Related papers: On the Pros and Cons of Momentum Encoder in Self-S…

This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to spatiotemporal representation learning from videos. We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels.…

Multimodal Large Language Models advance multimodal representation learning by acquiring transferable semantic embeddings, thereby substantially enhancing performance across a range of vision-language tasks, including cross-modal retrieval,…

Recently, wearable emotion recognition based on peripheral physiological signals has drawn massive attention due to its less invasive nature and its applicability in real-life scenarios. However, how to effectively fuse multimodal data…

Online monitoring remains an important requirement for a range of microsystems. The solution based on the injection of an actuating test stimulus into the bias structure of active devices holds great potential. This paper presents an…

Momentum-Aided Prompt Optimization (MAPO) enhances the efficiency and efficacy of prompt optimization for Large Language Models (LLMs). Building on ProTeGi, MAPO uses positive natural language "gradients" and a momentum-based extension to…

Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces significant memory overhead, which constrains scalability and computational efficiency. In…

Contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data. This technique requires a balanced mixture of two ingredients: positive (similar) and negative (dissimilar) samples. This is typically…

Motion estimation is one of the important procedures in the all video encoders. Most of the complexity of the video coder depends on the complexity of the motion estimation step. The original motion estimation algorithm has a remarkable…

Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations. Self-supervised learning helps but still struggles with intricate visual patterns in EM. To address this, we propose a…

Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio…

Designing a speech quality assessment (SQA) system for estimating mean-opinion-score (MOS) of multi-rate speech with varying sampling frequency (16-48 kHz) is a challenging task. The challenge arises due to the limited availability of a…

Self-supervised learning (SSL) has significantly advanced image representation learning, yet efficiency challenges persist, particularly with adversarial training. Many SSL methods require extensive epochs to achieve convergence, a demand…

Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. However, many existing methods treat frames independently in the…

The diagnostic value of electrocardiogram (ECG) lies in its dynamic characteristics, ranging from rhythm fluctuations to subtle waveform deformations that evolve across time and frequency domains. However, supervised ECG models tend to…

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

Semi-supervised learning (SSL) has become a promising direction for medical image segmentation, enabling models to learn from limited labeled data alongside abundant unlabeled samples. However, existing SSL approaches for multi-modal…

As an unsupervised feature representation paradigm, Self-Supervised Learning (SSL) uses the intrinsic structure of data to extract meaningful features without relying on manual annotation. Despite the success of SSL, there are still…

The use of deep neural networks in reinforcement learning (RL) often suffers from performance degradation as model size increases. While soft mixtures of experts (SoftMoEs) have recently shown promise in mitigating this issue for online RL,…

Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies. However, despite achieving state-of-the-art performance across various downstream vision…

Sparse autoencoders (SAEs) \citep{bricken2023monosemanticity,gao2024scalingevaluatingsparseautoencoders} rely on dictionary learning to extract interpretable features from neural networks at scale in an unsupervised manner, with…