Related papers: Virtual Parameter Sharpening: Dynamic Low-Rank Per…

A novel numerical method for the estimation of large time-varying parameter (TVP) models is proposed. The updating and smoothing estimates of the TVP model are derived within the context of generalised linear least squares and through…

Vocal Percussion Transcription (VPT) is concerned with the automatic detection and classification of vocal percussion sound events, allowing music creators and producers to sketch drum lines on the fly. Classifier algorithms in VPT systems…

As the scale of vision models continues to grow, Visual Prompt Tuning (VPT) has emerged as a parameter-efficient transfer learning technique, noted for its superior performance compared to full fine-tuning. However, indiscriminately…

The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different…

Adapters are a parameter-efficient alternative to fine-tuning, which augment a frozen base network to learn new tasks. Yet, the inference of the adapted model is often slower than the corresponding fine-tuned model. To improve on this, we…

We propose a method for adaptive nonlinear sequential modeling of vector-time series data. Data is modeled as a nonlinear function of past values corrupted by noise, and the underlying non-linear function is assumed to be approximately…

Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts, such as small changes in object pose. We attribute this brittleness to trajectory…

Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class predictions with only image-level labels for training. To this end, previous methods adopt the common pipeline: they generate pseudo masks from class activation…

Recent advances in generative models have amplified the risk of malicious misuse of speech synthesis technologies, enabling adversaries to impersonate target speakers and access sensitive resources. Although speech deepfake detection has…

Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical…

Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known as prompts, which steer the frozen pretrained ViTs. Although VPT has…

Aligning Large Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are performant,…

Vision-Language-Action (VLA) models inherit strong priors from pretrained Vision-Language Models (VLMs), but naive fine-tuning often disrupts these representations and harms generalization. Existing fixes -- freezing modules or applying…

Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Action (VLA) model inference. However, existing acceleration…

Implicit neural representations have recently been extended to represent convolutional neural network weights via neural representation for neural networks, offering promising parameter compression benefits. However, standard multi-layer…

As robots are expected to perform increasingly diverse tasks, they must understand not only low-level actions but also the higher-level structure that determines how a task should unfold. Existing vision-language-action (VLA) models…

Entropy-based inference methods have gained traction for improving the reliability of Large Language Models (LLMs). However, many existing approaches, such as entropy minimization techniques, suffer from high computational overhead and fail…

This paper explores reinforcement learning (RL) policy robustness by systematically analyzing network parameters under internal and external stresses. \textcolor{black}{We apply synaptic filtering methods using high-pass, low-pass, and…

Post-hoc explanation methods attempt to make the inner workings of deep neural networks more interpretable. However, since a ground truth is in general lacking, local post-hoc interpretability methods, which assign importance scores to…

Nonlinear parameter-varying (NPV) systems are a class of nonlinear systems whose dynamics explicitly depend on time-varying external parameters, making them suitable for modeling real-world systems with dynamics variations. Traditional…