3 papers
cs.LG2026
Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
Cristian Hinostroza, Rodrigo Toro Icarte, Christ Devia +4
Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more interpretable and optimized arc…
cs.LG2026
Seeing to Generalize: How Visual Data Corrects Binding Shortcuts
Nicolas Buzeta, Felipe del Rio, Cristian Hinostroza +3
Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform…
cs.AI2025
Extending NGU to Multi-Agent RL: A Preliminary Study
Juan Hernandez, Diego Fernández, Manuel Cifuentes +2
The Never Give Up (NGU) algorithm has proven effective in reinforcement learning tasks with sparse rewards by combining episodic novelty and intrinsic motivation. In this work, we…