ICML 2025 Papers

Online Continual Learning (OCL) models continuously adapt to nonstationary data streams, usually without task information. These settings are complex and many traditional CL methods fail, while online methods (mainly replay-based) suffer from instabilities after the task shift. To address this issue, we formalize replay-based OCL as a second-order online joint optimization with explicit KL-divergence constraints on replay data. We propose Online Curvature-Aware Replay (OCAR) to solve the problem: a method that leverages second-order information of the loss using a K-FAC approximation of the Fisher Information Matrix (FIM) to precondition the gradient. The FIM acts as a stabilizer to prevent forgetting while also accelerating the optimization in non-interfering directions. We show how to adapt the estimation of the FIM to a continual setting, stabilizing second-order optimization for non-iid data, uncovering the role of the Tikhonov damping in the stability-plasticity tradeoff. Empirical results show that OCAR outperforms state-of-the-art methods in continual metrics, achieving higher average accuracy throughout the training process in three different benchmarks.

The goal of offline reinforcement learning (RL) is to extract the best possible policy from the previously collected dataset considering the *out-of-distribution* (OOD) sample issue. Offline model-based RL (MBRL) is a captivating solution capable of alleviating such issues through a \textit{state-action transition augmentation} with a learned dynamic model. Unfortunately, offline MBRL methods have been observed to fail in sparse rewarded and long-horizon environments for a long time. In this work, we propose a novel MBRL method, dubbed Temporal Distance-Aware Transition Augmentation (TempDATA), that generates additional transitions in a geometrically structured representation space, instead of state space. For comprehending long-horizon behaviors efficiently, our main idea is to learn state abstraction, which captures a *temporal distance* from both *trajectory and transition levels* of state space. Our experiments empirically confirm that TempDATA outperforms previous offline MBRL methods and achieves matching or surpassing the performance of diffusion-based trajectory augmentation and goal-conditioned RL on the D4RL AntMaze, FrankaKitchen, CALVIN, and pixel-based FrankaKitchen.

Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustering method for FL, **FedGWC** (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution, allowing training of a more robust and personalized model on the identified clusters. **FedGWC** identifies homogeneous clusters by transforming individual empirical losses to model client interactions with a Gaussian reward mechanism. Additionally, we introduce the *Wasserstein Adjusted Score*, a new clustering metric for FL to evaluate cluster cohesion with respect to the individual class distribution. Our experiments on benchmark datasets show that **FedGWC** outperforms existing FL algorithms in cluster quality and classification accuracy, validating the efficacy of our approach.

Self-supervised contrastive learning has emerged as a powerful tool in machine learning and computer vision to learn meaningful representations from unlabeled data. Meanwhile, its empirical success has encouraged many theoretical studies to reveal the learning mechanisms. However, in the existing theoretical research, the role of data augmentation is still under-exploited, especially the effects of specific augmentation types. To fill in the blank, we for the first time propose an augmentation-aware error bound for self-supervised contrastive learning, showing that the supervised risk is bounded not only by the unsupervised risk, but also explicitly by a trade-off induced by data augmentation. Then, under a novel semantic label assumption, we discuss how certain augmentation methods affect the error bound. Lastly, we conduct both pixel- and representation-level experiments to verify our proposed theoretical results.

Sharpness-Aware Minimization (SAM) has been demonstrated to improve the generalization performance of overparameterized models by seeking flat minima on the loss landscape through optimizing model parameters that incur the largest loss within a neighborhood. Nevertheless, such min-max formulations are computationally challenging especially when the problem is highly non-convex. Additionally, focusing only on the worst-case local solution while ignoring potentially many other local solutions may be suboptimal when searching for flat minima. In this work, we propose Tilted SAM (TSAM), a smoothed generalization of SAM inspired by exponential tilting that effectively assigns higher priority to local solutions that incur larger losses. TSAM is parameterized by a tilt hyperparameter $t$ and reduces to SAM as $t$ approaches infinity. We show that TSAM is smoother than SAM and thus easier to optimize, and it explicitly favors flatter minima. We develop algorithms motivated by the discretization of Hamiltonian dynamics to solve TSAM. Empirically, TSAM arrives at flatter local minima and results in superior test performance than the baselines of SAM and ERM across a range of image and text tasks.

Electronic health records (EHR) aggregate extensive data critical for advancing patient care and refining intervention strategies. EHR data is essential for epidemiological study, more commonly referred to as cohort study, where patients with shared characteristics or similar diseases are analyzed over time. Unfortunately, existing studies on cohort modeling are limited, struggling to derive fine-grained cohorts or effectively utilize cohort information, which hinders their ability to uncover intrinsic relationships between cohorts. To this end, we propose NeuralCohort, a cohort-aware neural representation learning method that precisely segments patients into finer-grained cohorts via an innovative cohort contextualization mechanism and captures both intra- and inter-cohort information using a Biscale Cohort Learning Module. Designed as a plug-in, NeuralCohort integrates seamlessly with existing backbone models, enhancing their cohort analysis capabilities by infusing deep cohort insights into the representation learning processes. The effectiveness and generalizability of NeuralCohort are validated across extensive real-world EHR datasets. Experimental results demonstrate that NeuralCohort consistently improves the performance of various backbone models, achieving up to an 8.1% increase in AUROC.

Large language model inference is both memory-intensive and time-consuming, often requiring distributed algorithms to efficiently scale. Various model parallelism strategies are used in multi-gpu training and inference to partition computation across multiple devices, reducing memory load and computation time. However, using model parallelism necessitates communication of information between GPUs, which has been a major bottleneck and limits the gains obtained by scaling up the number of devices. We introduce Ladder Residual, a simple architectural modification applicable to all residual-based models that enables straightforward overlapping that effectively hides the latency of communication. **Our insight is that in addition to systems optimization, one can also redesign the model architecture to decouple communication from computation.** While Ladder Residual can allow communication-computation decoupling in conventional parallelism patterns, we focus on Tensor Parallelism in this paper, which is particularly bottlenecked by its heavy communication. For a Transformer model with 70B parameters, applying Ladder Residual to all its layers can achieve 29% end-to-end wall clock speed up at inference time with TP sharding over 8 devices. We refer the resulting Transformer model as the Ladder Transformer. We train a 1B and 3B Ladder Transformer from scratch and observe comparable performance to a standard dense transformer baseline. We also show that it is possible to convert parts of the Llama-3.1 8B model to our Ladder Residual architecture with minimal accuracy degradation by only retraining for 3B tokens.

Recent advances in Dynamic Sparse Training (DST) have pushed the frontier of sparse neural network training in structured and unstructured contexts, matching dense-model performance while drastically reducing parameter counts to facilitate model scaling. However, unstructured sparsity often fails to translate into practical speedups on modern hardware. To address this shortcoming, we propose DynaDiag, a novel structured sparse-to-sparse DST method that performs at par with unstructured sparsity. DynaDiag enforces a diagonal sparsity pattern throughout training and preserves sparse computation in forward and backward passes. We further leverage the diagonal structure to accelerate computation via a custom CUDA kernel, rendering the method hardware-friendly. Empirical evaluations on diverse neural architectures demonstrate that our method maintains accuracy on par with unstructured counterparts while benefiting from tangible computational gains. Notably, with 90\% sparse linear layers in ViTs, we observe up to a 3.13x speedup in online inference without sacrificing model performance and a 1.59x speedup in training on a GPU compared to equivalent unstructured layers.

Learning lighting adaptation is a crucial step in achieving good visual perception and supporting downstream vision tasks. Current research often addresses individual light-related challenges, such as high dynamic range imaging and exposure correction, in isolation. However, we identify shared fundamental properties across these tasks: i) different color channels have different light properties, and ii) the channel differences reflected in the spatial and frequency domains are different. Leveraging these insights, we introduce the channel-aware Learning Adaptive Lighting Network (LALNet), a multi-task framework designed to handle multiple light-related tasks efficiently. Specifically, LALNet incorporates color-separated features that highlight the unique light properties of each color channel, integrated with traditional color-mixed features by Light Guided Attention (LGA). The LGA utilizes color-separated features to guide color-mixed features focusing on channel differences and ensuring visual consistency across all channels. Additionally, LALNet employs dual domain channel modulation for generating color-separated features and a mixed channel modulation and light state space module for producing color-mixed features. Extensive experiments on four representative light-related tasks demonstrate that LALNet significantly outperforms state-of-the-art methods on benchmark tests and requires fewer computational resources. We provide an anonymous online demo at [LALNet](https://xxxxxx2025.github.io/LALNet/).

Model merging based on task vectors, i.e., the parameter differences between fine-tuned models and a shared base model, provides an efficient way to integrate multiple task-specific models into a multitask model without retraining. Recent works have endeavored to address the conflicts between task vectors, one of the significant challenges faced by model merging, through sparsification; however, two issues significantly limit their performance: *high parameter overlap* and *unbalanced weight distribution*. To address these issues, we propose a simple yet effective framework called **CABS** (Conflict-Aware and Balanced Sparsification), consisting of **C**onflict-**A**ware Sparsification (CA) and **B**alanced **S**parsification (BS). CA reduces parameter overlap by applying masks during sequential pruning, ensuring that each task vector retains distinct, non-overlapping parameters. BS leverages $n$:$m$ pruning to preserve critical weights while maintaining an even distribution across layers. Our comprehensive experiments demonstrate that CABS outperforms state-of-the-art methods across diverse tasks and model sizes.

Measuring the similarity between data points plays a vital role in lots of popular representation learning tasks such as metric learning and contrastive learning. Most existing approaches utilize point-level distances to learn the point-to-point similarity between pairwise instances. However, since the finite number of training data points cannot fully cover the whole sample space consisting of an infinite number of points, the generalizability of the learned distance is usually limited by the sample size. In this paper, we thus extend the conventional form of data point to the new form of data ball with a predictable volume, so that we can naturally generalize the existing point-level distance to a new volume-aware distance (VAD) which measures the field-to-field geometric similarity. The learned VAD not only takes into account the relationship between observed instances but also uncovers the similarity among those unsampled neighbors surrounding the training data. This practice significantly enriches the coverage of sample space and thus improves the model generalizability. Theoretically, we prove that VAD tightens the error bound of traditional similarity learning and preserves crucial topological properties. Experiments on multi-domain data demonstrate the superiority of VAD over existing approaches in both supervised and unsupervised tasks.

Developing models for protein-ligand interactions holds substantial significance for drug discovery. Supervised methods often failed due to the lack of labeled data for predicting the protein-ligand binding energy, like antibodies. Therefore, unsupervised approaches are urged to make full use of the unlabeled data. To tackle the problem, we propose an efficient, unsupervised protein-ligand binding energy prediction model via the conservation of energy (CEBind), which follows the physical laws. Specifically, given a protein-ligand complex, we randomly sample forces for each atom in the ligand. Then these forces are applied rigidly to the ligand to perturb its position, following the law of rigid body dynamics. Finally, CEBind predicts the energy of both the unperturbed complex and the perturbed complex. The energy gap between two complexes equals the work of the outer forces, following the law of conservation of energy. Extensive experiments are conducted on the unsupervised protein-ligand binding energy prediction benchmarks, comparing them with previous works. Empirical results and theoretic analysis demonstrate that CEBind is more efficient and outperforms previous unsupervised models on benchmarks.

Mesh-based 3D static analysis methods have recently emerged as efficient alternatives to traditional computational numerical solvers, significantly reducing computational costs and runtime for various physics-based analyses. However, these methods primarily focus on surface topology and geometry, often overlooking the inherent thickness of real-world 3D objects, which exhibits high correlations and similar behavior between opposing surfaces. This limitation arises from the disconnected nature of these surfaces and the absence of internal edge connections within the mesh. In this work, we propose a novel framework, the Thickness-aware E(3)-Equivariant 3D Mesh Neural Network (T-EMNN), that effectively integrates the thickness of 3D objects while maintaining the computational efficiency of surface meshes. Additionally, we introduce data-driven coordinates that encode spatial information while preserving E(3)-equivariance or invariance properties, ensuring consistent and robust analysis. Evaluations on a real-world industrial dataset demonstrate the superior performance of T-EMNN in accurately predicting node-level 3D deformations, effectively capturing thickness effects while maintaining computational efficiency.

N:M sparsity stands as a progressively important tool for DNN compression, achieving practical speedups by stipulating at most N non-zero components within M sequential weights. Unfortunately, most existing works identify the N:M sparse mask through dense backward propagation to update all weights, which incurs exorbitant training costs. In this paper, we introduce BAME, a method that maintains consistent sparsity throughout the N:M sparse training process. BAME perpetually keeps both sparse forward and backward propagation, while iteratively performing weight pruning-and-regrowing within designated weight blocks to tailor the N:M mask. These blocks are selected through a joint assessment based on accumulated mask oscillation frequency and expected loss reduction of mask adaptation, thereby ensuring stable and efficient identification of the optimal N:M mask. Our empirical results substantiate the effectiveness of BAME, illustrating it performs comparably to or better than previous works that fully maintaining dense backward propagation during training. For instance, BAME attains a 72.0% top-1 accuracy while training a 1:16 sparse ResNet-50 on ImageNet, eclipsing SR-STE by 0.5%, despite achieving 2.37 training FLOPs reduction. Code is released at \url{https://github.com/BAME-xmu/BAME}

Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representation using task latents, they often struggle with out-of-distribution (OOD) tasks. To address this, we propose Task-Aware Virtual Training (TAVT), a novel algorithm that accurately captures task characteristics for both training and OOD scenarios using metric-based representation learning. Our method successfully preserves task characteristics in virtual tasks and employs a state regularization technique to mitigate overestimation errors in state-varying environments. Numerical results demonstrate that TAVT significantly enhances generalization to OOD tasks across various MuJoCo and MetaWorld environments. Our code is available at https://github.com/JM-Kim-94/tavt.git.

Post-training quantization (PTQ) is a promising solution for deploying large language models (LLMs) on resource-constrained devices. Early methods developed for small-scale networks, such as ResNet, rely on gradient-based optimization, which becomes impractical for hyper-scale LLMs with billions of parameters. While recently proposed backpropagation-free or transformation-based methods alleviate this issue, they ignore inter-layer interactions or use the naive nearest-rounding-based quantized weight assignment to save the heavy computational cost of weight optimization. In this paper, we introduce a novel backpropagation-free PTQ algorithm that optimizes quantized weights by considering inter-layer dependencies. The key innovation is the development of attention-aware Hessian matrices that capture inter-layer interactions within the attention module. Extensive experiments demonstrate that our approach not only outperforms existing weight quantization methods but also shows good synergy with conventional methods to suppress activation outliers, leading to state-of-the-art weight-activation quantization performance. The code will be available at https://github.com/SamsungLabs/BoA.

Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. These architectures hold promise for streaming applications at the edge, but deployment in resource-constrained environments requires hardware-aware optimizations to minimize latency and energy consumption. Unstructured sparsity offers a compelling solution, enabling substantial reductions in compute and memory requirements--when accelerated by compatible hardware platforms. In this paper, we conduct a scaling study to investigate the Pareto front of performance and efficiency across inference compute budgets. We find that highly sparse linear RNNs *consistently* achieve better efficiency-performance trade-offs than dense baselines, with $2\times$ less compute and $36$\% less memory at iso-accuracy. Our models achieve state-of-the-art results on a real-time streaming task for audio denoising. By quantizing our sparse models to fixed-point arithmetic and deploying them on the Intel Loihi 2 neuromorphic chip for real-time processing, we translate model compression into tangible gains of $42\times$ lower latency and $149\times$ lower energy consumption compared to a dense model on an edge GPU. Our findings showcase the transformative potential of unstructured sparsity, paving the way for highly efficient recurrent neural networks in real-world, resource-constrained environments.

State space models are emerging as a dominant model class for sequence problems with many relying on the HiPPO framework to initialize their dynamics. However, HiPPO fundamentally assumes data to be noise-free; an assumption often violated in practice. We extend the HiPPO theory with measurement noise and derive an uncertainty-aware initialization for state space model dynamics. In our analysis, we interpret HiPPO as a linear stochastic control problem where the data enters as a noise-free control signal. We then reformulate the problem so that the data become noisy outputs of a latent system and arrive at an alternative dynamics initialization that infers the posterior of this latent system from the data without increasing runtime. Our experiments show that our initialization improves the resistance of state-space models to noise both at training and inference time.

Causal estimands can vary significantly depending on the relationship between outcomes in treatment and control groups, leading to wide partial identification (PI) intervals that impede decision making. Incorporating covariates can substantially tighten these bounds, but requires determining the range of PI over probability models consistent with the joint distributions of observed covariates and outcomes in treatment and control groups. This problem is known to be equivalent to a conditional optimal transport (COT) optimization task, which is more challenging than standard optimal transport (OT) due to the additional conditioning constraints. In this work, we study a tight relaxation of COT that effectively reduces it to standard OT, leveraging its well-established computational and theoretical foundations. Our relaxation incorporates covariate information and ensures narrower PI intervals for any value of the penalty parameter, while becoming asymptotically exact as a penalty increases to infinity. This approach preserves the benefits of covariate adjustment in PI and results in a data-driven estimator for the PI set that is easy to implement using existing OT packages. We analyze the convergence rate of our estimator and demonstrate the effectiveness of our approach through extensive simulations, highlighting its practical use and superior performance compared to existing methods.