Heuristic design with large language models (LLMs) has emerged as a promising approach for tackling combinatorial optimization problems (COPs). However, existing approaches often rely on manually predefined evolutionary computation (EC) optimizers and single-task training schemes, which may constrain the exploration of diverse heuristic algorithms and hinder the generalization of the resulting heuristics. To address these issues, we propose Meta-Optimization of Heuristics (MoH), a novel framework that operates at the optimizer level, discovering effective optimizers through the principle of meta-learning. Specifically, MoH leverages LLMs to iteratively refine a meta-optimizer that autonomously constructs diverse optimizers through (self-)invocation, thereby eliminating the reliance on a predefined EC optimizer. These constructed optimizers subsequently evolve heuristics for downstream tasks, enabling broader heuristic exploration. Moreover, MoH employs a multi-task training scheme to promote its generalization capability. Experiments on classic COPs demonstrate that MoH constructs an effective and interpretable meta-optimizer, achieving state-of-the-art performance across various downstream tasks, particularly in cross-size settings.
Network traffic prediction techniques have attracted much attention since they are valuable for network congestion control and user experience improvement. While existing prediction techniques can achieve favorable performance when there is sufficient training data, it remains a great challenge to make accurate predictions when only a small amount of training data is available. To tackle this problem, we propose a deep learning model, entitled MetaSTNet, based on a multimodal meta-learning framework. It is an end-to-end network architecture that trains the model in a simulator and transfers the meta-knowledge to a real-world environment, which can quickly adapt and obtain accurate predictions on a new task with only a small amount of real-world training data. In addition, we further employ cross conformal prediction to assess the calibrated prediction intervals. Extensive experiments have been conducted on real-world datasets to illustrate the efficiency and effectiveness of MetaSTNet.
In an era defined by rapid data evolution, traditional machine learning (ML) models often fall short in adapting to dynamic environments. Evolving Machine Learning (EML) has emerged as a critical paradigm, enabling continuous learning and adaptation in real-time data streams. This survey presents a comprehensive analysis of EML, focusing on five core challenges: data drift, concept drift, catastrophic forgetting, skewed learning, and network adaptation. We systematically review over 120 studies, categorizing state-of-the-art methods across supervised, unsupervised, and semi-supervised approaches. The survey explores diverse evaluation metrics, benchmark datasets, and real-world applications, offering a comparative lens on the effectiveness and limitations of current techniques. Additionally, we highlight the growing role of adaptive neural architectures, meta-learning, and ensemble strategies in addressing evolving data complexities. By synthesizing insights from recent literature, this work not only maps the current landscape of EML but also identifies critical gaps and opportunities for future research. Our findings aim to guide researchers and practitioners in developing robust, ethical, and scalable EML systems for real-world deployment.
Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) offer a fine-grained evaluation of intermediate reasoning steps and guide the reasoning process. However, extending PRMs to multimodal large language models (MLLMs) introduces challenges. Since multimodal reasoning covers a wider range of tasks compared to text-only scenarios, the resulting distribution shift from the training to testing sets is more severe, leading to greater generalization difficulty. Training a reliable multimodal PRM, therefore, demands large and diverse datasets to ensure sufficient coverage. However, current multimodal reasoning datasets suffer from a marked quality imbalance, which degrades PRM performance and highlights the need for an effective data selection strategy. To address the issues, we introduce DreamPRM, a domain-reweighted training framework for multimodal PRMs which employs bi-level optimization. In the lower-level optimization, DreamPRM performs fine-tuning on multiple datasets with domain weights, allowing the PRM to prioritize high-quality reasoning signals and alleviating the impact of dataset quality imbalance. In the upper-level optimization, the PRM is evaluated on a separate meta-learning dataset; this feedback updates the domain weights through an aggregation loss function, thereby improving the generalization capability of trained PRM. Extensive experiments on multiple multimodal reasoning benchmarks covering both mathematical and general reasoning show that test-time scaling with DreamPRM consistently improves the performance of state-of-the-art MLLMs. Further comparisons reveal that DreamPRM's domain-reweighting strategy surpasses other data selection methods and yields higher accuracy gains than existing test-time scaling approaches.
The growing adoption of Graph Neural Networks (GNNs) in high-stakes domains like healthcare and finance demands reliable explanations of their decision-making processes. While inherently interpretable GNN architectures like Graph Multi-linear Networks (GMT) have emerged, they remain vulnerable to generating explanations based on spurious correlations, potentially undermining trust in critical applications. We present MetaGMT, a meta-learning framework that enhances explanation fidelity through a novel bi-level optimization approach. We demonstrate that MetaGMT significantly improves both explanation quality (AUC-ROC, Precision@K) and robustness to spurious patterns, across BA-2Motifs, MUTAG, and SP-Motif benchmarks. Our approach maintains competitive classification accuracy while producing more faithful explanations (with an increase up to 8% of Explanation ROC on SP-Motif 0.5) compared to baseline methods. These advancements in interpretability could enable safer deployment of GNNs in sensitive domains by (1) facilitating model debugging through more reliable explanations, (2) supporting targeted retraining when biases are identified, and (3) enabling meaningful human oversight. By addressing the critical challenge of explanation reliability, our work contributes to building more trustworthy and actionable GNN systems for real-world applications.
We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's parameters, we identify parallels between LLM reasoning and various meta-learning paradigms. We formalize the training process for reasoning tasks as a meta-learning setup, with each question treated as an individual task, and reasoning trajectories serving as the inner loop optimization for adapting model parameters. Once trained on a diverse set of questions, the LLM develops fundamental reasoning capabilities that can generalize to previously unseen questions. Extensive empirical evaluations substantiate the strong connection between LLM reasoning and meta-learning, exploring several issues of significant interest from a meta-learning standpoint. Our work not only enhances the understanding of LLM reasoning but also provides practical insights for improving these models through established meta-learning techniques.
Transformer-based language models exhibit In-Context Learning (ICL), where predictions are made adaptively based on context. While prior work links induction heads to ICL through a sudden jump in accuracy, this can only account for ICL when the answer is included within the context. However, an important property of practical ICL in large language models is the ability to meta-learn how to solve tasks from context, rather than just copying answers from context; how such an ability is obtained during training is largely unexplored. In this paper, we experimentally clarify how such meta-learning ability is acquired by analyzing the dynamics of the model's circuit during training. Specifically, we extend the copy task from previous research into an In-Context Meta Learning setting, where models must infer a task from examples to answer queries. Interestingly, in this setting, we find that there are multiple phases in the process of acquiring such abilities, and that a unique circuit emerges in each phase, contrasting with the single-phases change in induction heads. The emergence of such circuits can be related to several phenomena known in large language models, and our analysis lead to a deeper understanding of the source of the transformer's ICL ability.
Prompting is one of the main ways to adapt a pretrained model to target tasks. Besides manually constructing prompts, many prompt optimization methods have been proposed in the literature. Method development is mainly empirically driven, with less emphasis on a conceptual understanding of prompting. In this paper we discuss how optimal prompting can be understood through a Bayesian view, which also implies some fundamental limitations of prompting that can only be overcome by tuning weights. The paper explains in detail how meta-trained neural networks behave as Bayesian predictors over the pretraining distribution, whose hallmark feature is rapid in-context adaptation. Optimal prompting can be studied formally as conditioning these Bayesian predictors, yielding criteria for target tasks where optimal prompting is and is not possible. We support the theory with educational experiments on LSTMs and Transformers, where we compare different versions of prefix-tuning and different weight-tuning methods. We also confirm that soft prefixes, which are sequences of real-valued vectors outside the token alphabet, can lead to very effective prompts for trained and even untrained networks by manipulating activations in ways that are not achievable by hard tokens. This adds an important mechanistic aspect beyond the conceptual Bayesian theory.
Minimum attention applies the least action principle in the changes of control concerning state and time, first proposed by Brockett. The involved regularization is highly relevant in emulating biological control, such as motor learning. We apply minimum attention in reinforcement learning (RL) as part of the rewards and investigate its connection to meta-learning and stabilization. Specifically, model-based meta-learning with minimum attention is explored in high-dimensional nonlinear dynamics. Ensemble-based model learning and gradient-based meta-policy learning are alternately performed. Empirically, we show that the minimum attention does show outperforming competence in comparison to the state-of-the-art algorithms in model-free and model-based RL, i.e., fast adaptation in few shots and variance reduction from the perturbations of the model and environment. Furthermore, the minimum attention demonstrates the improvement in energy efficiency.
This paper introduces Meta-PerSER, a novel meta-learning framework that personalizes Speech Emotion Recognition (SER) by adapting to each listener's unique way of interpreting emotion. Conventional SER systems rely on aggregated annotations, which often overlook individual subtleties and lead to inconsistent predictions. In contrast, Meta-PerSER leverages a Model-Agnostic Meta-Learning (MAML) approach enhanced with Combined-Set Meta-Training, Derivative Annealing, and per-layer per-step learning rates, enabling rapid adaptation with only a few labeled examples. By integrating robust representations from pre-trained self-supervised models, our framework first captures general emotional cues and then fine-tunes itself to personal annotation styles. Experiments on the IEMOCAP corpus demonstrate that Meta-PerSER significantly outperforms baseline methods in both seen and unseen data scenarios, highlighting its promise for personalized emotion recognition.
Finetuning openly accessible Large Language Models (LLMs) has become standard practice for achieving task-specific performance improvements. Until now, finetuning has been regarded as a controlled and secure process in which training on benign datasets led to predictable behaviors. In this paper, we demonstrate for the first time that an adversary can create poisoned LLMs that initially appear benign but exhibit malicious behaviors once finetuned by downstream users. To this end, our proposed attack, FAB (Finetuning-Activated Backdoor), poisons an LLM via meta-learning techniques to simulate downstream finetuning, explicitly optimizing for the emergence of malicious behaviors in the finetuned models. At the same time, the poisoned LLM is regularized to retain general capabilities and to exhibit no malicious behaviors prior to finetuning. As a result, when users finetune the seemingly benign model on their own datasets, they unknowingly trigger its hidden backdoor behavior. We demonstrate the effectiveness of FAB across multiple LLMs and three target behaviors: unsolicited advertising, refusal, and jailbreakability. Additionally, we show that FAB-backdoors are robust to various finetuning choices made by the user (e.g., dataset, number of steps, scheduler). Our findings challenge prevailing assumptions about the security of finetuning, revealing yet another critical attack vector exploiting the complexities of LLMs.
Understanding functional representations within higher visual cortex is a fundamental question in computational neuroscience. While artificial neural networks pretrained on large-scale datasets exhibit striking representational alignment with human neural responses, learning image-computable models of visual cortex relies on individual-level, large-scale fMRI datasets. The necessity for expensive, time-intensive, and often impractical data acquisition limits the generalizability of encoders to new subjects and stimuli. BraInCoRL uses in-context learning to predict voxelwise neural responses from few-shot examples without any additional finetuning for novel subjects and stimuli. We leverage a transformer architecture that can flexibly condition on a variable number of in-context image stimuli, learning an inductive bias over multiple subjects. During training, we explicitly optimize the model for in-context learning. By jointly conditioning on image features and voxel activations, our model learns to directly generate better performing voxelwise models of higher visual cortex. We demonstrate that BraInCoRL consistently outperforms existing voxelwise encoder designs in a low-data regime when evaluated on entirely novel images, while also exhibiting strong test-time scaling behavior. The model also generalizes to an entirely new visual fMRI dataset, which uses different subjects and fMRI data acquisition parameters. Further, BraInCoRL facilitates better interpretability of neural signals in higher visual cortex by attending to semantically relevant stimuli. Finally, we show that our framework enables interpretable mappings from natural language queries to voxel selectivity.
We present new fast-rate generalization bounds for multi-task and meta-learning in the unbalanced setting, i.e. when the tasks have training sets of different sizes, as is typically the case in real-world scenarios. Previously, only standard-rate bounds were known for this situation, while fast-rate bounds were limited to the setting where all training sets are of equal size. Our new bounds are numerically computable as well as interpretable, and we demonstrate their flexibility in handling a number of cases where they give stronger guarantees than previous bounds. Besides the bounds themselves, we also make conceptual contributions: we demonstrate that the unbalanced multi-task setting has different statistical properties than the balanced situation, specifically that proofs from the balanced situation do not carry over to the unbalanced setting. Additionally, we shed light on the fact that the unbalanced situation allows two meaningful definitions of multi-task risk, depending on whether if all tasks should be considered equally important or if sample-rich tasks should receive more weight than sample-poor ones.
Deep learning has seen widespread success in various domains such as science, industry, and society. However, it is acknowledged that certain approaches suffer from non-robustness, relying on spurious correlations for predictions. Addressing these limitations is of paramount importance, necessitating the development of methods that can disentangle spurious correlations. {This study attempts to implement causal models via logit perturbations and introduces a novel Causal Logit Perturbation (CLP) framework to train classifiers with generated causal logit perturbations for individual samples, thereby mitigating the spurious associations between non-causal attributes (i.e., image backgrounds) and classes.} {Our framework employs a} perturbation network to generate sample-wise logit perturbations using a series of training characteristics of samples as inputs. The whole framework is optimized by an online meta-learning-based learning algorithm and leverages human causal knowledge by augmenting metadata in both counterfactual and factual manners. Empirical evaluations on four typical biased learning scenarios, including long-tail learning, noisy label learning, generalized long-tail learning, and subpopulation shift learning, demonstrate that CLP consistently achieves state-of-the-art performance. Moreover, visualization results support the effectiveness of the generated causal perturbations in redirecting model attention towards causal image attributes and dismantling spurious associations.
Large language models (LLMs) are increasingly evaluated on formal tasks, where strong reasoning abilities define the state of the art. However, their ability to generalize to out-of-distribution problems remains limited. In this paper, we investigate how LLMs can achieve a systematic understanding of deductive rules. Our focus is on the task of identifying the appropriate subset of premises within a knowledge base needed to derive a given hypothesis. To tackle this challenge, we propose Meta-learning for In-context Deduction (MIND), a novel few-shot meta-learning fine-tuning approach. The goal of MIND is to enable models to generalize more effectively to unseen knowledge bases and to systematically apply inference rules. Our results show that MIND significantly improves generalization in small LMs ranging from 1.5B to 7B parameters. The benefits are especially pronounced in smaller models and low-data settings. Remarkably, small models fine-tuned with MIND outperform state-of-the-art LLMs, such as GPT-4o and o3-mini, on this task.
We propose a unified deep meta-learning framework for accelerated magnetic resonance imaging (MRI) that jointly addresses multi-coil reconstruction and cross-modality synthesis. Motivated by the limitations of conventional methods in handling undersampled data and missing modalities, our approach unrolls a provably convergent optimization algorithm into a structured neural network architecture. Each phase of the network mimics a step of an adaptive forward-backward scheme with extrapolation, enabling the model to incorporate both data fidelity and nonconvex regularization in a principled manner. To enhance generalization across different acquisition settings, we integrate meta-learning, which enables the model to rapidly adapt to unseen sampling patterns and modality combinations using task-specific meta-knowledge. The proposed method is evaluated on the open source datasets, showing significant improvements in PSNR and SSIM over conventional supervised learning, especially under aggressive undersampling and domain shifts. Our results demonstrate the synergy of unrolled optimization, task-aware meta-learning, and modality fusion, offering a scalable and generalizable solution for real-world clinical MRI reconstruction.
This work introduces CLIP-aware Domain-Adaptive Super-Resolution (CDASR), a novel framework that addresses the critical challenge of domain generalization in single image super-resolution. By leveraging the semantic capabilities of CLIP (Contrastive Language-Image Pre-training), CDASR achieves unprecedented performance across diverse domains and extreme scaling factors. The proposed method integrates CLIP-guided feature alignment mechanism with a meta-learning inspired few-shot adaptation strategy, enabling efficient knowledge transfer and rapid adaptation to target domains. A custom domain-adaptive module processes CLIP features alongside super-resolution features through a multi-stage transformation process, including CLIP feature processing, spatial feature generation, and feature fusion. This intricate process ensures effective incorporation of semantic information into the super-resolution pipeline. Additionally, CDASR employs a multi-component loss function that combines pixel-wise reconstruction, perceptual similarity, and semantic consistency. Extensive experiments on benchmark datasets demonstrate CDASR's superiority, particularly in challenging scenarios. On the Urban100 dataset at $\times$8 scaling, CDASR achieves a significant PSNR gain of 0.15dB over existing methods, with even larger improvements of up to 0.30dB observed at $\times$16 scaling.
This paper introduces Ready2Unlearn, a learning-time optimization approach designed to facilitate future unlearning processes. Unlike the majority of existing unlearning efforts that focus on designing unlearning algorithms, which are typically implemented reactively when an unlearning request is made during the model deployment phase, Ready2Unlearn shifts the focus to the training phase, adopting a "forward-looking" perspective. Building upon well-established meta-learning principles, Ready2Unlearn proactively trains machine learning models with unlearning readiness, such that they are well prepared and can handle future unlearning requests in a more efficient and principled manner. Ready2Unlearn is model-agnostic and compatible with any gradient ascent-based machine unlearning algorithms. We evaluate the method on both vision and language tasks under various unlearning settings, including class-wise unlearning and random data unlearning. Experimental results show that by incorporating such preparedness at training time, Ready2Unlearn produces an unlearning-ready model state, which offers several key advantages when future unlearning is required, including reduced unlearning time, improved retention of overall model capability, and enhanced resistance to the inadvertent recovery of forgotten data. We hope this work could inspire future efforts to explore more proactive strategies for equipping machine learning models with built-in readiness towards more reliable and principled machine unlearning.
Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when LLMs are used as reward models. We introduce Meta Policy Optimization (MPO), a framework that addresses these challenges by integrating a meta-reward model that dynamically refines the reward model's prompt throughout training. In MPO, the meta-reward model monitors the evolving training context and continuously adjusts the reward model's prompt to maintain high alignment, providing an adaptive reward signal that resists exploitation by the policy. This meta-learning approach promotes a more stable policy optimization, and greatly reduces the need for manual reward prompt design. It yields performance on par with or better than models guided by extensively hand-crafted reward prompts. Furthermore, we show that MPO maintains its effectiveness across diverse tasks, from essay writing to mathematical reasoning, without requiring specialized reward designs. Beyond standard RLAIF, MPO's meta-learning formulation is readily extensible to higher-level alignment frameworks. Overall, this method addresses theoretical and practical challenges in reward-based RL alignment for LLMs, paving the way for more robust and adaptable alignment strategies. The code and data can be accessed at: https://github.com/minnesotanlp/mpo
Large Language Models (LLMs) have shown remarkable capabilities, with optimizing their input prompts playing a pivotal role in maximizing their performance. However, while LLM prompts consist of both the task-agnostic system prompts and task-specific user prompts, existing work on prompt optimization has focused on user prompts specific to individual queries or tasks, and largely overlooked the system prompt that is, once optimized, applicable across different tasks and domains. Motivated by this, we introduce the novel problem of bilevel system prompt optimization, whose objective is to design system prompts that are robust to diverse user prompts and transferable to unseen tasks. To tackle this problem, we then propose a meta-learning framework, which meta-learns the system prompt by optimizing it over various user prompts across multiple datasets, while simultaneously updating the user prompts in an iterative manner to ensure synergy between them. We conduct experiments on 14 unseen datasets spanning 5 different domains, on which we show that our approach produces system prompts that generalize effectively to diverse user prompts. Also, our findings reveal that the optimized system prompt enables rapid adaptation even to unseen tasks, requiring fewer optimization steps for test-time user prompts while achieving improved performance.