ICML 2025 Papers

Class imbalance remains a major challenge in machine learning, especially in multi-class problems with long-tailed distributions. Existing methods, such as data resampling, cost-sensitive techniques, and logistic loss modifications, though popular and often effective, lack solid theoretical foundations. As an example, we demonstrate that cost-sensitive methods are not Bayes-consistent. This paper introduces a novel theoretical framework for analyzing generalization in imbalanced classification. We propose a new class-imbalanced margin loss function for both binary and multi-class settings, prove its strong $H$-consistency, and derive corresponding learning guarantees based on empirical loss and a new notion of class-sensitive Rademacher complexity. Leveraging these theoretical results, we devise novel and general learning algorithms, IMMAX (*Imbalanced Margin Maximization*), which incorporate confidence margins and are applicable to various hypothesis sets. While our focus is theoretical, we also present extensive empirical results demonstrating the effectiveness of our algorithms compared to existing baselines.

Language model (LLM) post-training can refine behaviors and unlock new skills, but the open science supporting these post-training techniques is still in its infancy. One limiting factor has been the difficulty of conducting large-scale comparative analyses of synthetic data generating models and LLM judges. To close this gap, we introduce WildChat-50M, the largest public chat dataset to date. We extend the existing WildChat dataset to include responses not only from GPT, but from over 50 different open-weight models, ranging in size from 0.5B to 104B parameters. We conduct an extensive comparative analysis and demonstrate the potential of this dataset by creating Re-Wild, our own public SFT mix, which outperforms the recent Tulu-3 SFT mixture from Allen AI with only 40% as many samples.

Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short captions. To address this, we propose Fine-Grained CLIP (FG-CLIP), which enhances fine-grained understanding through three key innovations. First, we leverage large multimodal models to generate 1.6 billion long caption-image pairs for capturing global-level semantic details. Second, a high-quality dataset is constructed with 12 million images and 40 million region-specific bounding boxes aligned with detailed captions to ensure precise, context-rich representations. Third, 10 million hard fine-grained negative samples are incorporated to improve the model's ability to distinguish subtle semantic differences. We construct a comprehensive dataset, termed FineHARD, by integrating high-quality region-specific annotations with challenging fine-grained negative samples. Corresponding training methods are meticulously designed for these data. Extensive experiments demonstrate that FG-CLIP outperforms the original CLIP and other state-of-the-art methods across various downstream tasks, including fine-grained understanding, open-vocabulary object detection, image-text retrieval, and general multimodal benchmarks. These results highlight FG-CLIP's effectiveness in capturing fine-grained image details and improving overall model performance. The data, code, and models are available at https://github.com/360CVGroup/FG-CLIP.

Despite deep neural networks' powerful representation learning capabilities, theoretical understanding of how networks can simultaneously achieve meaningful feature learning and global convergence remains elusive. Existing approaches like the neural tangent kernel (NTK) are limited because features stay close to their initialization in this parametrization, leaving open questions about feature properties during substantial evolution. In this paper, we investigate the training dynamics of infinitely wide, $L$-layer neural networks using the tensor program (TP) framework. Specifically, we show that, when trained with stochastic gradient descent (SGD) under the Maximal Update parametrization ($\mu$P) and mild conditions on the activation function, SGD enables these networks to learn linearly independent features that substantially deviate from their initial values. This rich feature space captures relevant data information and ensures that any convergent point of the training process is a global minimum. Our analysis leverages both the interactions among features across layers and the properties of Gaussian random variables, providing new insights into deep representation learning. We further validate our theoretical findings through experiments on real-world datasets.

This position paper critiques the reliance on rigid racial taxonomies in machine learning, exposing their U.S.-centric nature and lack of global applicability—particularly in Europe, where race categories are not commonly used. These classifications oversimplify racial identity, erasing the experiences of mixed-race individuals and reinforcing outdated essentialist views that contradict the social construction of race. We suggest research agendas in machine learning that move beyond categorical variables to better address discrimination and social inequality.

Modular object-centric representations are essential for *human-like reasoning* but are challenging to obtain under spatial ambiguities, *e.g. due to occlusions and view ambiguities*. However, addressing challenges presents both theoretical and practical difficulties. We introduce a novel multi-view probabilistic approach that aggregates view-specific slots to capture *invariant content* information while simultaneously learning disentangled global *viewpoint-level* information. Unlike prior single-view methods, our approach resolves spatial ambiguities, provides theoretical guarantees for identifiability, and requires *no viewpoint annotations*. Extensive experiments on standard benchmarks and novel complex datasets validate our method's robustness and scalability.

We address the challenge of certifying the performance of a federated learning model on an unseen target network using only measurements from the source network that trained the model. Specifically, consider a source network "A" with $K$ clients, each holding private, non-IID datasets drawn from heterogeneous distributions, modeled as samples from a broader meta-distribution $\mu$. Our goal is to provide certified guarantees for the model’s performance on a different, unseen network "B", governed by an unknown meta-distribution $\mu'$, assuming the deviation between $\mu$ and $\mu'$ is bounded—either in Wasserstein distance or an $f$-divergence. We derive worst-case uniform guarantees for both the model’s average loss and its risk CDF, the latter corresponding to a novel, adversarially robust version of the Dvoretzky–Kiefer–Wolfowitz (DKW) inequality. In addition, we show how the vanilla DKW bound enables principled certification of the model's true performance on unseen clients within the same (source) network. Our bounds are efficiently computable, asymptotically minimax optimal, and preserve clients' privacy. We also establish non-asymptotic generalization bounds that converge to zero as $K$ grows and the minimum per-client sample size exceeds $\mathcal{O}(\log K)$. Empirical evaluations confirm the practical utility of our bounds across real-world tasks. The project code is available at: github.com/samin-mehdizadeh/Robust-Evaluation-DKW

We evaluate methods for causal representation learning (CRL) on a simple, real-world system where these methods are expected to work. The system consists of a controlled optical experiment specifically built for this purpose, which satisfies the core assumptions of CRL and where the underlying causal factors---the inputs to the experiment---are known, providing a ground truth. We select methods representative of different approaches to CRL and find that they all fail to recover the underlying causal factors. To understand the failure modes of the evaluated algorithms, we perform an ablation on the data by substituting the real data-generating process with a simpler synthetic equivalent. The results reveal a reproducibility problem, as most methods already fail on this synthetic ablation despite its simple data-generating process. Additionally, we observe that common assumptions on the mixing function are crucial for the performance of some of the methods but do not hold in the real data. Our efforts highlight the contrast between the theoretical promise of the state of the art and the challenges in its application. We hope the benchmark serves as a simple, real-world sanity check to further develop and validate methodology, bridging the gap towards CRL methods that work in practice. We make all code and datasets publicly available at <anonymized>.

We study efficient algorithms for the Euclidean $k$-Center problem, focusing on the regime of large $k$. We take the approach of data reduction by considering $\alpha$-coreset, which is a small subset $S$ of the dataset $P$ such that any $\beta$-approximation on $S$ is an $(\alpha + \beta)$-approximation on $P$. We give efficient algorithms to construct coresets whose size is $k \cdot o(n)$, which immediately speeds up existing approximation algorithms. Notably, we obtain a near-linear time $O(1)$-approximation when $k = n^c$ for any $0 < c < 1$. We validate the performance of our coresets on real-world datasets with large $k$, and we observe that the coreset speeds up the well-known Gonzalez algorithm by up to $4$ times, while still achieving similar clustering cost. Technically, one of our coreset results is based on a new efficient construction of consistent hashing with competitive parameters. This general tool may be of independent interest for algorithm design in high dimensional Euclidean spaces.

Class distribution mismatch (CDM) refers to the discrepancy between class distributions in training data and target tasks. Previous methods address this by designing classifiers to categorize classes known during training, while grouping unknown or new classes into an "other" category. However, they focus on semi-supervised scenarios and heavily rely on labeled data, limiting their applicability and performance. To address this, we propose Unsupervised Learning for Class Distribution Mismatch (UCDM), which constructs positive-negative pairs from unlabeled data for classifier training. Our approach randomly samples images and uses a diffusion model to add or erase semantic classes, synthesizing diverse training pairs. Additionally, we introduce a confidence-based labeling mechanism that iteratively assigns pseudo-labels to valuable real-world data and incorporates them into the training process. Extensive experiments on three datasets demonstrate UCDM’s superiority over previous semi-supervised methods. Specifically, with a 60\% mismatch proportion on Tiny-ImageNet dataset, our approach, without relying on labeled data, surpasses OpenMatch (with 40 labels per class) by 35.1%, 63.7%, and 72.5% in classifying known, unknown, and new classes.

Advances in Large Language Models (LLMs) have sparked interest in their ability to solve Olympiad-level math problems. However, the training and evaluation of these models are constrained by the limited size and quality of available datasets, as creating large-scale data for such advanced problems requires extensive effort from human experts. In addition, current benchmarks are prone to contamination, leading to unreliable evaluations. In this paper, we present an automated pipeline that leverages the rich resources of the Art of Problem Solving (AoPS) forum, which predominantly features Olympiad-level problems and community-driven solutions. Using open-source LLMs, we develop a method to extract question-answer pairs from the forum, resulting in **AoPS-Instruct**, a dataset of more than 600,000 high-quality QA pairs. Our experiments demonstrate that fine-tuning LLMs on AoPS-Instruct improves their reasoning abilities across various benchmarks. Moreover, we build an automatic pipeline that introduces **LiveAoPSBench**, an evolving evaluation set with timestamps, derived from the latest forum data, providing a contamination-resistant benchmark for assessing LLM performance. Notably, we observe a significant decline in LLM performance over time, suggesting their success on older examples may stem from pre-training exposure rather than true reasoning ability. Our work presents a scalable approach to creating and maintaining large-scale, high-quality datasets for advanced math reasoning, offering valuable insights into the capabilities and limitations of LLMs in this domain.

Modern language models are trained on large, unstructured datasets consisting of trillions of tokens and obtained by crawling the web. The unstructured nature makes it difficult to reason about their contents and develop systematic approaches to data curation. In this paper, we unpack monolithic web corpora by developing taxonomies of their contents and organizing them into domains. We introduce WebOrganizer, a framework for organizing web pages in terms of both their topic and format. Using these two complementary notions of domains, we automatically annotate pre-training data by distilling annotations from a large language model into efficient classifiers. This allows us to study how data from different domains should be mixed to improve models on downstream tasks, and we show that we can combine insights about effective topics and formats to further boost performance. We demonstrate that our domain mixing also improves existing methods that select data based on quality. Furthermore, we study and compare how quality-based methods will implicitly change the domain mixture. Overall, our work demonstrates that constructing and mixing domains provides a valuable complement to quality-based data curation methods, opening new avenues for effective and insightful pre-training data curation.

The recent rapid adoption of large language models (LLMs) highlights the critical need for benchmarking their fairness. Conventional fairness metrics, which focus on discrete accuracy-based evaluations (i.e., prediction correctness), fail to capture the implicit impact of model uncertainty (e.g., higher model confidence about one group over another despite similar accuracy). To address this limitation, we propose an uncertainty-aware fairness metric, UCerf, to enable a fine-grained evaluation of model fairness that is more reflective of the internal bias in model decisions. Furthermore, observing data size, diversity, and clarity issues in current datasets, we introduce a new gender-occupation fairness evaluation dataset with 31,756 samples for co-reference resolution, offering a more diverse and suitable benchmark for modern LLMs. Combining our metric and dataset, we provide insightful comparisons of eight open-source LLMs. For example, Mistral-8B exhibits suboptimal fairness due to high confidence in incorrect predictions, a detail overlooked by Equalized Odds but captured by UCerF. Overall, this work provides a holistic framework for LLM evaluation by jointly assessing fairness and uncertainty, enabling the development of more transparent and accountable AI systems.

Dataset Distillation (DD) compresses large datasets into smaller, synthetic subsets, enabling models trained on them to achieve performance comparable to those trained on the full data. However, these models remain vulnerable to adversarial attacks, limiting their use in safety-critical applications. While adversarial robustness has been extensively studied in related fields, research on improving DD robustness is still limited. To address this, we propose ROME, a novel method that enhances the adversarial RObustness of DD by leveraging the InforMation BottlenEck (IB) principle. ROME includes two components: a performance-aligned term to preserve accuracy and a robustness-aligned term to improve robustness by aligning feature distributions between synthetic and perturbed images. Furthermore, we introduce the Improved Robustness Ratio (I-RR), a refined metric to better evaluate DD robustness. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate that ROME outperforms existing DD methods in adversarial robustness, achieving maximum I-RR improvements of nearly 40% under white-box attacks and nearly 35% under black-box attacks. Our code is available at https://github.com/zhouzhengqd/ROME.

The remarkable capabilities of Large Language Models (LLMs) can be mainly attributed to their massive training datasets, which are often scraped from the internet without respecting data owners’ intellectual property rights. Dataset Inference (DI) offers a potential remedy by identifying whether a suspect dataset was used in training, thereby enabling data owners to verify unauthorized use. However, existing DI methods require a private set—known to be absent from training—that closely matches the compromised dataset’s distribution. Such in-distribution, held-out data is rarely available in practice, severely limiting the applicability of DI. In this work, we address this challenge by synthetically generating the required held-out set. Our approach tackles two key obstacles: (1) creating high-quality, diverse synthetic data that accurately reflects the original distribution, which we achieve via a data generator trained on a carefully designed suffix-based completion task, and (2) bridging likelihood gaps between real and synthetic data, which is realized through post-hoc calibration. Extensive experiments on diverse text datasets show that using our generated data as a held-out set enables DI to detect the original training sets with high confidence, while maintaining a low false positive rate. This result empowers copyright owners to make legitimate claims on data usage and demonstrates our method’s reliability for real-world litigations. Our code is available at https://github.com/sprintml/PostHocDatasetInference.

Many real-world applications, such as logistics, routing, scheduling, and production planning, involve dynamic systems that require continuous updates to solutions for new Mixed Integer Linear Programming (MILP) problems. These systems often require rapid updates to their solutions to accommodate slight modifications in constraints or objectives introduced by evolving conditions. While reoptimization techniques have been explored for Linear Programming (LP) and certain specific MILP problems, their effectiveness in addressing general MILP is limited. In this work, we propose a two-stage reoptimization framework for efficiently identifying high-quality feasible solutions. Specifically, we first utilize the historical solving process information to predict a high confidence solution space for modified MILPs, which is likely to contain high-quality solutions. Building on the prediction results, we fix a part of variables within the predicted intervals and apply the Thompson Sampling algorithm to determine which variables to fix. This is done by updating the Beta distributions based on the solutions obtained from the solver. Extensive experiments across nine reoptimization datasets show that our VP-OR outperforms the state-of-the-art methods, achieving higher-quality solutions under strict time limits.

Medical large language models (LLMs) research often makes bold claims, from encoding clinical knowledge to reasoning like a physician. These claims are usually backed by evaluation on competitive benchmarks—a tradition inherited from mainstream machine learning. But how do we separate real progress from a leaderboard flex? Medical LLM benchmarks, much like those in other fields, are arbitrarily constructed using medical licensing exam questions. For these benchmarks to truly measure progress, they must accurately capture the real-world tasks they aim to represent. In this position paper, we argue that medical LLM benchmarks should—and indeed can—be empirically evaluated for their construct validity. In the psychological testing literature, “construct validity” refers to the ability of a test to measure an underlying “construct”, that is the actual conceptual target of evaluation. By drawing an analogy between LLM benchmarks and psychological tests, we explain how frameworks from this field can provide empirical foundations for validating benchmarks. To put these ideas into practice, we use real-world clinical data in proof-of-concept experiments to evaluate popular medical LLM benchmarks and report significant gaps in their construct validity. Finally, we outline a vision for a new ecosystem of medical LLM evaluation centered around the creation of valid benchmarks.

Existing reward shaping techniques for sparse-reward reinforcement learning generally fall into two categories: novelty-based exploration bonuses and significance-based hidden state values. The former promotes exploration but can lead to distraction from task objectives, while the latter facilitates stable convergence but often lacks sufficient early exploration. To address these limitations, we propose Dual Random Networks Distillation (DuRND), a novel reward shaping framework that efficiently balances exploration and exploitation in a unified mechanism. DuRND leverages two lightweight random network modules to simultaneously compute two complementary rewards: a novelty reward to encourage directed exploration and a contribution reward to assess progress toward task completion. With low computational overhead, DuRND excels in high-dimensional environments with challenging sparse rewards, such as Atari, VizDoom, and MiniWorld, outperforming several benchmarks.

This paper introduces Llavaguard, a suite of VLM-based vision safeguards that address the critical need for reliable tools in the era of large-scale data and models. To this end, we establish a novel open framework, describing a customizable safety taxonomy, data preprocessing, augmentation, and training setup. For teaching a VLM safeguard on safety, we further create a multimodal safety dataset with high-quality human expert annotations, where each image is labeled with a safety rating, category, and rationale. We also employ advanced augmentations to support context-specific assessments. The resulting Llavaguard models, ranging from 0.5B to 7B, serve as a versatile tool for evaluating the safety compliance of visual content against flexible policies. In comprehensive experiments, Llavaguard outperforms both state-of-the-art safeguards and VLMs in accuracy and in flexibly handling different policies. Additionally, we demonstrate Llavaguard's performance in two real-world applications: large-scale dataset annotation and moderation of text-to-image models. We make our entire framework, including the dataset, model weights, and training code, publicly available at https://ml-research.github.io/human-centered-genai/projects/llavaguard.