Proceedings of machine learning research最新文献

{"title":"Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space.","authors":"Giosue Migliorini, Padhraic Smyth","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Systems of interacting continuous-time Markov chains are a powerful model class, but inference is typically intractable in high-dimensional settings. Auxiliary information, such as noisy observations, is typically only available at discrete times, and incorporating it via a Doob's <math><mi>h</mi></math> -transform gives rise to an intractable posterior process that requires approximation. We introduce Latent Interacting Particle Systems, a model class parameterizing the generator of each Markov chain in the system. Our inference method involves estimating look-ahead functions (twist potentials) that anticipate future information, for which we introduce an efficient parameterization. We incorporate this approximation in a twisted Sequential Monte Carlo sampling scheme. We demonstrate the effectiveness of our approach on a challenging posterior inference task for a latent SIRS model on a graph, and on a neural model for wildfire spread dynamics trained on real data.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"300 ","pages":"3484-3492"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580705/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AdaFuse: Adaptive Multimodal Fusion for Lung Cancer Risk Prediction via Reinforcement Learning.","authors":"Chongyu Qu, Zhengyi Lu, Yuxiang Lai, Thomas Z Li, Junchao Zhu, Junlin Guo, Juming Xiong, Yanfan Zhu, Yuechen Yang, Allen J Luna, Kim L Sandler, Bennett A Landman, Yuankai Huo","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Multimodal fusion has emerged as a promising paradigm for disease diagnosis and prognosis, integrating complementary information from heterogeneous data sources such as medical images, clinical records, and radiology reports. However, existing fusion methods process all available modalities through the network, either treating them equally or learning to assign different contribution weights, leaving a fundamental question unaddressed: <b>for a given patient, should certain modalities be used at all?</b> We present AdaFuse, an adaptive multimodal fusion framework that leverages reinforcement learning (RL) to learn patient-specific modality selection and fusion strategies for lung cancer risk prediction. AdaFuse formulates multimodal fusion as a sequential decision process, where the policy network iteratively decides whether to incorporate an additional modality or proceed to prediction based on the information already acquired. This sequential formulation enables the model to condition each selection on previously observed modalities and terminate early when sufficient information is available, rather than committing to a fixed subset upfront. We evaluate AdaFuse on the National Lung Screening Trial (NLST) dataset. Experimental results demonstrate that AdaFuse achieves the highest AUC (0.762) compared to the best single-modality baseline (0.732), the best fixed fusion strategy (0.759), and adaptive baselines including DynMM (0.754) and MoE (0.742), while using fewer FLOPs than all triple-modality methods. Our work demonstrates the potential of reinforcement learning for personalized multimodal fusion in medical imaging, representing a shift from uniform fusion strategies toward adaptive diagnostic pipelines that learn when to consult additional modalities and when existing information suffices for accurate prediction. Code is publicly available at: https://github.com/hrlblab/adafuse.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"315 ","pages":"2582-2601"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13597164/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149027060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation.","authors":"Wanrong Zheng, Yunhao Ge, Laurent Itti","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Breakthrough progress in vision-based navigation through unknown environments has been achieved by using multimodal large language models (MLLMs). These models can plan a sequence of motions by evaluating the current view at each time step against the task and goal given to the agent. However, current zero-shot Vision-and-Language Navigation (VLN) agents powered by MLLMs still tend to drift off course, halt prematurely, and achieve low overall success rates. We propose Three-Step Nav to counteract these failures with a three-view protocol: First, \"look forward\" to extract global landmarks and sketch a coarse plan. Then, \"look now\" to align the current visual observation with the next sub-goal for fine-grained guidance. Finally, \"look backward\" audits the entire trajectory to correct accumulated drift before stopping. Requiring no gradient updates or task-specific fine-tuning, our planner drops into existing VLN pipelines with minimal overhead. Three-Step Nav achieves state-of-the-art zero-shot performance on the R2R-CE and RxR-CE dataset. Our code is available at https://github.com/ZoeyZheng0/3-step-Nav.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"300 ","pages":"4645-4653"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580651/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Catastrophic Failure of the <i>k</i>-Means Algorithm in High Dimensions, and How Hartigan's Algorithm Avoids It.","authors":"Roy R Lederman, David Silva-Sánchez, Ziling Chen, Gilles Mordant, Amnon Balanov, Tamir Bendory","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Lloyd's <math><mi>k</mi></math> -means algorithm is one of the most widely used clustering methods. We prove that in high-dimensional, high-noise settings, the algorithm exhibits catastrophic failure: with high probability, essentially every partition of the data is a fixed point. Consequently, Lloyd's algorithm simply returns its initial partition - even when the underlying clusters are trivially recoverable by other methods. In contrast, we prove that Hartigan's <math><mi>k</mi></math> -means algorithm does not exhibit this pathology. Our results show the stark difference between these algorithms and offer a theoretical explanation for the empirical difficulties often observed with <math><mi>k</mi></math> -means in high dimensions.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"306 ","pages":"63264-63305"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13626411/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GenUnfold: Rapidly Predict Protein Mechanical Unfolding Trajectory via a Physics-Guided Diffusion Model.","authors":"Yiyuan Zhang, Cailong Hua, Vinitendra Singh, Joseph M Muretta, James M Ervasti, Murti V Salapaka","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Many fundamental biological processes are governed by mechanical forces, with proteins acting as the key molecular mediators. Elucidating how protein unfolding responds to force is critical for understanding the mechano-pathologies, such as cardiomyopathy and muscular dystrophy. While the unfolding trajectories measured by Single-Molecule Force Spectroscopy (SMFS) map the instantaneous force response against molecular extension, its broader application is limited by time-consuming data collection and high operational costs. Here, we present the first scalable generative diffusion framework for full unfolding trajectory prediction, which integrates protein encoders for multi-scale conditioning. Beyond establishing the field's first systematic benchmark using existing models, we propose GenUnfold, a novel physics-guided diffusion model that combines global coevolutionary context with a local mechanical representation of the protein. The representation is derived from a novel physics-biased attention mechanism, which steers the generative diffusion process by modeling dynamic residue dependencies as a function of both structural topology and interaction stiffness. The benchmark for this task is built upon the biomolecule stretching database and several representative baseline models. Empirical results demonstrate that GenUnfold achieves state-of-the-art performance, reducing distributional error (FID) by 30% and 54% compared to pretrained Evolutionary Scale Model (ESM)-2 and standard transformer, respectively. Beyond statistical curve similarity, GenUnfold demonstrates superior physical consistency; in downstream mechanical property prediction, it reduces prediction errors for unfolding force and energy distributions by 6% and 36% over the ESM-2 baseline. These results indicate that while existing generative AI approaches can alleviate the need for predicting representative force curves, GenUnfold further improves performance by leveraging the synergy between protein structure and evolutionary information. By enabling proteome-wide screening to identify mechanical candidates before costly physical validation, our approach is promising to accelerate the discovery of force-targeted therapeutics.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"306 ","pages":"155857-155873"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13626394/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing.","authors":"Zarif Ikram, Arad Firouzkouhi, Stephen Tu, Mahdi Soltanolkotabi, Paria Rashidinejad","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>A central challenge in large language model (LLM) editing is capability preservation: methods that successfully change targeted behavior can quietly game the editing proxy and corrupt general capabilities, producing degenerate behaviors reminiscent of proxy/reward hacking. We present CrispEdit, a scalable and principled second-order editing algorithm that treats capability preservation as an explicit constraint, unifying and generalizing several existing editing approaches. CrispEdit formulates editing as constrained optimization and enforces the constraint by projecting edit updates onto the low-curvature subspace of the capability-loss landscape. At the crux of CrispEdit is expressing capability constraint via <i>Bregman divergence</i>, whose quadratic form yields the Gauss-Newton Hessian exactly and even when the base model is not trained to convergence. We make this second-order procedure efficient at the LLM scale using Kronecker-factored approximate curvature (K-FAC) and a novel <i>matrix-free projector</i> that exploits Kronecker structure to avoid constructing massive projection matrices. Across standard model-editing benchmarks, CrispEdit achieves high edit success while <b>keeping capability degradation below 1%</b> on average across datasets, significantly improving over prior editors.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"306 ","pages":"49502-49525"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13626427/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation.","authors":"Ruchi Sandilya, Sumaira Perez, Charles Lynch, Lindsay Victoria, Benjamin Zebley, Derrick Matthew Buchanan, Mahendra T Bhati, Nolan Williams, Timothy J Spellman, Faith M Gunning, Conor Liston, Logan Grosenick","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control. We introduce ConDA (Contrastive Diffusion Alignment), a plug-and-play geometry layer that applies contrastive learning to pretrained diffusion latents using auxiliary variables (e.g., time, stimulation parameters, facial action units). ConDA learns a low-dimensional embedding whose directions align with underlying dynamical factors, consistent with recent contrastive learning results on structured and disentangled representations. In this embedding, simple nonlinear trajectories support smooth interpolation, extrapolation, and counterfactual editing while rendering remains in the original diffusion space. ConDA separates editing and rendering by lifting embedding trajectories back to diffusion latents with a neighborhood-preserving kNN decoder and is robust across inversion solvers. Across fluid dynamics, neural calcium imaging, therapeutic neurostimulation, facial expression dynamics, and monkey motor cortex activity, ConDA yields more interpretable and controllable latent structure than linear traversals and conditioning-based baselines, indicating that diffusion latents encode dynamics-relevant structure that can be exploited by an explicit contrastive geometry layer.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"306 ","pages":"107499-107525"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13626448/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression.","authors":"Katie Matton, Purvaja Balaji, Hamzeh Ghasemzadeh, Jameson C Cooper, Daryush D Mehta, Jarrad H Van Stan, Robert E Hillman, Rosalind Picard, John Guttag, S Mazdak Abulnaga","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Phonotrauma refers to vocal fold tissue damage resulting from exposure to forces during voicing. It occurs on a continuum from mild to severe, and treatment options can vary based on severity. Assessment of severity involves a clinician's expert judgment, which is costly and can vary widely in reliability. In this work, we present the first method for automatically classifying phonotrauma severity from vocal fold images. To account for the ordinal nature of the labels, we adopt a widely used ordinal regression framework. To account for label uncertainty, we propose a novel modification to ordinal regression loss functions that enables them to operate on soft labels reflecting annotator rating distributions. Our proposed soft ordinal regression method achieves predictive performance approaching that of clinical experts, while producing well-calibrated uncertainty estimates. By providing an automated tool for phonotrauma severity assessment, our work can enable large-scale studies of phonotrauma, ultimately leading to improved clinical understanding and patient care.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"297 ","pages":"1360-1375"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13268597/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148267296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Paired Recipient-based Evaluation of Survival Prediction for Deceased Donor Kidney Transplants.","authors":"Misaki Matsuura, Mohammadreza Nemati, Dulat Bekbolsynov, Stanislaw Stepkowski, Kevin S Xu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>There has been significant interest in using machine learning algorithms to predict kidney transplant outcomes, such as the number of years until a graft inevitably fails. These prediction algorithms could possibly be used for pre-transplant donor-recipient matching to identify more compatible donors and recipients and thus improve post-transplant outcomes. In this study, we explore the use of survival prediction models trained on deceased donor kidney transplant data from the Scientific Registry of Transplant Recipients (SRTR). We propose a novel paired recipient-based evaluation framework that compares graft outcomes between two recipients who received kidneys from the same deceased donor, allowing us to evaluate the <i>counterfactual benefit</i> of changing the recipient for a certain donor. We find that five different survival prediction models, ranging in complexity from linear to deep learning-based models, all result in ~60% paired recipient-based accuracy. We further translate this accuracy into an interpretable quantity of post-transplant years gained. We also highlight major limitations of the commonly used concordance index (C-index) metric for evaluating survival prediction accuracy in this setting and demonstrate that our proposed paired recipient-based accuracy metric is more clinically relevant and better reflects real-world allocation settings.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"340 ","pages":"1300-1320"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637472/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging Foundation Models for Histological Grading in Cutaneous Squamous Cell Carcinoma using PathFMTools.","authors":"Abdul Rahman Diab, Emily E Karn, Renchin Wu, Emily S Ruiz, William Lotter","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Despite the promise of computational pathology foundation models, adapting them to specific clinical tasks remains challenging due to the complexity of whole-slide image (WSI) processing, the opacity of learned features, and the wide range of potential adaptation strategies. To address these challenges, we introduce <b>PathFMTools</b>, a lightweight, extensible Python package that enables efficient execution, analysis, and visualization of pathology foundation models. We use this tool to interface with and evaluate two state-of-the-art vision-language foundation models, CONCH and MUSK, on the task of histological grading in cutaneous squamous cell carcinoma (cSCC), a critical criterion that informs cSCC staging and patient management. Using a cohort of 440 cSCC H&E WSIs, we benchmark multiple adaptation strategies, demonstrating tradeoffs across prediction approaches and validating the potential of using foundation model embeddings to train small specialist models. These findings underscore the promise of pathology foundation models for real-world clinical applications, with <b>PathFMTools</b> enabling efficient analysis and validation.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"297 ","pages":"936-951"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13197084/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148019201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}