Umberto Cappellazzo's picture

5 21 2

Umberto Cappellazzo

hisoka94

·

https://umbertocappellazzo.github.io/

AI & ML interests

Multimodal Large Language Models and audio-visual speech processing at @ Imperial College London.

Organizations

None yet

commented a paper 3 months ago

Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models

Paper • 2511.07253 • Published Nov 10, 2025 • 3 •

commented 2 papers 4 months ago

Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMS

Paper • 2510.22603 • Published Oct 26, 2025 • 3 •

MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition

Paper • 2510.04136 • Published Oct 5, 2025 • 4 •

commented a paper 9 months ago

Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach

Paper • 2505.14336 • Published May 20, 2025 • 3 •

commented a paper 11 months ago

Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs

Paper • 2503.06362 • Published Mar 9, 2025 • 3 •