Related papers: Subspace Optimization for Backpropagation-Free Con…

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Inefficient driving behaviors, such as overly conservative yielding, remain a key obstacle to deployment of autonomous vehicles (AVs). Instantaneous driving efficiency metrics are crucial for self-driving decision-making because they affect…

Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend on backpropagation (BP), which incurs substantial memory overhead and makes them difficult…

Transferability estimation aims to provide heuristics for quantifying how suitable a pre-trained model is for a specific downstream task, without fine-tuning them all. Prior studies have revealed that well-trained models exhibit the…

Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients…

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial…

Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods…

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…

Continual fine-tuning aims to adapt a pre-trained backbone to new tasks sequentially while preserving performance on earlier tasks whose data are no longer available. Existing approaches fall into two categories which include input- and…

Continuous learning seeks to perform the learning on the data that arrives from time to time. While prior works have demonstrated several possible solutions, these approaches require excessive training time as well as memory usage. This is…

Distribution shifts between training and test data are inevitable over the lifecycle of a deployed model, leading to performance decay. Adapting a model on test samples can help mitigate this drop in performance. However, most test-time…

This paper introduces Locally Adaptive Neural Context Estimation (LANCE), a novel extension for overfitted image compression (OIC) frameworks like Cool-Chic. While traditional OIC methods rely on lightweight autoregressive networks with…

We propose a model-agnostic, progressive test-time energy adaptation approach for medical image segmentation. Maintaining model performance across diverse medical datasets is challenging, as distribution shifts arise from inconsistent…

Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by the out-of-distribution (OOD) extrapolation problem. Existing approaches typically…

Typical methods for unsupervised text style transfer often rely on two key ingredients: 1) seeking the explicit disentanglement of the content and the attributes, and 2) troublesome adversarial learning. In this paper, we show that neither…

Sample-efficient domain adaptation is an open problem in robotics. In this paper, we present affine transport -- a variant of optimal transport, which models the mapping between state transition distributions between the source and target…

Despite impressive performance, deep neural networks require significant memory and computation costs, prohibiting their application in resource-constrained scenarios. Sparse training is one of the most common techniques to reduce these…

We propose Amortized Posterior Sampling (APS), a novel variational inference approach for efficient posterior sampling in inverse problems. Our method trains a conditional flow model to minimize the divergence between the variational…

We focus on the challenge of finding a diverse collection of quality solutions on complex continuous domains. While quality diver-sity (QD) algorithms like Novelty Search with Local Competition (NSLC) and MAP-Elites are designed to generate…

Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target domain by transferring knowledge from labeled source domain with domain shift. Most of the existing UDA methods try to mitigate the adverse impact induced by the shift…