ICML 2026 论文列表

Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e.g., images) can guide a (smaller) student model building on another type of data (e.g., text/audio). Existing CMKD methods often require paired multi-modal data with aligned semantics, but obtaining such paired data are often costly and impractical. To mitigate this limitation, we develop a new CMKD framework for the more challenging setting where paired data are unavailable. In particular, we establish a cross-modal distributional relationship between teacher and student models which reveals two fundamental quantities governing effective distillation: feature alignment and label alignment. These quantities characterize semantic discrepancy between modalities at the levels of representation and prediction distributions, respectively. Motivated by this insight, we propose a principled framework, with theoretical guarantees, that enables effective cross-modal knowledge distillation by aligning distributions rather than individual samples. Extensive experiments across a wide range of multimodal benchmarks show that our framework is highly effective in both unpaired and paired data settings, improving significantly over prior work.

Large language models are typically optimized for accuracy and, therefore, will guess even when uncertain about their predictions. This problem becomes especially pronounced when the model is fine-tuned on small datasets, which often causes overfitting and results in a tendency toward miscalibration. In this work, we introduce Bayesian-LoRA, which reformulates the deterministic LoRA update as a probabilistic low-rank representation inspired by Sparse Gaussian Processes (SGP). We identify a structural isomorphism between LoRA's factorization and Kronecker-factored SGP posteriors, and show that LoRA emerges as a limiting case when posterior uncertainty collapses. We conduct extensive experiments on various LLM architectures across commonsense reasoning, language modeling, and mathematical reasoning benchmarks. With only approximately 0.42M additional parameters and ${\approx}1.2{\times}$ training cost relative to standard LoRA, Bayesian-LoRA significantly improves calibration across models from 7B up to 30B, achieving up to 84\% Expected Calibration Error (ECE) and 76\% Negative Log-Likelihood (NLL) reduction while maintaining competitive accuracy for both in-distribution and out-of-distribution (OoD) evaluations.

Recent advances in audio deepfake detection have been driven by increasingly large speech foundation models and growing amounts of synthetic data. Despite strong benchmark performance, it remains unclear how detection capability scales with model capacity and training data under realistic deployment conditions involving distribution shift, signal corruption, and unseen synthesis pipelines. In this work, we present the first systematic study of scaling laws in post-training audio deepfake detection, focusing on fine-tuning regimes rather than large-scale pretraining. Using a controlled family of speech foundation models with shared architecture and pretraining, we analyze how detection performance, robustness, and generalization evolve as a function of model size and training data scale. Our results reveal a fundamental asymmetry between performance scaling and robustness scaling in audio deepfake detection, suggesting increasing model capacity alone is insufficient for achieving reliable real-world generalization.

Targeted instruction tuning requires selecting pertinent samples from massive mixed *candidate datasets* guided by a small *reference dataset* reflecting the desired capability, yet efficiently identifying high-quality data amidst noise remains challenging. To address this, we propose **TarGATE** (**Tar**get-aware **GATE**s, a simple yet effective data selection framework that leverages the model's inherent data understanding. TarGATE computes a token-level Information Retention Ratio (**IRR**) to scale the output of the feed-forward network, where the instance-level average IRR serves as a quantitative metric for data quality. To align gates' preferences with the target task, we employ a joint optimization strategy utilizing the reference set and a subset of candidate data, which encourages the gates to assign higher IRRs to reference-aligned data while suppressing low-quality samples. Extensive experiments across noisy and real-world scenarios demonstrate that TarGATE outperforms related baselines. Furthermore, TarGATE exhibits superior computational efficiency and strong cross-model transferability, enabling smaller selector to effectively curate high-quality fine-tuning data for larger foundation models. The code is available at [here](https://github.com/FGinfinite/TarGATE).

Transformers enable in-context learning (ICL) for rapid, gradient-free adaptation in time series forecasting, yet most ICL-style approaches rely on tabularized, hand-crafted features, while end-to-end sequence models lack inference-time adaptation. We bridge this gap with a unified framework, Baguan-TS, which integrates the raw-sequence representation learning with ICL, instantiated by a 3D Transformer that attends jointly over temporal, variable, and context axes. To make this high-capacity model practical, we tackle two key hurdles: (i) calibration and training stability, improved with a feature-agnostic, target-space retrieval-based local calibration; and (ii) output oversmoothing, mitigated via context-overfitting strategy. On public benchmark with covariates, Baguan-TS consistently outperforms established baselines, achieving the highest win rate and significant reductions in both point and probabilistic forecasting metrics. Further evaluations across diverse real-world energy datasets demonstrate its robustness, yielding substantial improvements.

Fine-tuning large pre-trained models on a target distribution often improves in-distribution (ID) accuracy, but at the cost of out-of-distribution (OOD) robustness as representations specialize to the fine-tuning data. Weight-space ensembling methods, such as Model Soups, mitigate this effect by averaging multiple checkpoints, but they are computationally prohibitive, requiring the training and storage of dozens of fine-tuned models. In this paper, we introduce MonoSoup, a simple, data-free, hyperparameter-free, post-hoc method that achieves a strong ID–OOD balance using _only a single_ checkpoint. Our method applies Singular Value Decomposition (SVD) to each layer’s update and decomposes it into high-energy directions that capture task-specific adaptation and low-energy directions that introduce noise but may still encode residual signals useful for robustness. MonoSoup then uses entropy-based effective rank to automatically re-weigh these components with layer-wise coefficients that account for the spectral and geometric structure of the model. Experiments on CLIP models fine-tuned on ImageNet and evaluated under natural distribution shifts, as well as on Qwen language models tested on mathematical reasoning and multiple-choice benchmarks, show that this plug-and-play approach is a practical and effective alternative to multi-checkpoint methods, retaining much of their benefits without their computational overhead.

Instruction data curation is central to improving the instruction-following ability of large language models. However, existing approaches often struggle to simultaneously maintain data quality, diversity, and distributional consistency, largely because they do not explicitly distinguish semantic redundancy from quality defects and rely on coarse-grained modeling of instruction data quality. To address this issue, we propose Cure-SFT, a coarse-to-fine, diagnostic-guided method for instruction data curation that explicitly disentangles semantic redundancy from quality defects. Specifically, Cure-SFT removes redundant samples via stratified semantic-geometric sampling, applies teacher models for diagnostic triage, and performs targeted defect remediation on fixable samples. Our experiments show that Cure-SFT can surpass full-data instruction tuning using only 10% of the data budget. Moreover, Cure-SFT consistently outperforms strong selection-based and rewriting-based baselines across data budgets, supporting the effectiveness of diagnostic-guided data curation.

Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurrence structure and producing incoherent label sets where dominant concepts suppress weaker but compatible labels. We introduce Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that injects label dependency without tuning the backbone. BCP views zero-shot logits as a proxy for marginal posteriors under a fixed image-text likelihood and attributes shift-induced errors mainly to a mismatched label prior. For each test image, it selects a high-confidence anchor label and applies an anchor-conditioned Bayesian refinement. This update is closed-form in logit space and admits a pointwise mutual information (PMI) interpretation, explicitly promoting compatible labels and suppressing incompatible ones. BCP operates without target annotations by estimating anchor-conditioned priors online from the unlabeled test stream via lightweight second-order co-occurrence statistics, adding negligible overhead beyond a single forward pass. Across standard multi-label benchmarks and multiple CLIP backbones, BCP consistently outperforms strong TTA baselines, e.g., improving RN50 average mAP from 57.31 to 69.22 and ViT-B/16 from 62.61 to 71.79.

Real-world datasets across image and text domains are often characterized by skewed class distributions and noisy annotations, which jointly degrade model performance, particularly on minority classes. Among existing solutions, active learning offers an effective and efficient paradigm by selectively querying the most informative and balanced samples for annotation. We propose an innovative active learning framework that mitigates class imbalance and selects the most informative samples to annotate. Leveraging foundation model priors, our algorithm enables imbalance-aware co-decisions between foundation model and small model to tackle noisy and imbalanced labels across various domains. We introduce the first study to systematically explore active learning under the dual challenges of label noise and class imbalance across image and text domains. Extensive experiments on imbalanced datasets demonstrate that our method achieves substantial annotation savings—over 50\% compared to the best active learning baseline—while preserving performance and robustness to label noise.

Electroencephalography foundation models (EEG-FMs) have advanced brain signal analysis, but the lack of standardized evaluation benchmarks impedes model comparison and scientific progress. Current evaluations rely on inconsistent protocols that render cross-model comparisons unreliable, while a lack of diagnostic analyses obscures the internal mechanisms driving transfer efficiency and scaling behaviors. To address this, we introduce **EEG-FM-Bench**, a unified system for the standardized evaluation of EEG-FMs. The benchmark integrates 14 datasets across 10 paradigms and incorporates diverse experimental settings, including multiple fine-tuning strategies, task organizations, and classifier configurations, supported by tools for gradient and representation analysis. Our experiments and analysis reveal several critical insights: (1) multi-task learning often acts as a useful regularizer that mitigates overfitting in data-scarce EEG contexts, although negative transfer can arise under specific task paradigms; (2) pre-training efficiency is currently limited by gradient conflicts between reconstruction objectives and downstream tasks; (3) under released checkpoints and a matched downstream protocol, model or data scale alone does not fully explain transfer performance, while objective alignment, adaptation compatibility, and EEG-specific design appear to be important factors. This benchmark enables fair comparison and reproducible analysis, providing a step toward fairer comparison and more interpretable analysis of EEG-FMs. Code is available at https://github.com/xw1216/EEG-FM-Bench.

Full fine-tuning of large language models (LLMs) incurs prohibitive computational and storage costs. Parameter-efficient fine-tuning (PEFT) addresses this limitation, with Low-Rank Adaptation (LoRA) gaining widespread adoption due to its simplicity and zero inference overhead. However, LoRA and its variants typically rely on uniform rank allocation or a single importance metric such as gradient magnitude or output sensitivity to guide rank distribution. This approach fails to recognize that gradient magnitude and output contribution are decoupled properties, leading to suboptimal allocation where critical layers are under-provisioned while less important ones waste capacity. To address this challenge, we propose COBRA, a principled framework integrating dual importance factors for adaptive rank allocation. COBRA operates in three stages: (1) layer conductance attribution quantifies each layer's contribution via path-integral attribution; (2) dual-factor aggregation combines contribution with adaptation demand, producing the Task-Adaptive Layer Conductance (TA-LC) distribution; and (3) Bayesian rank allocation translates this distribution into optimal heterogeneous ranks via variational optimization. Layer conductance provides layer-level interpretability by explicitly quantifying how much each layer contributes to predictions without redundancy, directly aligning with the granularity of rank allocation decisions and enabling principled cross-layer comparison for rank distribution. Experiments across diverse architectures and tasks demonstrate that COBRA consistently outperforms existing methods, achieving up to 1.6 points improvement on GLUE and a 6.6\% average MSE reduction in high-rank regression regimes under comparable parameter budgets.

*Adaptability* has been regarded as a central feature in the foundation models, enabling them to effectively acclimate to unseen downstream tasks. Parameter-efficient fine-tuning methods such as celebrated LoRA facilitate efficient adaptation of large foundation models using labeled, high-quality and generally scarce task data. To mitigate data scarcity in fine-tuning of foundation models, we propose to leverage *task similarity* across downstream users. Intuitively, users with similar tasks must be able to assist each other in boosting the effective fine-tuning data size. We propose *Collaborative Low-Rank Adaptation*, or CoLoRA, which exploits task similarity to collaboratively and efficiently fine-tune personalized foundation models. The main idea in CoLoRA is to train one shared adapter capturing underlying task similarities across all tasks, and personalized adapters tailored to user-specific tasks. We theoretically study CoLoRA on heterogeneous linear regression and provide provable guarantees for ground truth recovery. We also conduct several natural language experiments with varying task similarity, which further demonstrate that when trained together with similar tasks, individual performances are significantly boosted.

Recent work has identified a counterintuitive phenomenon termed “Hyperfitting", where fine-tuning Large Language Models (LLMs) to near-zero training loss on small datasets surprisingly enhances open-ended generation quality and mitigates repetition in greedy decoding. While effective, the underlying mechanism remains poorly understood, with the extremely low-entropy output distributions suggesting a potential equivalence to simple temperature scaling. In this work, we demonstrate that this phenomenon is fundamentally distinct from distribution sharpening; entropy-matched control experiments reveal that temperature scaling fails to replicate the diversity gains of hyperfitting. Furthermore, we falsify the hypothesis of static vocabulary reweighting, showing through ablation studies that hyperfitting relies on a dynamic, context-dependent rank reordering mechanism. Layer-wise analysis localizes this effect to a “Terminal Expansion" in the final transformer block, where a substantial geometric expansion of the feature space ($\Delta \mathrm{Dim} \approx +80.8$) facilitates the promotion of deep-tail tokens. Additionally, we introduce \textbf{Late-Stage LoRA}, a targeted fine-tuning strategy that updates only the final 5 layers, yielding robust generation with minimal parameter updates.

Foundation flow-matching (FM) models promise universal priors for solving inverse problems (IPs); yet today, they trail behind domain-specific and even untrained priors. \emph{How can we unlock their potential?} We introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. For evaluation, we consider both simple image restoration tasks and scientific IPs with a few similar samples---where the prohibitive cost of data collection and model training hinders the development of domain-specific generative models. Our superior experimental results confirm the effectiveness of FMPlug. Overall, FMPlug paves the way for making foundation FM models practical, reusable priors for IPs, especially scientific ones with few similar samples.

In the pre-training-fine-tuning paradigm, pre-trained encoders have become high-value intellectual property (IP) due to their immense training costs, necessitating robust protection. Existing fingerprinting or watermarking methods typically rely on pre-defined samples and labels, or require intrusive modifications to the training process. However, downstream fine-tuning can significantly alter an encoder's representation and label space, thereby destroying the label consistency of existing methods and rendering them ineffective. Consequently, it is both challenging and urgent to provide a downstream-agnostic, black-box ownership verification mechanism for pre-trained encoders. To address this, we propose a downstream-agnostic, label-only fingerprinting method that leverages Adversarial Shifting to construct stable fingerprint clusters in the encoder’s latent space. By exploiting the inherent output consistency of these clusters, our method remains effective regardless of the specific downstream task or label mapping. Extensive experiments demonstrate that our method maintains superior robustness and stealthiness across various downstream tasks and category scales, providing a practical and reliable IP protection scheme for high-value pre-trained encoders.

Real-world multivariate time series are inherently in flux: different variables evolve asynchronously and interact in complex, time-varying ways, yet accurate forecasting requires these dispersed signals to converge into a single unified prediction. This structural mismatch between dynamic, heterogeneous inputs and a unified forecasting objective poses a fundamental challenge for building general-purpose multivariate forecasting models, especially in zero-shot and large-scale settings. To this end, inspired by the idea that ``\emph{all rivers run into the sea}'', we propose \textbf{ConFlux}, a \emph{general-purpose foundation model for multivariate time-series forecasting} by learning to adaptively integrate cross-channel information under a unified forecasting objective. Specifically, ConFlux first reorders variables to reduce cross-variable entanglement, then aggregates adjacent variables into compact patches that can be processed by a Vision Transformer-style architecture. This design shortens the effective context, reduces attention complexity, and provides a unified token representation for pre-training and downstream tasks. Experiments on 25 public datasets show that ConFlux achieves state-of-the-art performance in zero-shot, fine-tuning, and from-scratch settings, while offering faster inference and lower memory usage.

Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data---however, there remains unutilized potential in the form of recording metadata readily available within these community-driven data hubs. In this work, we explore the use of metadata---such as location and time---as auxiliary supervision signals, allowing the model to leverage species-metadata correlations in its learned representation. Auxiliary metadata losses provide additional information beyond vocalizations alone that can encourage a richer, more robust representation that generalizes better to species distribution and acoustic domain shifts---important challenges for deployment in real-world passive acoustic monitoring (PAM) settings. We introduce MetaPerch, a new foundation model that achieves strong species identification performance across multiple challenging domains and present an extensive empirical study of the effects of 9 diverse metadata sources on 17 bioacoustic datasets.

Existing Parameter-Efficient Fine-Tuning (PEFT) methods are fundamentally constrained by a static allocation paradigm, which overlooks the model's evolving optimization priorities during training. To address this, we introduce Dynamic Adaptive Fine-tuning (DAF), a novel framework that periodically evaluates and reconfigures the trainable structure based on a context-aware decoupled sensitivity analysis. DAF employs a Rebuild-and-Refocus strategy to preserve learned knowledge by freezing outdated modules while decisively reallocating the parameter budget to newly identified critical regions. Extensive experiments on challenging vision benchmarks demonstrate that DAF significantly outperforms mainstream static PEFT methods and achieves superior performance and efficiency, particularly under extreme parameter budgets. Our work fundamentally challenges the static nature of the field, offering a more intelligent and efficient paradigm for adapting large pretrained models. The code is available at https://github.com/E-green11/DAF.

Single-cell foundation models trained on millions of cells can learn gene expression patterns across diverse contexts. However, for predicting genetic perturbation effects they often underperform simple regression models. We hypothesize two potential limitations: targets defined on dropout-prone absolute expression, and pretraining objectives that reconstruct static co-expression rather than encoding how genes co-regulate under expression changes. We introduce $\textbf{scDEBART}$, a perturbation-specific pretraining framework that predicts log fold-changes (logFC) conditioned on basal expression, thereby learning how gene sets co-vary across expression-change contexts at scale. To obtain reliable estimates of expression change under technical sparsity, we compute logFC from scVI-denoised expression and restrict pretraining to genes with robust detection. Pretrained on 6.28 million expression-change profiles from 66.6 million human cells and fine-tuned on five Perturb-seq datasets, scDEBART achieves mean enrichment factor (EF) of 11.96, 4-7$\times$ higher than scGPT and GEARS (mean EF 1.74-2.99), and 71.4\% top-1 accuracy for reverse perturbation identification compared to near-zero accuracy for prior models. In cross-modal transfer to drug perturbations (SCIPLEX), the model shows dose-dependent improvement in directional alignment (cosine similarity 0.04→0.30) with above-random DEG enrichment (EF 2.91-4.32), suggesting partial transfer of learned regulatory patterns across modalities. Overall, these results indicate that large-scale pretraining on scVI-denoised expression-change profiles provides a useful inductive bias for perturbation prediction.