Related papers: MAN++: Scaling Momentum Auxiliary Network for Supe…

In recent years, large language models (LLMs) have made remarkable progress, with model optimization primarily relying on gradient-based optimizers such as Adam. However, these gradient-based methods impose stringent hardware requirements,…

The recently proposed optimization algorithm for deep neural networks Sharpness Aware Minimization (SAM) suggests perturbing parameters before gradient calculation by a gradient ascent step to guide the optimization into parameter space…

Recently, self-supervised Masked Autoencoders (MAE) have attracted unprecedented attention for their impressive representation learning ability. However, the pretext task, Masked Image Modeling (MIM), reconstructs the missing local patches,…

Despite considerable theoretical progress in the training of neural networks viewed as a multi-agent system of neurons, particularly concerning biological plausibility and decentralized training, their applicability to real-world problems…

Reinforcement learning (RL) has emerged as a powerful paradigm for achieving online agile navigation with quadrotors. Despite this success, policies trained via standard RL typically fail to generalize across significant dynamic variations,…

This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understanding with low-level texture generation to achieve…

In this paper, we present a novel framework for enhancing the performance of Quanvolutional Neural Networks (QuNNs) by introducing trainable quanvolutional layers and addressing the critical challenges associated with them. Traditional…

We develop new algorithms for simultaneous learning of multiple tasks (e.g., image classification, depth estimation), and for adapting to unseen task/domain distributions within those high-level tasks (e.g., different environments). First,…

Combining the strengths of model-based iterative algorithms and data-driven deep learning solutions, deep unrolling networks (DuNets) have become a popular tool to solve inverse imaging problems. While DuNets have been successfully applied…

This paper presents a matching network to establish point correspondence between images. We propose a Multi-Arm Network (MAN) to learn region overlap and depth, which can greatly improve the keypoint matching robustness while bringing…

Real-world video restoration is plagued by complex degradations from motion coupled with dynamically varying exposure - a key challenge largely overlooked by prior works and a common artifact of auto-exposure or low-light capture. We…

Traditional end-to-end deep learning models often enhance feature representation and overall performance by increasing the depth and complexity of the network during training. However, this approach inevitably introduces issues of parameter…

Recent progress in Machine Unlearning (MU) has introduced solutions for the selective removal of private or sensitive information encoded within deep neural networks. Nonetheless, MU for Multimodal Large Language Models (MLLMs) remains in…

In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images. Given the lack of ground truth data, most deep learning-based methods carry out supervised training in a reduced-resolution domain.…

Training a deep neural network requires a large amount of single-task data and involves a long time-consuming optimization phase. This is not scalable to complex, realistic environments with new unexpected changes. Humans can perform fast…

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored…

Training deep neural networks typically relies on backpropagating high dimensional error signals a computationally intensive process with little evidence supporting its implementation in the brain. However, since most tasks involve…

Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attention. Recent LA models such as Mamba2 and GDN interpret linear recurrences as…

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…