Joao Monteiro

GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

PairBench: Are Vision-Language Models Reliable at Comparing What They See?

BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Training Universal Text Encoders with Pair Relevance Classification Loss

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones