ICML 2026 Papers

Multi-modal dataset distillation (MDD) seeks to compress large-scale multi-modal datasets into a compact set of synthetic pairs. Existing methods employ a dual-trajectory matching framework to align the teacher and student models within each modality. While effective, this paradigm incurs non-negligible memory and computational overhead due to the checkpoint storage and bi-level optimization over synthetic data. To address these limitations, we propose analytic parameter matching (APM), which theoretically derives the analytic parameters of modal projectors to replace the inner-loop optimization, and then aligns the analytic projector parameters of teacher and student models. APM offers two key advantages: (1) it replaces checkpoint-intensive storage with only two cached matrices, significantly reducing memory consumption; and (2) it computes analytic parameters in a single forward pass, thereby avoiding costly bi-level optimization. Empirically, APM achieves up to 65$\times$ storage reduction and 9.6$\times$ faster distillation, while scaling to 1,000 synthetic pairs. Extensive experiments on image-text and audio-text benchmarks demonstrate the effectiveness of APM in cross-modal retrieval tasks, e.g., 12.8 IR@1 and 17.8 TR@1 in Flickr30k with 100 synthetic pairs. Moreover, APM exhibits notable generalization performance in cross-architecture evaluation and zero-shot classification tasks.

Privacy protection has become a critical requirement in the era of ubiquitous visual data sharing, imposing higher demands on efficient and robust privacy detection algorithms. However, current robust detection models are severely hindered by the lack of comprehensive datasets. Existing privacy-oriented datasets often suffer from limited scale, coarse-grained annotations, and narrow domain coverage, failing to capture the intricate details of sensitive information in real-world environments. To bridge this gap, we present a large-scale, fine-grained Visual Privacy Dataset (VPD-100K), designed to facilitate generalized privacy detection. We establish a holistic taxonomy comprising four primary domains: Human Presence, On-Screen Personally Identifiable Information (PII), Physical Identifiers, and Location Indicators, containing 100,000 images annotated with 33 fine-grained classes and over 190,000 object instances. Statistical analysis reveals that our dataset features long-tailed distributions, small object scales, and high visual complexity. These characteristics make the dataset particularly valuable for demanding, unconstrained applications such as live streaming, where actors frequently face unintentional, real-time information leakage. Furthermore, we design an effective frequency-enhance lightweight module consisting of frequency-domain attention fusion and adaptive spectral gating mechanism that breaks the limitations of spatial pixel intensity to better capture the subtle details of sensitive information. Extensive experiments conducted on both diverse image and streaming videos benchmarks consistently demonstrate the effectiveness of our VPD-100K dataset and the well-curated frequency mechanism.

Self-supervised learning (SSL) learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necessitating domain-specific explanations. We introduce KREPES, a unified framework to analytically interpret the learned representations of SSL objectives, including SimCLR, BYOL, and VICReg. By bridging empirical neural tangent kernel approximations of neural networks with the Representer Theorem for kernels, we express the learned latent space directly via "Representer Landmarks", which are the representations of influential unlabeled training examples. We introduce novel metrics, "Sample-Specific Influence Score", "Concept-Conditioned Influence Score" and "Feature Alignment Gap", to quantify the transparency of the learned representations. KREPES enables direct audit of the latent space without supervision, for example, revealing an algorithmic bias in the Adult-1M dataset where SSL uses demographic proxies for income. Finally, to ensure scalability to benchmarks with 1M+ samples (ImageNet-1K, Adult-1M), KREPES introduces a novel Nyström approximation-based analytical inference framework for SSL objectives.

Continual Model Merging (CMM) enables rapid customization of foundation models by sequentially incorporating task-adapted models without repeated retraining. However, existing merging rules usually update the deployed model through fixed algebraic or projection-based operations, providing limited control over how much previously accumulated knowledge should be retained relative to the incoming task model. This limitation leads to unstable retention and performance degradation in long task streams, and becomes more pronounced when tasks have heterogeneous utilities. We propose ODE-driven Merging (ODE-M), a controllable framework that formulates each continual merge as a trajectory in parameter space rather than a one-step endpoint update. Motivated by mode connectivity, ODE-M constructs a barrier-aware trajectory using a rectified time-dependent velocity field, where lightweight first-order feedback from a small calibration set suppresses loss-increasing motion while preserving progress toward the incoming model. The next merged model is then obtained by selecting an operating point along this trajectory through a utility-aware time schedule, providing an explicit mechanism for balancing retained historical knowledge and incoming task expertise. Extensive experiments on standard CMM benchmarks show that ODE-M consistently improves over strong continual merging baselines across CLIP ViT backbones, stream lengths, and heterogeneous task-utility settings.

Large language models (LLMs) can struggle to memorize factual knowledge in their parameters, often leading to hallucinations and poor performance on knowledge-intensive tasks. In this paper, we formalize fact memorization from an information-theoretic perspective and study how training data distributions affect fact accuracy. We show that fact accuracy is suboptimal (below the capacity limit) whenever the amount of information contained in the training data facts exceeds model capacity. This is further exacerbated when the fact frequency distribution is skewed (e.g. a power law). We propose data selection schemes based on the training loss alone that aim to limit the number of facts in the training data and flatten their frequency distribution. On semi-synthetic datasets containing high-entropy facts, our selection method effectively boosts fact accuracy to the capacity limit. When pretraining language models from scratch on an annotated Wikipedia corpus, our selection method enables a GPT2-Small model (110m parameters) to memorize 1.3X more entity facts compared to standard training, matching the performance of a 10X larger model (1.3B parameters) pretrained on the full dataset.

Artificial Intelligence (AI) benchmarks play a central role in measuring progress in model development and guiding deployment decisions. However, many benchmarks quickly become saturated, meaning that they can no longer differentiate between the best-performing models, diminishing their long-term value. In this study, we analyze benchmark saturation across 60 Large Language Model (LLM) benchmarks selected from technical reports by major model developers. To identify factors driving saturation, we characterize benchmarks along 14 properties spanning task design, data construction, and evaluation format. We test five hypotheses examining how each property contributes to saturation rates. Our analysis reveals that nearly half of the benchmarks exhibit saturation, with rates increasing as benchmarks age. Notably, hiding test data (i.e., public vs. private) shows no protective effect, while expert-curated benchmarks resist saturation better than crowdsourced ones. Our findings highlight which design choices extend benchmark longevity and inform strategies for more durable evaluation.

When computing gradients, deep learning training algorithms typically treat the mini-batch as a fundamental unit --- only returning batch-averaged gradients. Computing non-linear statistics of the mini-batch gradient distribution has traditionally been viewed as prohibitively expensive or requiring complex, custom implementations. We challenge this view by demonstrating that sequence-level architectures offer a natural testbed for prototyping algorithms based on per-example gradients. We show that staged programming languages like JAX enable generic manipulations of mini-batch gradient computations. We then build on Dangel et. al. (2019) to derive implementations of specific per-example or per-token operations with negligible computational or memory overhead. Finally, we leverage our findings to re-examine two nonlinear optimization operations. First, we analyze signSGD, showing that the optimal placement of the sign operation is critical to success and can be predicted via a simple signal-to-noise ratio argument. Second, we investigate per-example variations of the Adam preconditioner and find that, contrary to conventional wisdom, optimization is best served when the preconditioner is dominated by the mean squared of the gradient distribution rather than its variance. Overall our work shows that accessible per-example gradient information unlocks new avenues for algorithm analysis and design.

Evaluating survival models under censoring is inherently challenging, yet standard evaluation practices are often applied without explicitly assessing how censoring distorts metric reliability. Performing a large experimental study, we analyze and quantify how survival evaluation metrics are affected in fundamentally different ways by the censoring rate and the censoring mechanism. Using a controlled semi-synthetic framework, we vary both the censoring mechanism (administrative, independent, covariate-dependent) and the censoring rate, and compare standard evaluations based on censored data with oracle evaluations using fully observed event times. This controlled setting enables us to quantify distortions along two complementary axes: numerical bias and preservation of model ranking. Across datasets and metric families, we find that censoring induces systematic, mechanism-dependent distortions. Moderate numerical bias, if not properly addressed, can lead to unreliable model comparison as censoring increases. These findings reveal fundamental limitations of common benchmarking practices and call for more careful interpretation of survival evaluation under realistic censoring.

Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness uncontrolled. Recent robust DD methods improve robustness, yet they often suffer from a poor accuracy–robustness trade-off because they (i) treat all adversarially perturbed examples uniformly, despite robust risk being dominated by near-zero robust margins, and (ii) do not explicitly increase inter-class separation in the decision boundary where attacks concentrate. We present Contrastive Curriculum for Robust Dataset Distillation (C$^2$R), a framework that couples an attack-aware curriculum with a contrastive robustness objective. From a robust-margin perspective, we derive a \emph{perturbation score} that approximates each sample’s robust hinge, enabling a curriculum that prioritizes the smallest-margin adversaries that most directly drive robust error. In parallel, a class-balanced contrastive robustness loss enforces adversarial invariance while explicitly widening boundary separation across classes. Experiments on CIFAR-10/100, Tiny-ImageNet, and multiple ImageNet-1K subsets under six attacks show that C$^2$R achieves the best robust accuracy, outperforming prior robust DD by 2.8% on average.

Recent benchmarks reveal that single-cell perturbation response models are often outperformed by simply predicting the dataset mean. Through large-scale *in silico* simulations, together with analyses of two real-world perturbation datasets, we trace this anomaly to a metric artifact: unweighted error metrics systematically reward mean predictions when perturbation effects are sparse. To address this limitation, we introduce differentially expressed gene (DEG)-aware metrics—weighted mean-squared error (WMSE) and weighted delta $R^{2}$ ($R^{2}_{w}(\Delta)$)—that sensitively measure error in niche, perturbation-specific signals. We further propose explicit negative and positive performance baselines to calibrate these metrics. Under this framework, the mean baseline sinks to null performance, while genuinely informative predictors are correctly rewarded. Finally, we show that using WMSE as a training objective reduces mode collapse and improves predictive performance across multiple model architectures.

The rapid development of multimodal large language models (MLLMs) has created an urgent demand for more reliable and robust evaluation protocols, however, existing static benchmarks are prone to data contamination and performance saturation, which can result in inflated or misleading evaluation results. To address these limitations, we first introduce a graph formulation to represent both static and dynamic visual question answering (VQA) samples. Building upon this formulation, we propose Knowledge-Enhanced Benchmark Evolution (KBE), a dynamic multimodal evaluation framework that first analyzes the original static benchmark, then expands it by integrating multimodal knowledge, transforming the static benchmark into a controllable, dynamic evolving version. Crucially, KBE can both reconstruct questions by Re-selecting visual information in the original image and expand existing questions with external textual knowledge. By explicitly controlling the degree of question exploration, KBE enables difficulty-controllable evaluation across a wide range of model capabilities. Extensive experimental results demonstrate that KBE effectively mitigates data contamination and benchmark saturation, while providing a more comprehensive and flexible assessment of MLLM performance.

Post-training quantization (PTQ) suffers from severe accuracy degradation in ultra-low-bit regimes. To address this challenge, we propose SHARP-Q, a unified framework grounded in Information Geometry that aligns the quantization objective with the intrinsic Fisher geometry. Following a "Rectify-then-Approximate" strategy, SHARP-Q first preconditions the optimization landscape via Hessian-Aware Rectification (HAR) and subsequently approximates the rectified Fisher Information Matrix through Dynamic Fisher-Subspace Compensation (DFSC). Our empirical evaluations reveal a pivotal insight: precise geometric alignment enables hardware-friendly uniform quantizers to outperform specialized non-uniform designs. Extensive experiments across representative convolutional networks, Vision Transformers, and State Space Models confirm that SHARP-Q establishes new state-of-the-art results, achieving substantial accuracy gains in the challenging W2A2 and W3A3 settings.

Unsupervised Camouflaged Object Detection (UCOD) aims to identify objects concealed in their surroundings without relying on pixel-level labels. Existing methods rely solely on simple post-processing of DINO high-dimensional features to generate pseudo labels for training. However, these methods suffer from two major limitations: 1) pseudo labels they easily generate contain excessive noise, causing the model to learn substantial incorrect information. 2) Although pseudo-label supervision allows the model to understand the task, it remains insufficient for generating fine-grained segmentation of the camouflaged objects. To address these issues, we propose DualUCOD, a novel UCOD method based on dual-branch contrastive learning that effectively detects camouflaged objects without pixel-level labels. Specifically, we propose the Dual-Eigenvector Spectral Pseudo-Labeling (DESPL) strategy, which fuses semantic and color cues into an affinity matrix. We then compute the eigenvectors of its normalized graph Laplacian and generate high-quality pseudo-labels using these eigenvectors. Furthermore, we introduce a Boundary-Guided Foreground-Background Refinement (BGFBR) module that explicitly incorporates boundary information to improve segmentation accuracy. Finally, we introduce a Dual-Branch Contrastive Learning (DBCL) module that constructs positive and negative pairs from the original and augmented images, aligning positive representations while contrasting them against negatives to enhance camouflaged object understanding. Extensive experiments demonstrate that DualUCOD outperforms state-of-the-art methods on different datasets in the unsupervised setting.

With large language models (LLMs) now performing strongly across diverse tasks, there is growing demand for them to personalize outputs for individual users. Personalization is typically framed as an additional layer on top of a base NLP task, requiring model responses to meet user-specific needs while still accomplishing the underlying task. From a token-level perspective, different tokens in a response contribute to personalization to varying degrees. Tokens with higher personalization relevance should therefore receive greater emphasis when developing personalized LLMs. However, accurately estimating such personalization degrees remains challenging. To address this challenge, we propose PerContrast, a self-contrast method that estimates each output token’s dependence on user-specific information through causal intervention. Building on this mechanism, we develop the PerCE loss, which adaptively upweights tokens with higher estimated personalization degrees during training via a bootstrap procedure, enabling the model to alternate between estimating and optimizing these tokens. Experiments on multiple LLMs demonstrate that PerCE substantially improves personalization performance with minimal additional cost, achieving average gains of over 10\% and up to 68.04\% on the LongLaMP dataset, along with strong cross-task and cross-scenario transferability. These results highlight the importance of token-level personalization modeling and establish token-aware training as a simple yet effective paradigm for advancing personalized LLMs.

Current LLM evaluations often conflate benchmark performance with intrinsic model capability. This is misleading, as observed outcomes arise from the entire evaluation system, including datasets, prompting methods, decoding parameters, and the software–hardware stack, rather than the model alone. When this system is under-specified, attribution becomes unreliable; in practice, evaluation choices alone can induce accuracy swings of up to 70%. This challenge is compounded by the open-ended nature of LLM evaluation, where questions span languages, domains, and usage styles, forming variable and implicitly shifting datasets. Consequently, strong performance on static benchmarks may reflect surface alignment or dataset-induced effects rather than robust capability. Prior studies often focus on individual components or manually-curated small-scale dataset variants, overlooking interactions and dataset-related confounding. To address these limitations, we propose LLM evaluatology, a principled framework that grounds LLM evaluation in a causally motivated system design. It combines structured causal modeling as an intervention-oriented lens with factorial decomposition under design of experiments, quantifying main and interaction effects while using instance-level interventions to probe dataset-induced effects. By jointly modeling evaluation components and structured question variations, LLM evaluatology enables more interpretable, reproducible, and carefully attributed assessment of model capability. Our framework is publicly available at [GitHub](https://github.com/BenchCouncil/llm-evaluatology).

When gradient information is unavailable, black-box optimization (BBO) methods provide a practical alternative. While Evolution Strategies (ES), Consensus-Based Optimization (CBO), Optimization via Integration (OVI), and related methods have each been studied independently, their connections remain underexplored. We unify these approaches within a common theoretical framework, revealing that they differ primarily in two design choices: fitness aggregation (controlling sharpness preference) and consensus scope (controlling modality). Leveraging these insights, we introduce hybrid optimizers that interpolate between existing methods. Our ES-OVI hybrid allows explicit control over the preference for flat minima, enabling a trade-off between performance and robustness in continuous control tasks. Our CBO-OVI hybrids combine the higher-dimensional efficiency of parametric methods with the multimodal capabilities of particle-based approaches, achieving competitive results on language model merging under limited evaluation budgets. We validate our methods on standard BBO benchmarks and higher-dimensional locomotion tasks, demonstrating that the hybrid methods can outperform their constituent algorithms.

Standard contrastive learning minimizes geometric distance between positive pairs, implicitly assuming that strict compactness optimizes discrimination. However, this topology-agnostic confusion neglects intrinsic data structures and topological complexity, leading to class confusion—particularly when aggressive augmentations induce semantic drift. To address this, we propose Topology-Aware Contrastive Learning, a framework that shifts the objective from geometric singularity to topological connectivity. Leveraging Persistent Homology, we explicitly regulate the connectivity of the latent space, ensuring positive pairs maintain an $\alpha\text{--}\beta$ connectivity that balances intra-class cohesion with separability. Theoretically, we formally define the topology-agnostic confusion phenomenon, prove that excessive compactness strictly lower-bounds the probability of confusion and derive a generalization bound demonstrating that richer topological connectivity tightens downstream risk. Furthermore, we establish a measure-theoretic framework to mitigating the sensitivity of our method against varying augmentation strengths. Empirical results on benchmarks confirm that our approach enhances representation quality and reduces reliance on specific augmentation strategies compared to standard baselines.

Graph coarsening reduces the size of a graph while preserving certain properties. Most existing methods preserve either spectral or spatial characteristics. Recent research shows that topology-preserving coarsening methods maintain GNN performance on coarsened graphs but suffer from exponential time complexity. To address these problems, we propose Scalable Topology-Preserving Graph Coarsening (STPGC) by introducing the concepts of graph strong collapse and graph edge collapse extended from algebraic topology. STPGC comprises three new algorithms, GStrongCollapse, GEdgeCollapse, and NeighborhoodConing, based on these two concepts, which eliminate dominated nodes and edges while rigorously preserving topological features. We further prove that STPGC preserves the GNN receptive field and develop approximate algorithms to accelerate GNN training. Experiments on node classification with GNNs demonstrate the efficiency and effectiveness of STPGC.

Causal softmax attention is the algorithmic foundation of modern large language models. Inspired by linear attention, recent work has sought to enhance it by incorporating forget gates. However, these efforts, such as FoX, have been limited to coarse, scalar gates. While fine-grained, element-wise gates are shown to be more effective than scalar ones in linear attention, their direct integration into softmax attention is non-trivial due to algebraic constraints. In this work, we introduce *Fine-grained Forgetting Transformer* (*FiX*), a novel architecture that successfully enables element-wise forget gates in softmax attention. Our core insight is that the softmax denominator becomes mathematically redundant under a subsequent RMSNorm layer, allowing us to reformulate the forgetting mechanism as a direct element-wise multiplication on the value vectors. This formulation makes FiX the first positional encoding applied to value-output (VO) pairs, designed to be complementary to existing query-key (QK) encodings like RoPE. We systematically address implementation challenges including numerical precision, computational efficiency, and inference memory consumption. Extensive experiments show *FiX* achieves lower training loss and superior performance on both short-text common sense benchmarks and long-context tasks, opening a new path for building more powerful transformers. Our code is available at https://github.com/AlayaDB-AI/FiX.