2 papers
cs.LG2026
Sparse Competition during Training For the Emergence of Specialized Modules
Baptiste Rossigneux, Karim Haroun
Modularity in deep neural networks has been proposed as a means of improving both interpretability and training by promoting disentangled representations and reducing redundancy. I…
cs.CV2026
Clustering and Token Denoising for Faster and More Robust VLMs
Baptiste Rossigneux, Inna Kucher, Vincent Lorrain +1
Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing impressive result…