedVersa. Our experiments demonstrate that MedVersa achieves state-of-the-art performance in 9 tasks, sometimes outperforming specialist counterparts by over 10%. MedVersa is the first to showcase the viability of multimodal generative medical AI in implementing multimodal outputs, inputs, and dynamic task specification, highlighting its potential as a multifunctional system for comprehensive medical image analysis. This generalist approach to medical image interpretation paves the way for more adaptable and efficient AI-assisted clinical decision-making., Comment: Technical study

In this paper, we have studied the consequences of the $\mu$-$\tau$ reflection symmetry for leptogenesis in the type-I seesaw model with diagonal Dirac neutrino mass matrix. We have first obtained the phenomenologically allowed values of the model parameters, which show that there may exist zero or equal entries in the Majorana mass matrix for the right-handed neutrinos, and then studied their predictions for three right-handed neutrino masses, which show that there may exist two nearly degenerate right-handed neutrinos. Then, we have studied the consequences of the model for leptogenesis. Due to the $\mu$-$\tau$ reflection symmetry, leptogenesis can only work in the two-flavor regime. Furthermore, leptogenesis cannot work for the particular case of $r=1$. Accordingly, for some benchmark values of $r \neq 1$, we have given the constraints of leptogenesis for relevant parameters. Furthermore, we have investigated the possibilities of leptogenesis being induced by the renormalization group evolution effects for two particular scenarios. For the particular case of $r=1$, the renormalization group evolution effects will break the orthogonality relations among different columns of $M^{}_{\rm D}$ and consequently induce leptogenesis to work. For the low-scale resonant leptogenesis scenario which is realized for nearly degenerate right-handed neutrinos, the renormalization group evolution effects can break the $\mu$-$\tau$ reflection symmetry and consequently induce leptogenesis to work., Comment: 26 pages, 10 figures, version accepted for publication in PRD

Rapidly spinning magnetars are potential candidates for the energy source of supernovae (SNe) and gamma-ray bursts and the most promising sources for continuous gravitational waves (GWs) detected by ground-based GW detectors. Continuous GWs can be radiated from magnetars due to magnetic-induced deformation or fluid oscillations, compatible with magnetic dipole (MD) radiation for spin-down energy. In this paper, we investigate the diverse light curves of magnetar-driven SNe in the scenario that the spin-down is dominated by GW radiation and/or MD radiation. By simulating the light curves of SNe and employing the Markov chain Monte Carlo method, we constrain the parameters of the magnetars and SN explosions and show that the signature of GW radiation may be indicated by the bolometric luminosity curves of SNe Ic-BL 2007ru and 2009bb. We find that the ellipticity of magnetars in the order of $10^{-3}$ can be induced by the magnetic field of $\sim 10^{16} \mbox{ G}$. If such continuous GWs associated with SNe can be detected in the future by the Advanced LIGO and Virgo detectors, this would be a smoking gun for a magnetar engine powering SNe., Comment: 13pages, 9 figures, Accepted for publication in ApJ

The rotation curve is significant to research on dark matter and the structure of the Milky Way. But it is a great challenge to measure rotation curve accurately, and different ways obtain distinct results. In this work, we use a DIY small radio telescope to carry out hydrogen 21-cm line observations on campus, and calculate the rotation curve of inner disk by tangent method based on the model of Przemek et al. (the rotation speed of the Sun $v(R_0)=233.6\pm2.8$ km/s, and distance to the Galactic center $R_0=8.122\pm0.031$ kpc). Furthermore, we obtain the distribution of spiral arms in the Milky Way with our data by adopting different rotation curve models. We also compare our rotation curve result with previous works, analyse the possible measurement error in the tangent method, and discuss the consistence of our result with others.

We introduce an Outlier-Efficient Modern Hopfield Model (termed $\mathrm{OutEffHop}$) and use it to address the outlier inefficiency problem of {training} gigantic transformer-based models. Our main contribution is a novel associative memory model facilitating \textit{outlier-efficient} associative memory retrievals. Interestingly, this memory model manifests a model-based interpretation of an outlier-efficient attention mechanism (${\rm Softmax}_1$): it is an approximation of the memory retrieval process of $\mathrm{OutEffHop}$. Methodologically, this allows us to introduce novel outlier-efficient Hopfield layers as powerful alternatives to traditional attention mechanisms, with superior post-quantization performance. Theoretically, the Outlier-Efficient Modern Hopfield Model retains and improves the desirable properties of standard modern Hopfield models, including fixed point convergence and exponential storage capacity. Empirically, we demonstrate the efficacy of the proposed model across large-scale transformer-based and Hopfield-based models (including BERT, OPT, ViT, and STanHop-Net), benchmarking against state-of-the-art methods like $\mathtt{Clipped\_Softmax}$ and $\mathtt{Gated\_Attention}$. Notably, $\mathrm{OutEffHop}$ achieves an average reduction of 22+\% in average kurtosis and 26+\% in the maximum infinity norm of model outputs across four models. Code is available at \href{https://github.com/MAGICS-LAB/OutEffHop}{GitHub}; models are on \href{https://huggingface.co/collections/magicslabnu/outeffhop-6610fcede8d2cda23009a98f}{Hugging Face Hub}; future updates are on \href{https://arxiv.org/abs/2404.03828}{arXiv}., Comment: Accepted at ICML 2024; v2 updated to camera-ready version; Code available at https://github.com/MAGICS-LAB/OutEffHop; Models are on Hugging Face: https://huggingface.co/collections/magicslabnu/outeffhop-6610fcede8d2cda23009a98f

Automated classification of liver lesions in multi-phase CT and MR scans is of clinical significance but challenging. This study proposes a novel Siamese Dual-Resolution Transformer (SDR-Former) framework, specifically designed for liver lesion classification in 3D multi-phase CT and MR imaging with varying phase counts. The proposed SDR-Former utilizes a streamlined Siamese Neural Network (SNN) to process multi-phase imaging inputs, possessing robust feature representations while maintaining computational efficiency. The weight-sharing feature of the SNN is further enriched by a hybrid Dual-Resolution Transformer (DR-Former), comprising a 3D Convolutional Neural Network (CNN) and a tailored 3D Transformer for processing high- and low-resolution images, respectively. This hybrid sub-architecture excels in capturing detailed local features and understanding global contextual information, thereby, boosting the SNN's feature extraction capabilities. Additionally, a novel Adaptive Phase Selection Module (APSM) is introduced, promoting phase-specific intercommunication and dynamically adjusting each phase's influence on the diagnostic outcome. The proposed SDR-Former framework has been validated through comprehensive experiments on two clinical datasets: a three-phase CT dataset and an eight-phase MR dataset. The experimental results affirm the efficacy of the proposed framework. To support the scientific community, we are releasing our extensive multi-phase MR dataset for liver lesion analysis to the public. This pioneering dataset, being the first publicly available multi-phase MR dataset in this field, also underpins the MICCAI LLD-MMRI Challenge. The dataset is accessible at:https://bit.ly/3IyYlgN., Comment: 13 pages, 7 figures

In this paper we have studied the realizations of the popular TM1 neutrino mixing and neutrino $\mu$-$\tau$ reflection symmetry (which are well motivated from the neutrino oscillation data and lead to interesting phenomenological consequences) in the most minimal seesaw model with a pseudo-Dirac pair of right-handed neutrinos, and their consequences for leptogenesis. In order to realize the low-scale resonant leptogenesis scenario, we have considered two possible ways of generating the tiny mass splitting between the two right-handed neutrinos: one way is to modify their Majorana mass matrix to a form as shown in Eq. (25); the other way is to consider the renormalization-group corrections for their masses. For the $\mu$-$\tau$ reflection symmetry, in order for leptogenesis to work, we have further considered the flavor-dependent conversion efficiencies from the lepton asymmetry to the baryon asymmetry during the sphaleron processes, and its breaking via the renormalization-group corrections., Comment: 24 pages, 10 figures, version accepted for publication in PRD

The interplay between disorder and topology leads to rich phenomena such as topological Anderson insulator phases, where disorder opens a topological bandgap and thereby enhances transport. With the recent advances in non-Hermitian topological physics, topological Anderson insulators have been generalized to systems with non-Hermitian disorder. However, achieving disorder-induced nontrivial point-gap topology, which is unique to non-Hermitian systems and is responsible for non-Hermitian skin effect, remains elusive. In this work, we experimentally realized non-Hermitian disorder-induced point-gap topology in a one-dimensional acoustic crystal. By controlling the gain factor of the amplifier in each basic unit, we obtained a series of disordered unidirectional hoppings with tunable strength. Using disordered acoustic crystals under open boundary conditions, we observed the emergence of non-Hermitian skin effect and the direction reversal of skin mode localization when the disorder strength is tuned. These results serve as hallmarks of point-gap topological phase transition induced by non-Hermitian disorder. Our work paves the way for exploring various disorder-induced phenomena in non-Hermitian acoustic systems., Comment: 7 pages, 4 figures

Accurate medical image segmentation demands the integration of multi-scale information, spanning from local features to global dependencies. However, it is challenging for existing methods to model long-range global information, where convolutional neural networks (CNNs) are constrained by their local receptive fields, and vision transformers (ViTs) suffer from high quadratic complexity of their attention mechanism. Recently, Mamba-based models have gained great attention for their impressive ability in long sequence modeling. Several studies have demonstrated that these models can outperform popular vision models in various tasks, offering higher accuracy, lower memory consumption, and less computational burden. However, existing Mamba-based models are mostly trained from scratch and do not explore the power of pretraining, which has been proven to be quite effective for data-efficient medical image analysis. This paper introduces a novel Mamba-based model, Swin-UMamba, designed specifically for medical image segmentation tasks, leveraging the advantages of ImageNet-based pretraining. Our experimental results reveal the vital role of ImageNet-based training in enhancing the performance of Mamba-based models. Swin-UMamba demonstrates superior performance with a large margin compared to CNNs, ViTs, and latest Mamba-based models. Notably, on AbdomenMRI, Encoscopy, and Microscopy datasets, Swin-UMamba outperforms its closest counterpart U-Mamba_Enc by an average score of 2.72%., Comment: Code and models of Swin-UMamba are publicly available at: https://github.com/JiarunLiu/Swin-UMamba

Parameter-efficient fine-tuning (PEFT) that was initially developed for exploiting pre-trained large language models has recently emerged as an effective approach to perform transfer learning on computer vision tasks. However, the effectiveness of PEFT on medical vision foundation models is still unclear and remains to be explored. As a proof of concept, we conducted a detailed empirical study on applying PEFT to chest radiography foundation models. Specifically, we delved into LoRA, a representative PEFT method, and compared it against full-parameter fine-tuning (FFT) on two self-supervised radiography foundation models across three well-established chest radiograph datasets. Our results showed that LoRA outperformed FFT in 13 out of 18 transfer learning tasks by at most 2.9% using fewer than 1% tunable parameters. Combining LoRA with foundation models, we set up new state-of-the-art on a range of data-efficient learning tasks, such as an AUROC score of 80.6% using 1% labeled data on NIH ChestX-ray14. We hope this study can evoke more attention from the community in the use of PEFT for transfer learning on medical imaging tasks. Code and models are available at https://github.com/RL4M/MED-PEFT., Comment: Technical report

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in natural datasets. Besides, medical image-text pairs often involve numerous complex fine-grained correspondences. This paper aims to enhance the data efficiency by introducing multiple-to-multiple local relationship modeling to capture denser supervisions. More specifically, we propose a Medical Language-Image Pre-training (MLIP) framework, which exploits the limited image-text medical data more efficiently through patch-sentence matching. Furthermore, we introduce a masked contrastive learning strategy with semantic integrity estimation to reduce redundancy in images while preserving the underlying semantics. Our evaluation results show that MLIP outperforms previous work in zero/few-shot classification and few-shot segmentation tasks by a large margin., Comment: 5 pages, 3 figures

The development of medical vision-language foundation models has attracted significant attention in the field of medicine and healthcare due to their promising prospect in various clinical applications. While previous studies have commonly focused on feature learning at a single learning scale, investigation on integrating multi-scale information is lacking, which may hinder the potential for mutual reinforcement among these features. This paper aims to bridge this gap by proposing a method that effectively exploits multi-scale information to enhance the performance of medical foundation models. The proposed method simultaneously exploits features at the local, instance, modality and global aspects, facilitating comprehensive representation learning within the models. We evaluate the effectiveness of the proposed method on six open-source datasets across different clinical tasks, demonstrating its ability to enhance the performance of medical foundation models.

Defining pathologies automatically from medical images aids the understanding of the emergence and progression of diseases, and such an ability is crucial in clinical diagnostics. However, existing deep learning models heavily rely on expert annotations and lack generalization capabilities in open clinical environments. In this study, we present a generalizable vision-language model for Annotation-Free pathology Localization (AFLoc). The core strength of AFLoc lies in its extensive multi-level semantic structure-based contrastive learning, which comprehensively aligns multi-granularity medical concepts from reports with abundant image features, to adapt to the diverse expressions of pathologies and unseen pathologies without the reliance on image annotations from experts. We demonstrate the proof of concept on Chest X-ray images, with extensive experimental validation across 6 distinct external datasets, encompassing 13 types of chest pathologies. The results demonstrate that AFLoc surpasses state-of-the-art methods in pathology localization and classification, and even outperforms the human benchmark in locating 5 different pathologies. Additionally, we further verify its generalization ability by applying it to retinal fundus images. Our approach showcases AFLoc's versatilities and underscores its suitability for clinical diagnosis in complex clinical environments.

Multimodal deep learning utilizing imaging and diagnostic reports has made impressive progress in the field of medical imaging diagnostics, demonstrating a particularly strong capability for auxiliary diagnosis in cases where sufficient annotation information is lacking. Nonetheless, localizing diseases accurately without detailed positional annotations remains a challenge. Although existing methods have attempted to utilize local information to achieve fine-grained semantic alignment, their capability in extracting the fine-grained semantics of the comprehensive context within reports is limited. To address this problem, a new method is introduced that takes full sentences from textual reports as the basic units for local semantic alignment. This approach combines chest X-ray images with their corresponding textual reports, performing contrastive learning at both global and local levels. The leading results obtained by this method on multiple datasets confirm its efficacy in the task of lesion localization.