Juan C Leon Alcazar

Transformers from Compressed Representations

Motion-Aware Concept Alignment for Consistent Video Editing

MoDA: Modulation Adapter for Fine-Grained Visual Understanding in Instructional MLLMs

EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models

CoLaP: Contrastive Learning with Adaptive Prompts for Continual Learning

Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models

Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration