Xiao Hu

Yuzhang Xie, Keqi Han, Yunpeng Xiao et al.

Clinical decision-making (CDM) is central to real-world clinical workflows, where clinicians infer diagnoses, select treatments, or anticipate future health outcomes under incomplete evidence. LLMs are increasingly used to support these decisions due to strong language capabilities, broad biomedical knowledge, and efficiency, yet the reliability of LLMs on real-world clinical decision tasks remains insufficiently understood. To evaluate CDM models, especially LLM-based models, an ideal and practical medical decision benchmark should be constructed via an automated yet reliable pipeline to ensure both scale and quality. Moreover, the grounding of a CDM benchmark in real patient EHRs can better support evaluation on practical CDM tasks that require substantive biomedical knowledge and clinical inference. To fill the gaps, we introduce EHRBench, an automated and reliable EHR-grounded benchmark for evaluating LLM-based clinical decision-making at scale. To ensure scalability and reliability, EHRBench is constructed through an EHR-LLM-KB(knowledge-base) interaction pipeline. For efficiency, we use a specialized LLM to automatically convert encounter-level EHR trajectories into structured templates and deterministically instantiate the templates into QA items. In parallel, we apply systematic KB-based verification and enrichment to filter hallucinated or ambiguous relations and to improve reliability. Using this pipeline, we construct nearly 1M (960,067) QA items spanning three core inference-required clinical decision tasks: diagnosis, treatment, and prognosis. We benchmark more than 30 representative LLMs on EHRBench and provide detailed analyses of performance and robustness. The results show consistent capability trends across settings, further validating the reliability of EHRBench and highlighting actionable gaps toward clinically reliable LLM systems.

Jianxiong Li, Xiao Hu, Haoran Xu et al. · tsinghua

Reward function is essential in reinforcement learning (RL), serving as the guiding signal to incentivize agents to solve given tasks, however, is also notoriously difficult to design. In many cases, only imperfect rewards are available, which inflicts substantial performance loss for RL agents. In this study, we propose a unified offline policy optimization approach, \textit{RGM (Reward Gap Minimization)}, which can smartly handle diverse types of imperfect rewards. RGM is formulated as a bi-level optimization problem: the upper layer optimizes a reward correction term that performs visitation distribution matching w.r.t. some expert data; the lower layer solves a pessimistic RL problem with the corrected rewards. By exploiting the duality of the lower layer, we derive a tractable algorithm that enables sampled-based learning without any online interactions. Comprehensive experiments demonstrate that RGM achieves superior performance to existing methods under diverse settings of imperfect rewards. Further, RGM can effectively correct wrong or inconsistent rewards against expert preference and retrieve useful information from biased rewards.

Zhi Zheng, Zhaopeng Qiu, Xiao Hu et al.

The rapid development of online recruitment services has encouraged the utilization of recommender systems to streamline the job seeking process. Predominantly, current job recommendations deploy either collaborative filtering or person-job matching strategies. However, these models tend to operate as "black-box" systems and lack the capacity to offer explainable guidance to job seekers. Moreover, conventional matching-based recommendation methods are limited to retrieving and ranking existing jobs in the database, restricting their potential as comprehensive career AI advisors. To this end, here we present GIRL (GeneratIve job Recommendation based on Large language models), a novel approach inspired by recent advancements in the field of Large Language Models (LLMs). We initially employ a Supervised Fine-Tuning (SFT) strategy to instruct the LLM-based generator in crafting suitable Job Descriptions (JDs) based on the Curriculum Vitae (CV) of a job seeker. Moreover, we propose to train a model which can evaluate the matching degree between CVs and JDs as a reward model, and we use Proximal Policy Optimization (PPO)-based Reinforcement Learning (RL) method to further fine-tine the generator. This aligns the generator with recruiter feedback, tailoring the output to better meet employer preferences. In particular, GIRL serves as a job seeker-centric generative model, providing job suggestions without the need of a candidate set. This capability also enhances the performance of existing job recommendation models by supplementing job seeking features with generated content. With extensive experiments on a large-scale real-world dataset, we demonstrate the substantial effectiveness of our approach. We believe that GIRL introduces a paradigm-shifting approach to job recommendation systems, fostering a more personalized and comprehensive job-seeking experience.

Yuepeng Wang, Ken Kawano, Yongqi Zhou et al.

Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals. Existing RL formulations and simulated environments, however, are based on discrete-time MDP or POMDP abstractions with fixed or pre-specified decision intervals. Thus, it remains difficult to evaluate whether RL methods can handle time-interval-dependent disease progression, personalized treatment response, and safety between consecutive measurement points. To address this gap, we introduce MedGym, a benchmark environment for dynamic treatment recommendation. MedGym models longitudinal patient evolution in a continuous-time framework and constructs a configurable medical RL benchmark from clinical data by using Physics-Informed Neural Networks. The resulting benchmark supports both offline and online RL, and enables direct comparison between discrete-time and continuous-time methods under irregular treatment timing and patient-specific dynamics. Besides, MedGym supports evaluation from clinically important perspectives, including personalization, trajectory-level safety, and the performance gap between model-based offline learning and online deployment. By providing a standardized and configurable benchmark for continuous-time dynamic treatment, MedGym aims to facilitate more realistic and informative evaluation of medical RL methods.

Xun Shen, Yuepeng Wang, Akifumi Wachi et al.

Dynamic medical treatment requires deciding treatment intensity and intervention timing, while patient states evolve continuously and adverse events may occur between clinical interactions. Most existing treatment learning methods assume fixed schedules or enforce safety only at discrete decision points. We propose Interaction-Limited Safe Continuous-Time Reinforcement Learning, a framework that jointly optimizes treatment administration and clinical interaction timing under trajectory-level safety constraints. Our key idea is to reformulate the continuous time treatment problem as an option-based semi-Markov decision process, where each option specifies a continuous-time treatment policy and its duration. We develop a safety-tightening mechanism showing that suitably constructed constraints at interaction times guarantee safety over the full continuous-time trajectory with high probability. We further establish finite-sample guarantees for policy learning from logged treatment trajectories and introduce a practical data-driven conservative surrogate. Experiments show that the proposed adaptive interaction-timing mechanism improves both safety and treatment effectiveness over equidistant interaction schemes across different safe policy optimization methods.

Caleb Tung, Abhinav Goel, Fischer Bordwell et al.

Object detectors are vital to many modern computer vision applications. However, even state-of-the-art object detectors are not perfect. On two images that look similar to human eyes, the same detector can make different predictions because of small image distortions like camera sensor noise and lighting changes. This problem is called inconsistency. Existing accuracy metrics do not properly account for inconsistency, and similar work in this area only targets improvements on artificial image distortions. Therefore, we propose a method to use non-artificial video frames to measure object detection consistency over time, across frames. Using this method, we show that the consistency of modern object detectors ranges from 83.2% to 97.1% on different video datasets from the Multiple Object Tracking Challenge. We conclude by showing that applying image distortion corrections like .WEBP Image Compression and Unsharp Masking can improve consistency by as much as 5.1%, with no loss in accuracy.

Changwoo Lee, Xiao Hu, Hun-Seok Kim

In this paper, we propose an iterative source error correction (ISEC) decoding scheme for deep-learning-based joint source-channel coding (Deep JSCC). Given a noisy codeword received through the channel, we use a Deep JSCC encoder and decoder pair to update the codeword iteratively to find a (modified) maximum a-posteriori (MAP) solution. For efficient MAP decoding, we utilize a neural network-based denoiser to approximate the gradient of the log-prior density of the codeword space. Albeit the non-convexity of the optimization problem, our proposed scheme improves various distortion and perceptual quality metrics from the conventional one-shot (non-iterative) Deep JSCC decoding baseline. Furthermore, the proposed scheme produces more reliable source reconstruction results compared to the baseline when the channel noise characteristics do not match the ones used during training.

Zihao Ye, Yung Hsiang Lu, Xiao Hu et al.

The IEEE Low-Power Computer Vision Challenge (LPCVC) aims to promote the development of efficient vision models for edge devices, balancing accuracy with constraints such as latency, memory capacity, and energy use. The 2025 challenge featured three tracks: (1) Image classification under various lighting conditions and styles, (2) Open-Vocabulary Segmentation with Text Prompt, and (3) Monocular Depth Estimation. This paper presents the design of LPCVC 2025, including its competition structure and evaluation framework, which integrates the Qualcomm AI Hub for consistent and reproducible benchmarking. The paper also introduces the top-performing solutions from each track and outlines key trends and observations. The paper concludes with suggestions for future computer vision competitions.

Caleb Tung, Abhinav Goel, Xiao Hu et al.

Computer vision is often performed using Convolutional Neural Networks (CNNs). CNNs are compute-intensive and challenging to deploy on power-contrained systems such as mobile and Internet-of-Things (IoT) devices. CNNs are compute-intensive because they indiscriminately compute many features on all pixels of the input image. We observe that, given a computer vision task, images often contain pixels that are irrelevant to the task. For example, if the task is looking for cars, pixels in the sky are not very useful. Therefore, we propose that a CNN be modified to only operate on relevant pixels to save computation and energy. We propose a method to study three popular computer vision datasets, finding that 48% of pixels are irrelevant. We also propose the focused convolution to modify a CNN's convolutional layers to reject the pixels that are marked irrelevant. On an embedded device, we observe no loss in accuracy, while inference latency, energy consumption, and multiply-add count are all reduced by about 45%.

Zhicheng Guo, Cheng Ding, Duc H. Do et al.

Atrial fibrillation (AF) is the most common type of cardiac arrhythmia. It is associated with an increased risk of stroke, heart failure, and other cardiovascular complications, but can be clinically silent. Passive AF monitoring with wearables may help reduce adverse clinical outcomes related to AF. Detecting AF in noisy wearable data poses a significant challenge, leading to the emergence of various deep learning techniques. Previous deep learning models learn from a single modality, either electrocardiogram (ECG) or photoplethysmography (PPG) signals. However, deep learning models often struggle to learn generalizable features and rely on features that are more susceptible to corruption from noise, leading to sub-optimal performances in certain scenarios, especially with low-quality signals. Given the increasing availability of ECG and PPG signal pairs from wearables and bedside monitors, we propose a new approach, SiamAF, leveraging a novel Siamese network architecture and joint learning loss function to learn shared information from both ECG and PPG signals. At inference time, the proposed model is able to predict AF from either PPG or ECG and outperforms baseline methods on three external test sets. It learns medically relevant features as a result of our novel architecture design. The proposed model also achieves comparable performance to traditional learning regimes while requiring much fewer training labels, providing a potential approach to reduce future reliance on manual labeling.

Kling Team, Jialu Chen, Yuanzheng Ci et al.

We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.

Sully F. Chen, Zhicheng Guo, Cheng Ding et al.

Rapid, reliable, and accurate interpretation of medical time-series signals is crucial for high-stakes clinical decision-making. Deep learning methods offered unprecedented performance in medical signal processing but at a cost: they were compute-intensive and lacked interpretability. We propose Sparse Mixture of Learned Kernels (SMoLK), an interpretable architecture for medical time series processing. SMoLK learns a set of lightweight flexible kernels that form a single-layer sparse neural network, providing not only interpretability, but also efficiency, robustness, and generalization to unseen data distributions. We introduce a parameter reduction techniques to reduce the size of SMoLK's networks while maintaining performance. We test SMoLK on two important tasks common to many consumer wearables: photoplethysmography (PPG) artifact detection and atrial fibrillation detection from single-lead electrocardiograms (ECGs). We find that SMoLK matches the performance of models orders of magnitude larger. It is particularly suited for real-time applications using low-power devices, and its interpretability benefits high-stakes situations.

Pranay Jain, Cheng Ding, Cynthia Rudin et al.

Smart watches and other wearable devices are equipped with photoplethysmography (PPG) sensors for monitoring heart rate and other aspects of cardiovascular health. However, PPG signals collected from such devices are susceptible to corruption from noise and motion artifacts, which cause errors in heart rate estimation. Typical denoising approaches filter or reconstruct the signal in ways that eliminate much of the morphological information, even from the clean parts of the signal that would be useful to preserve. In this work, we develop an algorithm for denoising PPG signals that reconstructs the corrupted parts of the signal, while preserving the clean parts of the PPG signal. Our novel framework relies on self-supervised training, where we leverage a large database of clean PPG signals to train a denoising autoencoder. As we show, our reconstructed signals provide better estimates of heart rate from PPG signals than the leading heart rate estimation methods. Further experiments show significant improvement in Heart Rate Variability (HRV) estimation from PPG signals using our algorithm. We conclude that our algorithm denoises PPG signals in a way that can improve downstream analysis of many different health metrics from wearable devices.

Yi-Fan Zhang, Xingyu Lu, Shukang Yin et al.

Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks. However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make a preliminary attempt in this direction by introducing Thyme (Think Beyond Images), a novel paradigm for enabling MLLMs to transcend existing ``think with images'' approaches by autonomously generating and executing diverse image processing and computational operations via executable code. This approach not only facilitates a rich, on-the-fly set of image manipulations (e.g., cropping, rotation, contrast enhancement) but also allows for mathematical computations, all while maintaining high autonomy in deciding when and how to apply these operations. We activate this capability through a two-stage training strategy: an initial SFT on a curated dataset of 500K samples to teach code generation, followed by a RL phase to refine decision-making. For the RL stage, we manually collect and design high-resolution question-answer pairs to increase the learning difficulty, and we propose GRPO-ATS (Group Relative Policy Optimization with Adaptive Temperature Sampling), an algorithm that applies distinct temperatures to text and code generation to balance reasoning exploration with code execution precision. We conduct extensive experimental analysis and ablation studies. Comprehensive evaluations on nearly 20 benchmarks show that Thyme yields significant and consistent performance gains, particularly in challenging high-resolution perception and complex reasoning tasks.

Hong Xie, Xiao Hu, Tao Tan et al.

The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed, inconsistent conclusions also arise from time to time, making the progress illusive. Reflecting on this illusion, we still lack principled answers to two fundamental questions: 1) what is the role of each design choice? 2) which ones are critical? This paper aims to shed light on them. The underlying challenge is that design choices are entangled together, making their contribution to learning and generalization difficult to attribute. To address this challenge, we first construct a minimalist baseline for disentangling factors: one rollout per query in each round, the outcome reward serving as the training signal without any advantage trick, and a batch size of thirty-two. This baseline connects to batched contextual bandit learning, which facilitates experimental analysis. Centering around this baseline, we design an experiment pipeline, examining the marginal gains of factors like advantage, number of rollouts, etc. Experiments on three base models and two datasets, not only reveal new understanding on the role of various design choices on learning and generalization dynamics, but also identify critical ones that deserve more effort.

Yuzhang Xie, Jiaying Lu, Joyce Ho et al.

Linking (aligning) biomedical concepts across diverse data sources enables various integrative analyses, but it is challenging due to the discrepancies in concept naming conventions. Various strategies have been developed to overcome this challenge, such as those based on string-matching rules, manually crafted thesauri, and machine learning models. However, these methods are constrained by limited prior biomedical knowledge and can hardly generalize beyond the limited amounts of rules, thesauri, or training samples. Recently, large language models (LLMs) have exhibited impressive results in diverse biomedical NLP tasks due to their unprecedentedly rich prior knowledge and strong zero-shot prediction abilities. However, LLMs suffer from issues including high costs, limited context length, and unreliable predictions. In this research, we propose PromptLink, a novel biomedical concept linking framework that leverages LLMs. It first employs a biomedical-specialized pre-trained language model to generate candidate concepts that can fit in the LLM context windows. Then it utilizes an LLM to link concepts through two-stage prompts, where the first-stage prompt aims to elicit the biomedical prior knowledge from the LLM for the concept linking task and the second-stage prompt enforces the LLM to reflect on its own predictions to further enhance their reliability. Empirical results on the concept linking task between two EHR datasets and an external biomedical KG demonstrate the effectiveness of PromptLink. Furthermore, PromptLink is a generic framework without reliance on additional prior knowledge, context, or training data, making it well-suited for concept linking across various types of data sources. The source code is available at https://github.com/constantjxyz/PromptLink.

Vishal Dey, Xiao Hu, Xia Ning

Despite recent advancements, most computational methods for molecule optimization are constrained to single- or double-property optimization tasks and suffer from poor scalability and generalizability to novel optimization tasks. Meanwhile, Large Language Models (LLMs) demonstrate remarkable out-of-domain generalizability to novel tasks. To demonstrate LLMs' potential for molecule optimization, we introduce MuMOInstruct, the first high-quality instruction-tuning dataset specifically focused on complex multi-property molecule optimization tasks. Leveraging MuMOInstruct, we develop GeLLMOs, a series of instruction-tuned LLMs for molecule optimization. Extensive evaluations across 5 in-domain and 5 out-of-domain tasks demonstrate that GeLLMOs consistently outperform state-of-the-art baselines. GeLLMOs also exhibit outstanding zero-shot generalization to unseen tasks, significantly outperforming powerful closed-source LLMs. Such strong generalizability demonstrates the tremendous potential of GeLLMOs as foundational models for molecule optimization, thereby tackling novel optimization tasks without resource-intensive retraining. MuMOInstruct, models, and code are accessible through https://github.com/ninglab/GeLLMO.

Xingyu Lu, Jinpeng Wang, YiFan Zhang et al.

We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks. Specifically, to enhance Identifiability, we provide the reward model with full reference solutions as context, enabling fine-grained process verification to filter out false positives (samples with the right answer but low-quality reasoning process). To improve Reachability, we introduce a multi-turn sampling strategy where the reward model generates mistake reports for failed attempts, guiding the policy to "recover" correct responses from previously all-negative groups. Experimental results on 11 perception and reasoning benchmarks show that ContextRL significantly improves knowledge discovery efficiency. Notably, ContextRL enables the Qwen3-VL-8B model to achieve performance comparable to the 32B model, outperforming standard RLVR baselines by a large margin while effectively mitigating reward hacking. Our in-depth analysis reveals the significant potential of contextual information for improving reward model accuracy and document the widespread occurrence of reward hacking, offering valuable insights for future RLVR research.

Jiajun Jiang, Xiao Hu, Wancheng Liu et al.

Circular targets are widely used in LiDAR-camera extrinsic calibration due to their geometric consistency and ease of detection. However, achieving accurate 3D-2D circular center correspondence remains challenging. Existing methods often fail due to decoupled 3D fitting and erroneous 2D ellipse-center estimation. To address this, we propose a geometrically principled framework featuring two innovations: (i) a robust 3D circle center estimator based on conformal geometric algebra and RANSAC; and (ii) a chord-length variance minimization method to recover the true 2D projected center, resolving its dual-minima ambiguity via homography validation or a quasi-RANSAC fallback. Evaluated on synthetic and real-world datasets, our framework significantly outperforms state-of-the-art approaches. It reduces extrinsic estimation error and enables robust calibration across diverse sensors and target types, including natural circular objects. Our code will be publicly released for reproducibility.

Anni Zhao, Alex Bateh, Tyler Baldridge et al.

Defining vascular age in terms of physiological function has become one focal point of the extensive studies to categorize and track chronological age. Transcranial Doppler (TCD) is a method by which cerebral blood flow velocity is measured along the major arteries feeding the human brain. This study aims to use features extracted from TCD to estimate chronological age and assess accelerated aging in subjects with various brain diseases. We predict subjects with various brain diseases to present with accelerated cerebrovascular aging when tested on various regression models trained by healthy subjects. 168 healthy subjects and 277 diseased subjects with bilateral TCD recordings of the middle cerebral artery were analyzed using the Morphological Analysis and Clustering of Intracranial Pressure (MOCAIP) algorithm. MOCAIP-generated features and heart rate variability features were used as input features for regression models to predict the brain vascular age. 66 subjects with acute stroke, 27 subjects with post stroke, 26 subjects with Alzheimer's disease, 23 subjects with mild cognitive impairment, and 135 established subjects were tested against the machine learning model to assess for accelerated cerebrovascular age. The trained model, on average, predicted healthy subjects' cerebrovascular age to be 3.69 years above their chronological age. Subjects with different disease conditions exhibited varying levels of age acceleration. The differences in healthy and diseased subjects' performances suggest that features generated using TCD may be relevant when evaluating accelerated cerebrovascular aging. Moreover, imbalanced datasets have been observed to affect the performance of machine-learning-based brain age prediction models.

Xiao Hu, Hong Xie, Tao Tan et al.

A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive. Reflecting on this situation, two fundamental questions still lack a clear understanding: 1) what is the role of each optimizing choice? 2) which ones are the bottlenecks? This paper aims to shed light on them, and it faces the challenge of several entangled confounding factors in the fine-tuning process. To tackle this challenge, we propose a bottom-up experiment pipeline. The bottom layer is composed of a minimalist configuration: one training data, one rollout per round and the reward directly serve as the learning signal without advantage function design. This minimalist configuration connects to multi-armed bandit learning with extremely large discrete action space, which offers theories to corroborate the experiment findings. The up procedure of the experiment pipeline expanding the minimalist configuration layer by layer, examining the role of each design choice. Experimental results on three LLMs and two reasoning datasets not only reveal new understanding of the design choice but also yield essential insights to shape the area.

Vishal Dey, Xiao Hu, Xia Ning

In real-world drug design, molecule optimization requires selectively improving multiple molecular properties up to pharmaceutically relevant levels, while maintaining others that already meet such criteria. However, existing computational approaches and instruction-tuned LLMs fail to capture such nuanced property-specific objectives, limiting their practical applicability. To address this, we introduce C-MuMOInstruct, the first instruction-tuning dataset focused on multi-property optimization with explicit, property-specific objectives. Leveraging C-MuMOInstruct, we develop GeLLMO-Cs, a series of instruction-tuned LLMs that can perform targeted property-specific optimization. Our experiments across 5 in-distribution and 5 out-of-distribution tasks show that GeLLMO-Cs consistently outperform strong baselines, achieving up to 126% higher success rate. Notably, GeLLMO-Cs exhibit impressive 0-shot generalization to novel optimization tasks and unseen instructions. This offers a step toward a foundational LLM to support realistic, diverse optimizations with property-specific objectives. C-MuMOInstruct and code are accessible through https://github.com/ninglab/GeLLMO-C.

Guanchen Wu, Linzhi Zheng, Han Xie et al.

The de-identification of private information in medical data is a crucial process to mitigate the risk of confidentiality breaches, particularly when patient personal details are not adequately removed before the release of medical records. Although rule-based and learning-based methods have been proposed, they often struggle with limited generalizability and require substantial amounts of annotated data for effective performance. Recent advancements in large language models (LLMs) have shown significant promise in addressing these issues due to their superior language comprehension capabilities. However, LLMs present challenges, including potential privacy risks when using commercial LLM APIs and high computational costs for deploying open-source LLMs locally. In this work, we introduce LPPA, an LLM-empowered Privacy-Protected PHI Annotation framework for clinical notes, targeting the English language. By fine-tuning LLMs locally with synthetic notes, LPPA ensures strong privacy protection and high PHI annotation accuracy. Extensive experiments demonstrate LPPA's effectiveness in accurately de-identifying private information, offering a scalable and efficient solution for enhancing patient privacy protection.

Zongheng Guo, Tao Chen, Yang Jiao et al.

Current foundation model for photoplethysmography (PPG) signals is challenged by the intrinsic redundancy and noise of the signal. Standard masked modeling often yields trivial solutions while contrastive methods lack morphological precision. To address these limitations, we propose a Statistical-prior Informed Generative Masking Architecture (SIGMA-PPG), a generative foundation model featuring a Prior-Guided Adversarial Masking mechanism, where a reinforcement learning-driven teacher leverages statistical priors to create challenging learning paths that prevent overfitting to noise. We also incorporate a semantic consistency constraint via vector quantization to ensure that physiologically identical waveforms (even those altered by recording artifacts or minor perturbations) map to shared indices. This enhances codebook semantic density and eliminates redundant feature structures. Pre-trained on over 120,000 hours of data, SIGMA-PPG achieves superior average performance compared to five state-of-the-art baselines across 12 diverse downstream tasks. The code is available at https://github.com/ZonghengGuo/SigmaPPG.

Ruiyu Wang, Yuzhang Xie, Xiao Hu et al.

Assessing journal impact is central to scholarly communication, yet existing open resources rarely capture how collaboration structures and artificial intelligence (AI) research jointly shape venue prestige in biomedicine. We present BioMedJImpact, a large-scale, biomedical-oriented dataset designed to advance journal-level analysis of scientific impact and AI engagement. Built from 1.74 million PubMed Central articles across 2,744 journals, BioMedJImpact integrates bibliometric indicators, collaboration features, and LLM-derived semantic indicators for AI engagement. Specifically, the AI engagement feature is extracted through a reproducible three-stage LLM pipeline that we propose. Using this dataset, we analyze how collaboration intensity and AI engagement jointly influence scientific impact across pre- and post-pandemic periods (2016-2019, 2020-2023). Two consistent trends emerge: journals with higher collaboration intensity, particularly those with larger and more diverse author teams, tend to achieve greater citation impact, and AI engagement has become an increasingly strong correlate of journal prestige, especially in quartile rankings. To further validate the three-stage LLM pipeline we proposed for deriving the AI engagement feature, we conduct human evaluation, confirming substantial agreement in AI relevance detection and consistent subfield classification. Together, these contributions demonstrate that BioMedJImpact serves as both a comprehensive dataset capturing the intersection of biomedicine and AI, and a validated methodological framework enabling scalable, content-aware scientometric analysis of scientific impact and innovation dynamics. Code is available at https://github.com/JonathanWry/BioMedJImpact.

Yuhao Xu, Xiaoda Wang, Jiaying Lu et al.

Electrocardiogram (ECG) analysis plays a vital role in the early detection, monitoring, and management of various cardiovascular conditions. While existing models have achieved notable success in ECG interpretation, they fail to leverage the interrelated nature of various cardiac abnormalities. Conversely, developing a specific model capable of extracting all relevant features for multiple ECG tasks remains a significant challenge. Large-scale foundation models, though powerful, are not typically pretrained on ECG data, making full re-training or fine-tuning computationally expensive. To address these challenges, we propose EnECG(Mixture of Experts-based Ensemble Learning for ECG Multi-tasks), an ensemble-based framework that integrates multiple specialized foundation models, each excelling in different aspects of ECG interpretation. Instead of relying on a single model or single task, EnECG leverages the strengths of multiple specialized models to tackle a variety of ECG-based tasks. To mitigate the high computational cost of full re-training or fine-tuning, we introduce a lightweight adaptation strategy: attaching dedicated output layers to each foundation model and applying Low-Rank Adaptation (LoRA) only to these newly added parameters. We then adopt a Mixture of Experts (MoE) mechanism to learn ensemble weights, effectively combining the complementary expertise of individual models. Our experimental results demonstrate that by minimizing the scope of fine-tuning, EnECG can help reduce computational and memory costs while maintaining the strong representational power of foundation models. This framework not only enhances feature extraction and predictive performance but also ensures practical efficiency for real-world clinical applications. The code is available at https://github.com/yuhaoxu99/EnECG.git.

Yuhao Xu, Jiaying Lu, Sirui Ding et al.

In the process of patient diagnosis, non-invasive measurements are widely used due to their low risks and quick results. Electrocardiogram (ECG), as a non-invasive method to collect heart activities, is used to diagnose cardiac conditions. Analyzing the ECG typically requires domain expertise, which is a roadblock to applying artificial intelligence (AI) for healthcare. Through advances in self-supervised learning and foundation models, AI systems can now acquire and leverage domain knowledge without relying solely on human expertise. However, there is a lack of comprehensive analyses over the foundation models' performance on ECG. This study aims to answer the research question: "Are Foundation Models Useful for ECG Analysis?" To address it, we evaluate language/general time-series/ECG foundation models in comparison with time-series deep learning models. The experimental results show that general time-series/ECG foundation models achieve a top performance rate of 80%, indicating their effectiveness in ECG analysis. In-depth analyses and insights are provided along with comprehensive experimental results. This study highlights the limitations and potential of foundation models in advancing physiological waveform analysis. The data and code for this benchmark are publicly available at https://github.com/yuhaoxu99/ECGMultitasks-Benchmark.

Xiao Han, Chen Zhu, Xiao Hu et al.

Job recommender systems are crucial for aligning job opportunities with job-seekers in online job-seeking. However, users tend to adjust their job preferences to secure employment opportunities continually, which limits the performance of job recommendations. The inherent frequency of preference drift poses a challenge to promptly and precisely capture user preferences. To address this issue, we propose a novel session-based framework, BISTRO, to timely model user preference through fusion learning of semantic and behavioral information. Specifically, BISTRO is composed of three stages: 1) coarse-grained semantic clustering, 2) fine-grained job preference extraction, and 3) personalized top-$k$ job recommendation. Initially, BISTRO segments the user interaction sequence into sessions and leverages session-based semantic clustering to achieve broad identification of person-job matching. Subsequently, we design a hypergraph wavelet learning method to capture the nuanced job preference drift. To mitigate the effect of noise in interactions caused by frequent preference drift, we innovatively propose an adaptive wavelet filtering technique to remove noisy interaction. Finally, a recurrent neural network is utilized to analyze session-based interaction for inferring personalized preferences. Extensive experiments on three real-world offline recruitment datasets demonstrate the significant performances of our framework. Significantly, BISTRO also excels in online experiments, affirming its effectiveness in live recruitment settings. This dual success underscores the robustness and adaptability of BISTRO. The source code is available at https://github.com/Applied-Machine-Learning-Lab/BISTRO.

Xiao Hu, Ziqi Chen, Bo Peng et al.

Accurate prediction of chemical reaction yields is crucial for optimizing organic synthesis, potentially reducing time and resources spent on experimentation. With the rise of artificial intelligence (AI), there is growing interest in leveraging AI-based methods to accelerate yield predictions without conducting in vitro experiments. We present log-RRIM, an innovative graph transformer-based framework designed for predicting chemical reaction yields. A key feature of log-RRIM is its integration of a cross-attention mechanism that focuses on the interplay between reagents and reaction centers. This design reflects a fundamental principle in chemical reactions: the crucial role of reagents in influencing bond-breaking and formation processes, which ultimately affect reaction yields. log-RRIM also implements a local-to-global reaction representation learning strategy. This approach initially captures detailed molecule-level information and then models and aggregates intermolecular interactions. Through this hierarchical process, log-RRIM effectively captures how different molecular fragments contribute to and influence the overall reaction yield, regardless of their size variations. log-RRIM shows superior performance in our experiments, especially for medium to high-yielding reactions, proving its reliability as a predictor. The framework's sophisticated modeling of reactant-reagent interactions and precise capture of molecular fragment contributions make it a valuable tool for reaction planning and optimization in chemical synthesis. The data and codes of log-RRIM are accessible through https://github.com/ninglab/Yield_log_RRIM.

Weizhou Wang, Eric Liu, Xiangyu Guo et al.

Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data. In contrast, Large Language Models (LLMs) like GPT-4 are trained on vast unlabelled code corpora, yet perform only marginally better than coin flips when directly prompted to detect vulnerabilities. In this paper, we reframe vulnerability detection as anomaly detection, based on the premise that vulnerable code is rare and thus anomalous relative to patterns learned by LLMs. We introduce ANVIL, which performs a masked code reconstruction task: the LLM reconstructs a masked line of code, and deviations from the original are scored as anomalies. We propose a hybrid anomaly score that combines exact match, cross-entropy loss, prediction confidence, and structural complexity. We evaluate our approach across multiple LLM families, scoring methods, and context sizes, and against vulnerabilities after the LLM's training cut-off. On the PrimeVul dataset, ANVIL outperforms state-of-the-art supervised detectors-LineVul, LineVD, and LLMAO-achieving up to 2x higher Top-3 accuracy, 75% better Normalized MFR, and a significant improvement on ROC-AUC. Finally, by integrating ANVIL with fuzzers, we uncover two previously unknown vulnerabilities, demonstrating the practical utility of anomaly-guided detection.

Xiaoda Wang, Minxiao Wang, Kaiqiao Han et al.

Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring. Photoplethysmography (PPG) is ubiquitous in wearables but lacks ECG-specific diagnostic morphology and is corrupted by motion and sensor noise. PPG-to-ECG generation aims to bridge this gap by recovering electrical morphology and timing from peripheral pulse signals. However, existing methods largely rely on statistical alignment and data-driven generation. They fail to explicitly structure the latent space around physiology-aware electro-hemodynamic factors and lack constraints from forward physiological dynamics. To address these challenges, we propose PG-LRF, a physiology-guided latent rectified flow framework. PG-LRF introduces an electro-hemodynamic simulator that co-models ECG and PPG through shared cardiac phase dynamics. Guided by this simulator, a Physiology-Aware AutoEncoder learns a structured electro-hemodynamic latent space. Then we integrate this simulator guidance into a PPG-conditioned latent rectified flow, enforcing ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. Experiments on the large-scale MC-MED dataset demonstrate that PG-LRF significantly improves PPG-to-ECG generation and downstream cardiovascular disease classification, proving its ability to generate ECGs that are both signal-faithful and physiologically plausible under the ECG-to-PPG hemodynamic pathway

Yuzhang Xie, Yuhua Wu, Ruiyu Wang et al.

Atrial fibrillation (AF) is a major complication following embolic stroke of undetermined source (ESUS), elevating the risk of recurrent stroke and mortality. Early identification is clinically important, yet existing tools face limitations in accuracy, scalability, and cost. Machine learning (ML) offers promise but is hindered by small ESUS cohorts and high-dimensional medical features. To address these challenges, we introduce supervised and unsupervised hypergraph-based pre-training strategies to improve AF prediction in ESUS patients. We first pre-train hypergraph-based patient embedding models on a large stroke cohort (7,780 patients) to capture salient features and higher-order interactions. The resulting embeddings are transferred to a smaller ESUS cohort (510 patients), reducing feature dimensionality while preserving clinically meaningful information, enabling effective prediction with lightweight models. Experiments show that both pre-training approaches outperform traditional models trained on raw data, improving accuracy and robustness. This framework offers a scalable and efficient solution for AF risk prediction after stroke.

Guanchen Wu, Zhe Huang, Yuzhang Xie et al.

Reliable Alzheimer's disease (AD) diagnosis increasingly relies on multimodal assessments combining structural Magnetic Resonance Imaging (MRI) and Electronic Health Records (EHR). However, deploying these models is bottlenecked by modality missingness, as MRI scans are expensive and frequently unavailable in many patient cohorts. Furthermore, synthesizing de novo 3D anatomical scans from sparse, high-dimensional tabular records is technically challenging and poses severe clinical risks. To address this, we introduce MIRAGE, a novel framework that reframes the missing-MRI problem as an anatomy-guided cross-modal latent distillation task. First, MIRAGE leverages a Biomedical Knowledge Graph (KG) and Graph Attention Networks to map heterogeneous EHR variables into a unified embedding space that can be propagated from cohorts with real MRIs to cohorts without them. To bridge the semantic gap and enforce physical spatial awareness, we employ a frozen pre-trained 3D U-Net decoder strictly as an auxiliary regularization engine. Supported by a novel cohort-aggregated skip feature compensation strategy, this decoder acts as a rigorous structural penalty, forcing 1D latent representations to encode biologically plausible, macro-level pathological semantics. By exclusively utilizing this distilled "diagnostic-surrogate" representation during inference, MIRAGE completely bypasses computationally expensive 3D voxel reconstruction. Experiments demonstrate that our framework successfully bridges the missing-modality gap, improving the AD classification rate by 13% compared to unimodal baselines in cohorts without real MRIs.

Saurabh Kataria, Xiao Hu

Audio-Language Models (ALMs) are making strides in understanding speech and non-speech audio. However, domain-specialist Foundation Models (FMs) remain the best for closed-ended speech processing tasks such as Speech Emotion Recognition (SER). Using ALMs for Zero-shot SER is a popular choice, but their potential to work with specialists to achieve state-of-the-art (SOTA) performance remains unexplored. We propose ZS-Fuse, a late-fusion method that combines zero-shot emotion estimates from a dual-encoder ALM with specialist FMs. To handle ambiguity in emotions and sensitivity to prompt choice, 1) we use a simple prompt ensemble and 2) suggest a novel technique called prompt amplification, which repeats audio and text queries to discover stronger zero-shot capabilities. We demonstrate the efficacy of our technique by evaluating ZS-Fuse with three dual-encoder ALMs and two FMs, and report improvements over SOTA baselines, such as WavLM-Large, on three speech emotion recognition datasets.

Yi-Fan Zhang, Xingyu Lu, Xiao Hu et al.

Multimodal Reward Models (MRMs) play a crucial role in enhancing the performance of Multimodal Large Language Models (MLLMs). While recent advancements have primarily focused on improving the model structure and training data of MRMs, there has been limited exploration into the effectiveness of long-term reasoning capabilities for reward modeling and how to activate these capabilities in MRMs. In this paper, we explore how Reinforcement Learning (RL) can be used to improve reward modeling. Specifically, we reformulate the reward modeling problem as a rule-based RL task. However, we observe that directly applying existing RL algorithms, such as Reinforce++, to reward modeling often leads to training instability or even collapse due to the inherent limitations of these algorithms. To address this issue, we propose the StableReinforce algorithm, which refines the training loss, advantage estimation strategy, and reward design of existing RL methods. These refinements result in more stable training dynamics and superior performance. To facilitate MRM training, we collect 200K preference data from diverse datasets. Our reward model, R1-Reward, trained using the StableReinforce algorithm on this dataset, significantly improves performance on multimodal reward modeling benchmarks. Compared to previous SOTA models, R1-Reward achieves a $8.4\%$ improvement on the VL Reward-Bench and a $14.3\%$ improvement on the Multimodal Reward Bench. Moreover, with more inference compute, R1-Reward's performance is further enhanced, highlighting the potential of RL algorithms in optimizing MRMs.

Yuchen Zou, Xiao Hu, Dexing Zhong et al.

Monocular re-localization plays a crucial role in enabling intelligent agents to achieve human-like perception. However, traditional methods rely on dense maps, which face scalability limitations and privacy risks. OpenStreetMap (OSM), as a lightweight map that protects privacy, offers semantic and geometric information with global scalability. Nonetheless, there are still challenges in using OSM for localization: the inherent cross-modal discrepancies between natural images and OSM, as well as the high computational cost of global map-based localization. In this paper, we propose a hierarchical search framework with semantic alignment for localization in OSM. First, the semantic awareness capability of DINO-ViT is utilised to deconstruct visual elements to establish semantic relationships with OSM. Second, a coarse-to-fine search paradigm is designed to replace global dense matching, enabling efficient progressive refinement. Extensive experiments demonstrate that our method significantly improves both localization accuracy and speed. When trained on a single dataset, the 3° orientation recall of our method even outperforms the 5° recall of state-of-the-art methods.

Shengyi Huang, Quentin Gallouédec, Florian Felten et al.

In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curves are rarely available. As a result, it is usually necessary to reproduce the experiments from scratch, which can be time-consuming and error-prone. We present Open RL Benchmark, a set of fully tracked RL experiments, including not only the usual data such as episodic return, but also all algorithm-specific and system metrics. Open RL Benchmark is community-driven: anyone can download, use, and contribute to the data. At the time of writing, more than 25,000 runs have been tracked, for a cumulative duration of more than 8 years. Open RL Benchmark covers a wide range of RL libraries and reference implementations. Special care is taken to ensure that each experiment is precisely reproducible by providing not only the full parameters, but also the versions of the dependencies used to generate it. In addition, Open RL Benchmark comes with a command-line interface (CLI) for easy fetching and generating figures to present the results. In this document, we include two case studies to demonstrate the usefulness of Open RL Benchmark in practice. To the best of our knowledge, Open RL Benchmark is the first RL benchmark of its kind, and the authors hope that it will improve and facilitate the work of researchers in the field.

Kwai Keye Team, Biao Yang, Bin Wen et al.

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a strong emphasis on video, and an innovative training recipe. This recipe features a four-stage pre-training process for solid vision-language alignment, followed by a meticulous two-phase post-training process. The first post-training stage enhances foundational capabilities like instruction following, while the second phase focuses on stimulating advanced reasoning. In this second phase, a key innovation is our five-mode ``cold-start'' data mixture, which includes ``thinking'', ``non-thinking'', ``auto-think'', ``think with image'', and high-quality video data. This mixture teaches the model to decide when and how to reason. Subsequent reinforcement learning (RL) and alignment steps further enhance these reasoning capabilities and correct abnormal model behaviors, such as repetitive outputs. To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks (Figure 1). Furthermore, we develop and release the \textbf{KC-MMBench}, a new benchmark tailored for real-world short-video scenarios, where Keye-VL shows a significant advantage.

Jianxiong Li, Jinliang Zheng, Yinan Zheng et al. · tsinghua

Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3) capturing trajectory-level language grounding. Most existing methods approach these via separate objectives, which often reach sub-optimal solutions. In this paper, we propose a universal unified objective that can simultaneously extract meaningful task progression information from image sequences and seamlessly align them with language instructions. We discover that via implicit preferences, where a visual trajectory inherently aligns better with its corresponding language instruction than mismatched pairs, the popular Bradley-Terry model can transform into representation learning through proper reward reparameterizations. The resulted framework, DecisionNCE, mirrors an InfoNCE-style objective but is distinctively tailored for decision-making tasks, providing an embodied representation learning framework that elegantly extracts both local and global task progression features, with temporal consistency enforced through implicit time contrastive learning, while ensuring trajectory-level instruction grounding via multimodal joint encoding. Evaluation on both simulated and real robots demonstrates that DecisionNCE effectively facilitates diverse downstream policy learning tasks, offering a versatile solution for unified representation and reward learning. Project Page: https://2toinf.github.io/DecisionNCE/

Zhaoliang Chen, Cheng Ding, Saurabh Kataria et al.

This study introduces a novel application of a Generative Pre-trained Transformer (GPT) model tailored for photoplethysmography (PPG) signals, serving as a foundation model for various downstream tasks. Adapting the standard GPT architecture to suit the continuous characteristics of PPG signals, our approach demonstrates promising results. Our models are pre-trained on our extensive dataset that contains more than 200 million 30s PPG samples. We explored different supervised fine-tuning techniques to adapt our model to downstream tasks, resulting in performance comparable to or surpassing current state-of-the-art (SOTA) methods in tasks like atrial fibrillation detection. A standout feature of our GPT model is its inherent capability to perform generative tasks such as signal denoising effectively, without the need for further fine-tuning. This success is attributed to the generative nature of the GPT framework.

Xiao Hu, Xingyu Lu, Liyuan Mao et al.

Reinforcement learning (RL) has played an important role in improving the reasoning ability of large language models (LLMs). Some studies apply RL directly to \textit{smaller} base models (known as zero-RL) and also achieve notable progress. However, in this paper, we show that using only 920 examples, a simple distillation method based on the base model can clearly outperform zero-RL, which typically requires much more data and computational cost. By analyzing the token frequency in model outputs, we find that the distilled model shows more flexible reasoning. It uses anthropomorphic tokens and logical connectors much more often than the zero-RL model. Further analysis reveals that distillation enhances the presence of two advanced cognitive behaviors: Multi-Perspective Thinking or Attempting and Metacognitive Awareness. Frequent occurrences of these two advanced cognitive behaviors give rise to flexible reasoning, which is essential for solving complex reasoning problems, while zero-RL fails to significantly boost the frequency of these behaviors.

Biao Yang, Bin Wen, Boyang Ding et al.

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding strategy that dynamically allocates computational resources based on inter-frame similarity, processing key frames with significant visual changes at higher resolution (Slow pathway) while handling relatively static frames with increased temporal coverage at lower resolution (Fast pathway). Second, we implement a progressive four-stage pre-training methodology that systematically extends the model's context length from 8K to 128K tokens, enabling processing of longer videos and more complex visual content. Third, we develop a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment, incorporating a 5-step chain-of-thought data construction process, iterative GSPO-based reinforcement learning with progressive prompt hinting for difficult cases, and alignment training. Through extensive evaluation on public benchmarks and rigorous internal human assessment, Keye-VL-1.5 demonstrates significant improvements over existing models, particularly excelling in video understanding tasks while maintaining competitive performance on general multimodal benchmarks.

Kexin Li, Xiao Hu, Ilya Grishchenko et al.

The availability of high-quality, AI-generated audio raises security challenges such as misinformation campaigns and voice-cloning fraud. A key defense against the misuse of AI-generated audio is by watermarking it, so that it can be easily distinguished from genuine audio. As those seeking to misuse AI-generated audio may thus seek to remove audio watermarks, studying effective watermark removal techniques is critical to being able to objectively evaluate the robustness of audio watermarks against removal. Previous watermark removal schemes either assume impractical knowledge of the watermarks they are designed to remove or are computationally expensive, potentially generating a false sense of confidence in current watermark schemes. We introduce HarmonicAttack, an efficient audio watermark removal method that only requires the basic ability to generate the watermarks from the targeted scheme and nothing else. With this, we are able to train a general watermark removal model that is able to remove the watermarks generated by the targeted scheme from any watermarked audio sample. HarmonicAttack employs a dual-path convolutional autoencoder that operates in both temporal and frequency domains, along with GAN-style training, to separate the watermark from the original audio. When evaluated against state-of-the-art watermark schemes AudioSeal, WavMark, and Silentcipher, HarmonicAttack demonstrates greater watermark removal ability than previous watermark removal methods with near real-time performance. Moreover, while HarmonicAttack requires training, we find that it is able to transfer to out-of-distribution samples with minimal degradation in performance.

Yuzhang Xie, Hejie Cui, Ziyang Zhang et al.

Medical diagnosis prediction plays a critical role in disease detection and personalized healthcare. While machine learning (ML) models have been widely adopted for this task, their reliance on supervised training limits their ability to generalize to unseen cases, particularly given the high cost of acquiring large, labeled datasets. Large language models (LLMs) have shown promise in leveraging language abilities and biomedical knowledge for diagnosis prediction. However, they often suffer from hallucinations, lack structured medical reasoning, and produce useless outputs. To address these challenges, we propose KERAP, a knowledge graph (KG)-enhanced reasoning approach that improves LLM-based diagnosis prediction through a multi-agent architecture. Our framework consists of a linkage agent for attribute mapping, a retrieval agent for structured knowledge extraction, and a prediction agent that iteratively refines diagnosis predictions. Experimental results demonstrate that KERAP enhances diagnostic reliability efficiently, offering a scalable and interpretable solution for zero-shot medical diagnosis prediction.

Saurabh Kataria, Ran Xiao, Timothy Ruchti et al.

Non-invasive patient monitoring for tracking and predicting adverse acute health events is an emerging area of research. We pursue in-hospital cardiac arrest (IHCA) prediction using only single-channel finger photoplethysmography (PPG) signals. Our proposed two-stage model Feature Extractor-Aggregator Network (FEAN) leverages powerful representations from pre-trained PPG foundation models (PPG-GPT of size up to 1 Billion) stacked with sequential classification models. We propose two FEAN variants ("1H", "FH") which use the latest one-hour and (max) 24-hour history to make decisions respectively. Our study is the first to present IHCA prediction results in ICU patients using only unimodal (continuous PPG signal) waveform deep representations. With our best model, we obtain an average of 0.79 AUROC over 24~h prediction window before CA event onset with our model peaking performance at 0.82 one hour before CA. We also provide a comprehensive analysis of our model through architectural tuning and PaCMAP visualization of patient health trajectory in latent space.

Ni Mu, Hao Hu, Xiao Hu et al.

Preference-based reinforcement learning (PbRL) bypasses explicit reward engineering by inferring reward functions from human preference comparisons, enabling better alignment with human intentions. However, humans often struggle to label a clear preference between similar segments, reducing label efficiency and limiting PbRL's real-world applicability. To address this, we propose an offline PbRL method: Contrastive LeArning for ResolvIng Ambiguous Feedback (CLARIFY), which learns a trajectory embedding space that incorporates preference information, ensuring clearly distinguished segments are spaced apart, thus facilitating the selection of more unambiguous queries. Extensive experiments demonstrate that CLARIFY outperforms baselines in both non-ideal teachers and real human feedback settings. Our approach not only selects more distinguished queries but also learns meaningful trajectory embeddings.

Zeyuan Meng, Lovely Yeswanth Panchumarthi, Saurabh Kataria et al.

Acute Coronary Syndrome (ACS) is a life-threatening cardiovascular condition where early and accurate diagnosis is critical for effective treatment and improved patient outcomes. This study explores the use of ECG foundation models, specifically ST-MEM and ECG-FM, to enhance ACS risk assessment using prehospital ECG data collected in ambulances. Both models leverage self-supervised learning (SSL), with ST-MEM using a reconstruction-based approach and ECG-FM employing contrastive learning, capturing unique spatial and temporal ECG features. We evaluate the performance of these models individually and through a fusion approach, where their embeddings are combined for enhanced prediction. Results demonstrate that both foundation models outperform a baseline ResNet-50 model, with the fusion-based approach achieving the highest performance (AUROC: 0.843 +/- 0.006, AUCPR: 0.674 +/- 0.012). These findings highlight the potential of ECG foundation models for early ACS detection and motivate further exploration of advanced fusion strategies to maximize complementary feature utilization.

Xiao Hu, Tianshu Wang, Min Gong et al.

Guidance commands of flight vehicles are a series of data sets with fixed time intervals, thus guidance design constitutes a sequential decision problem and satisfies the basic conditions for using deep reinforcement learning (DRL). In this paper, we consider the scenario where the escape flight vehicle (EFV) generates guidance commands based on DRL and the pursuit flight vehicle (PFV) generates guidance commands based on the proportional navigation method. For the EFV, the objective of the guidance design entails progressively maximizing the residual velocity, subject to the constraint imposed by the given evasion distance. Thus an irregular dynamic max-min problem of extremely large-scale is formulated, where the time instant when the optimal solution can be attained is uncertain and the optimum solution depends on all the intermediate guidance commands generated before. For solving this problem, a two-step strategy is conceived. In the first step, we use the proximal policy optimization (PPO) algorithm to generate the guidance commands of the EFV. The results obtained by PPO in the global search space are coarse, despite the fact that the reward function, the neural network parameters and the learning rate are designed elaborately. Therefore, in the second step, we propose to invoke the evolution strategy (ES) based algorithm, which uses the result of PPO as the initial value, to further improve the quality of the solution by searching in the local space. Simulation results demonstrate that the proposed guidance design method based on the PPO algorithm is capable of achieving a residual velocity of 67.24 m/s, higher than the residual velocities achieved by the benchmark soft actor-critic and deep deterministic policy gradient algorithms. Furthermore, the proposed ES-enhanced PPO algorithm outperforms the PPO algorithm by 2.7\%, achieving a residual velocity of 69.04 m/s.

Runze Yan, Cheng Ding, Ran Xiao et al.

Atrial fibrillation (AF), a common cardiac arrhythmia, significantly increases the risk of stroke, heart disease, and mortality. Photoplethysmography (PPG) offers a promising solution for continuous AF monitoring, due to its cost efficiency and integration into wearable devices. Nonetheless, PPG signals are susceptible to corruption from motion artifacts and other factors often encountered in ambulatory settings. Conventional approaches typically discard corrupted segments or attempt to reconstruct original signals, allowing for the use of standard machine learning techniques. However, this reduces dataset size and introduces biases, compromising prediction accuracy and the effectiveness of continuous monitoring. We propose a novel deep learning model, Signal Quality Weighted Fusion of Attentional Convolution and Recurrent Neural Network (SQUWA), designed to learn how to retain accurate predictions from partially corrupted PPG. Specifically, SQUWA innovatively integrates an attention mechanism that directly considers signal quality during the learning process, dynamically adjusting the weights of time series segments based on their quality. This approach enhances the influence of higher-quality segments while reducing that of lower-quality ones, effectively utilizing partially corrupted segments. This approach represents a departure from the conventional methods that exclude such segments, enabling the utilization of a broader range of data, which has great implications for less disruption when monitoring of AF risks and more accurate estimation of AF burdens. Our extensive experiments show that SQUWA outperform existing PPG-based models, achieving the highest AUCPR of 0.89 with label noise mitigation. This also exceeds the 0.86 AUCPR of models trained with using both electrocardiogram (ECG) and PPG data.

Yuhao Xu, Xiaoda Wang, Yi Wu et al.

Electrocardiography (ECG) analysis is crucial for cardiac diagnosis, yet existing foundation models often fail to capture the periodicity and diverse features required for varied clinical tasks. We propose ECG-MoE, a hybrid architecture that integrates multi-model temporal features with a cardiac period-aware expert module. Our approach uses a dual-path Mixture-of-Experts to separately model beat-level morphology and rhythm, combined with a hierarchical fusion network using LoRA for efficient inference. Evaluated on five public clinical tasks, ECG-MoE achieves state-of-the-art performance with 40% faster inference than multi-task baselines.