Papers by Brais Martinez

4 papers
More Images, More Problems? A Controlled Analysis of VLM Failure Modes. (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluations of large vision language models lack a comprehensive analysis of their weaknesses and causes.
Approach: They propose a new benchmark to evaluate multi-image capabilities of Large Vision Language Models.
Outcome: The proposed model outperforms existing benchmarks on multi-image models.
Graph Guided Question Answer Generation for Procedural Question-Answering (2024.eacl-long)

Copied to clipboard

Challenge: a new method for question-answer generation from procedural text is sub-optimal for training QA models.
Approach: They propose a method for generating exhaustive and high-quality training data from procedural text . they use procedural data to represent each step and the overall flow of the procedure as graphs .
Outcome: The proposed method outperforms existing methods on task-specific question answering tasks.
Efficient Vision-Language pre-training via domain-specific learning for human activities (2024.emnlp-main)

Copied to clipboard

Challenge: Current vision-language models owe their success to large-scale pretraining on web-collected data.
Approach: They propose a domain-aligned pretraining strategy that aligns the downstream tasks to the downstream domain without additional data collection.
Outcome: The proposed method outperforms existing models on large-scale vision-language training datasets while preserving generalist knowledge.
MobileQuant: Mobile-friendly Quantization for On-device Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have revolutionized language processing, but deployment on edge devices is costly in terms of memory, computation and energy.
Approach: They propose to reduce the number of bits used to represent weights and activations . they propose to use 8-bit activations to enable LLMs to fully exploit mobile-friendly hardware .
Outcome: The proposed method reduces the number of bits used to represent weights and activations . 8-bit activations are attractive for on-device deployment as they would exploit mobile-friendly hardware .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations