Related papers: Subspace Optimization for Backpropagation-Free Con…

Ensuring neural networks adhere to domain-specific constraints is crucial for addressing safety and trustworthiness while also enhancing inference accuracy. Despite the nonlinear nature of most real-world tasks, the majority of existing…

In this paper, we propose a framework for efficient Source-Free Domain Adaptation (SFDA) in the context of time-series, focusing on enhancing both parameter efficiency and data-sample utilization. Our approach introduces an improved…

Predicting the behavior of complex systems is critical in many scientific and engineering domains, and hinges on the model's ability to capture their underlying dynamics. Existing methods encode the intrinsic dynamics of high-dimensional…

Real-world deployment often exposes models to distribution shifts, making test-time adaptation (TTA) critical for robustness. Yet most TTA methods are unfriendly to edge deployment, as they rely on backpropagation, activation buffering, or…

Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectories that score well yet are locally inconsistent with the environment dynamics, resulting in brittle…

The full approximation storage (FAS) scheme is a widely used multigrid method for nonlinear problems. In this paper, a new framework to design and analyze FAS-like schemes for convex optimization problems is developed. The new method, the…

As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…

Audio is a fundamental modality for analyzing speech, music, and environmental sounds. Although pretrained audio models have significantly advanced audio understanding, they remain fragile in real-world settings where data distributions…

Sparse Inverse Covariance Estimation (SICE) is useful in many practical data analyses. Recovering the connectivity, non-connectivity graph of covariates is classified amongst the most important data mining and learning problems. In this…

Inference-time steering enables pretrained diffusion/flow models to be adapted to new tasks without retraining. A widely used approach is the ratio-of-densities method, which defines a time-indexed target path by reweighting…

A recent series of works has shown that initialization-free BA can be achieved using pseudo Object Space Error (pOSE) as a surrogate objective. The initial reconstruction-step optimizes an objective where all terms are projectively…

Sparse neural networks are becoming increasingly important as the field seeks to improve the performance of existing models by scaling them up, while simultaneously trying to reduce power consumption and computational footprint.…

Constructing valid and informative conformal prediction regions for multi-dimensional outputs remains a fundamental challenge. While conformal prediction provides finite-sample, distribution-free coverage guarantees, its practical…

In this paper we present FASE (Fast Asynchronous Systems Evaluation), a tool for evaluating worst-case efficiency of asynchronous systems. This tool implements some well-established results in the setting of a timed CCS-like process…

Source-free domain adaptation has become popular because of its practical usefulness and no need to access source data. However, the adaptation process still takes a considerable amount of time and is predominantly based on optimization…

We propose SPARC, a lightweight continual learning framework for large language models (LLMs) that enables efficient task adaptation through prompt tuning in a lower-dimensional space. By leveraging principal component analysis (PCA), we…

Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining…

Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit…

Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test-Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches…

Large-scale deep learning models impose substantial communication overh ead in distributed training, particularly in bandwidth-constrained or heterogeneous clo ud-edge environments. Conventional synchronous or fixed-compression techniques o…