M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation

no code implementations • 30 Jan 2024 • Fotios Lygerakis, Vedant Dave, Elmar Rueckert

One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities.

reinforcement-learning Reinforcement Learning (RL) +3

Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training

no code implementations • 22 Jan 2024 • Vedant Dave, Fotios Lygerakis, Elmar Rueckert

In evaluating our methodology, we focus on two distinct tasks: material classification and grasping success prediction.

Contrastive Learning Material Classification +1

CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse

1 code implementation • 6 Sep 2023 • Fotios Lygerakis, Elmar Rueckert

The Variational Autoencoder (VAE) is known to suffer from the phenomenon of \textit{posterior collapse}, where the latent representations generated by the model become independent of the inputs.

Sequential Late Fusion Technique for Multi-modal Sentiment Analysis

no code implementations • 22 Jun 2021 • Debapriya Banerjee, Fotios Lygerakis, Fillia Makedon

Multi-modal sentiment analysis plays an important role for providing better interactive experiences to users.

Sentiment Analysis