The impressive performance of large language models (LLMs) arises from their massive scale and heterogeneous module composition. However, this structural heterogeneity poses significant optimization challenges. While adaptive optimizers such as Adam(W) provide per-parameter adaptivity, they do not explicitly account for module-level gradient heterogeneity, often resulting in slower convergence, suboptimal performance, or occasional training instability. Existing approaches typically rely on manually tuned module-specific learning rates or specific optimization strategies, which are computationally costly and difficult to generalize across tasks or models. To establish a more principled approach, we first analyze the noise-damping behavior of Adam in high-noise modules and introduce \textbf{Module-wise Learning Rate Scaling via SNR (MoLS)}. MoLS estimates module-level SNRs to scale Adam updates, allowing automated module-wise learning rate allocation without manual tuning. Empirical results across multiple LLM training benchmarks demonstrate that MoLS improves convergence speed and generalization, achieving performance comparable to carefully tuned module-specific learning rates, while remaining compatible with memory-efficient training algorithms.
论文检索
输入标题、作者或关键词，从 4,255 篇学术成果中精准定位
Stochastic gradient methods are central to large-scale learning, yet their generalization theory typically relies on independent sampling assumptions. In many practical applications, data are generated by Markov chains and learning is performed in a decentralized manner, which introduces significant analytical challenges. In this work, we investigate the stability and generalization of decentralized stochastic gradient descent (SGD) and stochastic gradient descent ascent (SGDA) under Markov chain sampling. Leveraging a stability-based framework, we characterize how Markovian dependence and decentralized communication jointly influence generalization behavior. Our analysis captures the effects of network topology, Markov chain mixing properties, and primal–dual dynamics. We establish non-asymptotic generalization bounds for both algorithms, extending existing results on Markov stochastic gradient methods to decentralized and minimax settings.
Federated Learning (FL) faces two major challenges when deploying large vision-language models such as contrastive language-image pretraining (CLIP) model, namely high computation/communication overhead and performance degradation due to data heterogeneity. To address these, we propose FedENC, a novel federated adaptive CLIP framework. FedENC keeps the CLIP encoder frozen and introduces a lightweight communicable global expert adaptation module for learning general knowledge across clients and two local experts for client-specific adaptation to reduce computation and communication overhead. To mitigate data heterogeneity, we introduce neural collapse (NC) alignment to encourage the model to learn unified and balanced image feature representations. To enrich the performance, we propose a cosine and Kullback–Leibler (KL) divergence based alignment function to improve the prediction consistency between the global and local experts. Finally, we ensemble their outputs for robust inference. Extensive experiments on six datasets (4 natural + 2 medical) in challenging settings (e.g., domain shift) show that FedENC improves the test accuracy (e.g., by +5.37% on DomainNet compared to LoRA) with reasonable communication load (e.g., 15.2x lower than LoRA, with 3.3GB GPU memory usage). The code is available at https://github.com/AIPMLab/FedENC.
Training with instance-dependent label noise poses a critical challenge in deep learning, severely impeding model generalization. Existing methods often struggle to break the vicious cycle where corrupted labels degrade feature representations, which in turn impairs noise identification. To overcome this, we propose the Meta-Cognitive Resonance Label Correction (MecReC) framework. For feature representation, MecReC structurally decouples representation learning from label correction, leveraging a pre-trained model as a frozen anchor to ensure feature robustness. For label correction, we introduce a novel meta-cognitive resonance mechanism that aggregates multiple complementary signals to comprehensively assess label reliability. These collaborative signals are fed to a lightweight meta-weight network, which automatically learns whether and how to correct each label. Furthermore, our personalized confidence thresholding strategy guarantees a tighter error bound for label purification. Extensive experiments demonstrate that MecReC consistently outperforms SOTA methods, exhibiting superior robustness particularly under extreme noise conditions. Code and additional details are available at https://github.com/JieSu272/MecReC.
Test-time scaling (TTS) has demonstrated remarkable potential in enhancing the reasoning capabilities of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs). However, its application has primarily been limited to domains such as mathematics and programming, owing to their reasoning-intensive nature and the ease of result verification. Its utility in other knowledge-intensive fields, such as medicine and general scientific research, remains underexplored. To bridge this gap and unlock the potential of TTS in broader domains, we propose Cross-Domain TTS, a novel framework that enables task-tailored scaling. This framework consists of two key components: a conformal prediction-based cold-start strategy and an information-gain-based dynamic reasoning adjustment. The CP-based cold-start strategy guides the model's initialization during test-time scaling based on conformal prediction theory, while the information-gain-based dynamic reasoning adjustment guides the model's reasoning progress through a progress vector according to the information gain of reasoning steps. We conducted experiments using LLMs and LVLMs on cross-domain benchmarks. Our results demonstrate that the proposed framework consistently improves performance across various domain-specific datasets. For instance, in the medical domain, it achieves an improvement of up to 17% in pass@1 accuracy while reducing inference latency and saving up to 30% in token consumption. Code is available at https://github.com/Yan0613/Cross-Domain-TTS.
Gradient boosting remains a strong and widely used method for tabular data learning, but its performance often degrades when training labels are noisy. This behavior is largely related to the way boosting algorithms emphasize samples with large gradients, without explicitly accounting for whether such errors originate from informative hard cases or from unreliable labels. We address this issue by reconsidering how sample reliability is evaluated during boosting. Instead of relying on instantaneous error, we examine the evolution of each sample’s residuals across iterations. Based on this insight, we propose Information-Theoretic Trust Boosting (ITBoost), which uses the Minimum Description Length principle to measure the complexity of residual trajectories. Samples whose residual patterns fluctuate in an irregular manner are treated as less trustworthy and are down-weighted during learning. Theoretically, we derive a tighter generalization bound for ITBoost under label noise. Empirical results on various tabular benchmarks indicate that ITBoost provides improved robustness in noisy environments over leading boosting and deep tabular models, while retaining best average performance on clean data.
4D Gaussian Splatting (4DGS) enables high-quality, real-time rendering of dynamic scenes and is becoming a popular format for sharing 4D assets. This trend calls for robust copyright watermarking that can be verified from rendered videos without access to the original scene or model parameters. However, watermarking 4DGS is challenging: verification relies on short multi-view clips whose frames vary with motion, viewpoint changes, and post-processing. More importantly, decoding from rendered frames is easily dominated by scene content (objects, textures, illumination) rather than subtle watermark traces, leading to unstable evidence across frames and poor generalization across scenes. We propose Guard4D, a decoupled watermarking framework for 4DGS. Guard4D pre-trains a general-purpose message decoder under text supervision and embeds a binary message by optimizing compact spherical-harmonic offsets while keeping geometry and opacity fixed. To improve extraction from short clips and suppress semantic interference, we introduce a temporal modeling and semantic decoupling (TMSD) module that temporally aggregates watermark information and uses clean and noise-perturbed control clips generated from the non-watermarked model to reduce the influence of semantics on watermark decoding. Extensive experiments on dynamic 4DGS scenes demonstrate the effectiveness of Guard4D. Code is available at https://github.com/shisyy/Guard4D.
Contrastive learning has become a dominant paradigm for learning time series representations from large-scale unlabeled data. However, current methods are often adapted from computer vision and rely on random time-domain augmentations (e.g., jittering and cropping). Such augmentations can unpredictably disrupt the natural frequency structure of signals, leading to representations failing to capture crucial patterns in the data. To address this, we propose a framework of Frequency-Aware Augmentation and Alignment for Time Series Contrastive Learning (FACL), which comprises two key innovations. First, FACL employs a novel frequency-structured augmentation mechanism based on wavelet transforms. The mechanism constructs controlled and interpretable contrastive views by the structured attenuation and recombination of specific wavelet components. Second, FACL introduces a multi-level contrastive objective that incorporates a subspace alignment strategy. This objective explicitly aligns representations within their corresponding frequency subspaces. Experiments across six forecasting and four classification benchmarks show that FACL achieves superior performance compared to recent baselines. Ablation studies and model analysis highlight the contribution of each component in FACL. Furthermore, low-sample semi-supervised learning experiments confirm the robustness and generalization of FACL.
Machine Learning Models Assisting the Development of Antibody Therapeutics and Vaccines – an Emerging Trend
PDF ↗The development of novel effective medical treatments is one of the most important and expected beneficial effects of the AI revolution. This decade is witnessing the rise of AI models able to predict complex properties for protein-protein interactions that hold great promise in assisting in the development of antibody therapeutics and vaccines, including for diseases that long eluded us in the pursuit of an effective treatment. This paper introduces this area of research in a language accessible to an AI researcher, exploring the biological problems that can be solved by AI models, as well as the general context to make solutions feasible in practical scenarios. We survey the main current trends and works in this research area and point towards current still unsolved challenges and trade offs. We expect this paper will be extremely helpful for AI researchers trying to join the field, as well as for researchers already working in one of the subtopics that wish to have a better understanding of the general context around it.
Digital Scale: Open-Source On-Device BMI Estimation from Smartphone Camera Images Trained on a Large-Scale Real-World Dataset
PDF ↗Estimating Body Mass Index (BMI) from camera images with machine learning models enables rapid weight assessment when traditional methods are unavailable or impractical, such as in telehealth or emergency scenarios. Existing computer vision approaches have been limited to datasets of up to 14,500 images. In this study, we present a deep learning-based BMI estimation method trained on our WayBED dataset, a large proprietary collection of 84,963 smartphone images from 25,353 individuals. We introduce an automatic filtering method that uses posture clustering and person detection to curate the dataset by removing low-quality images, such as those with atypical postures or incomplete views. This process retained 71,322 high-quality images suitable for training. We achieve a Mean Absolute Percentage Error (MAPE) of 7.9% on our hold-out test set (WayBED data) using full-body images, the lowest value in the published literature to the best of our knowledge. Further, we achieve a MAPE of 13% on the completely unseen (during training) VisualBodyToBMI dataset, comparable with state-of-the-art approaches trained on it, demonstrating robust generalization. Lastly, we fine-tune our model on VisualBodyToBMI and achieve a MAPE of 8.56%, the lowest reported value on this dataset so far. We deploy the full pipeline, including image filtering and BMI estimation, on Android devices using the CLAID framework. We release our complete code for model training, filtering, and the CLAID package for mobile deployment as open-source contributions.
We propose a new theoretical foundation for artificial intelligence (AI) and machine learning (ML), building on ideas in pure mathematics relating to categories and functors. This paper builds on our AAAI 2025 tutorial Thinking with Functors: Category Theory for A(G)I, which provides background material. In addition, our recent papers on intuitionistic j-do calculus in Topos Causal Models} and GAIA: Categorical Foundations of Generative AI, illustrate how to generalize well-known formalisms in AI, such as causal inference and deep learning, to a category-theoretic setting.
Machine learning models are often used to make predictions about the outcomes of applications to selective programs. Many prospective school or college applicants turn to machine learning models to predict whether they will be admitted to a program, and employers may use algorithmic tools to filter out resumes predicted to have a low probability of being hired when offering interviews for a job opening. However, such decision processes differ substantially from the conventional machine learning setting: decisions are not independent across applicants. Whether a student is admitted depends on the other applicants who apply because admissions decisions are capacity-constrained. We formalize how the nature of admission decisions results in a data-generating process which is incompatible with traditional machine learning assumptions. We characterize how selection functions properties affect the difficulty of generalization to applicant pool distribution shifts, introducing two concepts: stability, which measures how many existing decisions can change when a single new applicant is introduced; and variability, which measures the number of unique students whose decisions can change. We demonstrate our theory on admissions data from the New York City high school matching system, showing that machine learning performance degrades as the applicant pool increasingly differs from the training data. Furthermore, there are larger performance drops for schools using decision rules that are less stable and more variable. Our work raises questions about the reliability of predicting individual admissions probabilities.
In applications across agriculture, ecology, and human development, machine learning with satellite imagery (SatML) is limited by the sparsity of labeled training data. While satellite data cover the globe, labeled training datasets for SatML are often small, spatially clustered, and collected for other purposes (e.g., administrative surveys or field measurements). Despite the pervasiveness of this issue in practice, past SatML research has largely focused on new model architectures and training algorithms to handle scarce training data, rather than modeling data conditions directly. This leaves scientists and policymakers who wish to use SatML for large-scale monitoring uncertain about whether and how to collect additional data to maximize performance. Here, we present the first problem formulation for the optimization of spatial training data in the presence of heterogeneous data collection costs and realistic budget constraints, as well as novel methods for addressing this problem. In experiments simulating different problem settings across three continents and four tasks, our strategies reveal substantial gains from sample optimization. Further experiments delineate settings for which optimized sampling is particularly effective. The problem formulation and methods we introduce are designed to generalize across application domains for SatML; we put special emphasis on a specific problem setting where our coauthors can immediately use our findings to augment clustered agricultural surveys for SatML monitoring in Togo.
Stochastic Decentralized Optimization of Non-Smooth Convex and Convex-Concave Problems over Time-Varying Networks
PDF ↗We study non-smooth stochastic decentralized optimization problems over time-varying networks, where objective functions are distributed across nodes and network connections may intermittently appear or break. Specifically, we consider two settings: (i) stochastic non-smooth (strongly) convex optimization, and (ii) stochastic non-smooth (strongly) convex–(strongly) concave saddle point optimization. Convex problems of this type commonly arise in deep neural network training, while saddle point problems are central to machine learning tasks such as the training of generative adversarial networks (GANs). Prior works have primarily focused on the smooth setting, or time-invariant network scenarios. We extend the existing theory to the more general non-smooth and stochastic setting over time-varying networks and saddle point problems. Our analysis establishes upper bounds on both the number of stochastic oracle calls and communication rounds, matching lower bounds for both convex and saddle point optimization problems.
Machine learning methods have been increasingly applied to solve Vehicle Routing Problems (VRPs). A high-efficiency approach is to learn solution construction using deep neural networks. However, their tendency toward premature convergence is a critical barrier, severely hindering generalization across diverse distributions and scales. To overcome this, we introduce Elite-Pattern Reinforcement (EPR), a novel strategy designed to create a synergy between the diverse, exploratory nature of reinforcement learning and the high-quality, structured knowledge from classical heuristics. The strategy guides the learning process by reinforcing structural patterns from elite solutions, employing an elite-guided score modulation to integrate this external knowledge. The inherent symmetry of path patterns is also exploited to augment the structural information. This steers the policy away from premature convergence by enabling it to distinguish and favour elite path patterns over inferior ones. Integrating our strategy with four construction methods yields substantial performance improvements on the CVRPLIB and TSPLIB benchmarks. Furthermore, our approach outperforms state-of-the-art learning-based methods, demonstrating superior generalization across diverse distributions and scales.
Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. Like human programmers, LLMs tend to call high-level APIs and libraries to program efficiently. However, this shortcut may hinder LLMs from learning the essential algorithm reasoning, leading instead to rote memorization of API usage. As a result, LLMs often struggle to generalize to new or domain-specific algorithms that lack ready-made library support. In this work, we propose ARBench, a novel benchmark for evaluating LLMs’ ability to generate machine learning algorithms from scratch, beyond merely invoking high-level APIs. It emphasizes algorithmic reasoning and implementation, distinguishing genuine understanding from superficial API usage. It covers fundamental and advanced machine learning tasks, rigorously assessing current LLMs’ capacity to implement these algorithms from scratch. Our evaluation reveals the strengths and weaknesses of state-of-the-art LLMs in algorithmic reasoning and generalization, offering valuable insights to guide future research and development.
Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation
PDF ↗Multi-domain machine translation (MDMT) aims to build a unified model capable of translating content across diverse domains. Despite the impressive machine translation capabilities demonstrated by large language models (LLMs), domain adaptation still remains a challenge for LLMs. Existing MDMT methods such as in-context learning and parameter-efficient fine-tuning often suffer from domain shift, parameter interference and limited generalization. In this work, we propose a neuron-efficient fine-tuning framework for MDMT that identifies and updates consensus-aligned neurons within LLMs. These neurons are selected by maximizing the mutual information between neuron behavior and domain features, enabling LLMs to capture both generalizable translation patterns and domain-specific nuances. Our method then fine-tunes LLMs guided by these neurons, effectively mitigating parameter interference and domain-specific overfitting. Comprehensive experiments on three LLMs across ten German-English and Chinese-English translation domains evidence that our method consistently outperforms strong PEFT baselines on both seen and unseen domains, achieving state-of-the-art performance.
The success of modern machine learning hinges on access to high-quality training data. In many real-world scenarios, such as acquiring data from public repositories or sharing across institutions, data is naturally organized into discrete datasets that vary in relevance, quality, and utility. Selecting which repositories or institutions to search for useful datasets, and which datasets to incorporate into model training are therefore critical decisions, yet most existing methods select individual samples and treat all data as equally relevant, ignoring differences between datasets and their sources. In this work, we formalize the task of dataset selection: selecting entire datasets from a large, heterogeneous pool to improve downstream performance under resource constraints. We propose Dataset Selection via Hierarchies (DaSH), a dataset selection method that models utility at both dataset and group (e.g., collections, institutions) levels, enabling efficient generalization from limited observations. Across two public benchmarks (Digit-Five and DomainNet), DaSH outperforms state-of-the-art data selection baselines by up to 26.2% in accuracy, while requiring significantly fewer exploration steps. Ablations show DaSH is robust to low-resource settings and lack of relevant datasets, making it suitable for scalable and adaptive dataset selection in practical multi-source learning workflows.
Fairness concerns are increasingly critical as machine learning models are deployed in high-stakes applications. While existing fairness-aware methods typically intervene at the model level, they often suffer from high computational costs, limited scalability, and poor generalization. To address these challenges, we propose a Bayesian data selection framework that ensures fairness by aligning group-specific posterior distributions of model parameters and sample weights with a shared central distribution. Our framework supports flexible alignment via various distributional discrepancy measures, including Wasserstein distance, maximum mean discrepancy, and f-divergence, allowing geometry-aware control without imposing explicit fairness constraints. This data-centric approach mitigates group-specific biases in training data and improves fairness in downstream tasks, with theoretical guarantees. Experiments on benchmark datasets show that our method consistently outperforms existing data selection and model-based fairness methods in both fairness and accuracy.
Label Distribution Learning (LDL) is an effective machine learning paradigm for addressing label ambiguity, where each sample is annotated with a distribution that conveys rich semantic information. However, during the actual annotation process of label distributions, annotators often exhibit divergent labeling preferences for the same sample. Most existing LDL methods overlook this heterogeneity, assuming that the observed label distribution originates from a single labeling pattern. Such an assumption limits their capacity to manage inter-annotator disagreement and constrains the generalization of the resulting models. To address this issue, we propose, for the first time, a Dirichlet process mixture model (DPMM)-based framework for LDL. This framework leverages nonparametric Bayesian methods to adaptively uncover diverse latent labeling patterns from the data and to accurately model annotator heterogeneity. Specifically, the ground-truth label distribution of each sample is modeled as a weighted mixture of multiple latent components, where a feature-conditioned gating mechanism adaptively controls the contribution of each component. Experimental results demonstrate that the proposed model consistently achieves competitive performance on several widely-used benchmark datasets.