Papers by Ignacio Cases

4 papers
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models (MLLMs) have advanced from perception tasks to complex multi-step reasoning.
Approach: They propose a framework that integrates reinforcement learning with verifiable rewards with process-level supervision through automatically collected rubric-based generative rewards.
Outcome: The proposed framework achieves state-of-the-art performance on six multimodal reasoning benchmarks and significantly improves reasoning faithfulness in dedicated evaluations.
Recursive Routing Networks: Learning to Compose Modules for Language Understanding (N19-1)

Copied to clipboard

Challenge: Recursive Routing Networks are modular, adaptable models that learn effectively in diverse environments.
Approach: They propose to apply Recursive Routing Networks (RRNs) to natural language understanding by integrating them into existing architectures and recurrent network hidden layers.
Outcome: The proposed model optimizes the parameters of the functions and the meta-learner decision-making component for routing inputs through those functions.
The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank (2022.emnlp-main)

Copied to clipboard

Challenge: Existing treebanks derived from text include only text and are based on single-modality texts.
Approach: They propose to use audio-visual transcripts and part of speech tags to create an English language treebank based on dialog in Hollywood movies.
Outcome: The proposed treebank is the 3rd largest UD English treebank and the only multimodal treebank in UD.
Posing Fair Generalization Tasks for Natural Language Inference (D19-1)

Copied to clipboard

Challenge: Existing evaluation methods for deep learning semantics rely on naturalistic corpora, but they often fail to support the kind of generalization we are asking for.
Approach: They define and motivate a formal notion of fairness for evaluations of deep learning models for semantics . they then apply it to natural language inference by constructing challenging but provably fair artificial datasets based on the results .
Outcome: The proposed evaluations show that standard neural models fail to generalize in the required ways and even these models do not solve the task perfectly.

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