8 papers
Limits of Spatial Imagery Reasoning in Frontier LLM Models
Sergio Y. Hayashi, Nina S. T. Hirata
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet they struggle with spatial tasks that require mental simulation, such as mental rotation. This…
Uncovering Latent Connections in Indigenous Heritage: Semantic Pipelines for Cultural Preservation in Brazil
Luis Vitor Zerkowski, Nina S. T. Hirata
Indigenous communities face ongoing challenges in preserving their cultural heritage, particularly in the face of systemic marginalization and urban development. In Brazil, the Mus…
LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
Gabriel J. Perin, Runjin Chen, Xuxi Chen +3
Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding…
Fine-Tuning Video-Text Contrastive Model for Primate Behavior Retrieval from Unlabeled Raw Videos
Giulio Cesare Mastrocinque Santo, PatrÃcia Izar, Irene Delval +2
Video recordings of nonhuman primates in their natural habitat are a common source for studying their behavior in the wild. We fine-tune pre-trained video-text foundational models…
Extracting and Understanding the Superficial Knowledge in Alignment
Runjin Chen, Gabriel Jacob Perin, Xuxi Chen +5
Alignment of large language models (LLMs) with human values and preferences, often achieved through fine-tuning based on human feedback, is essential for ensuring safe and responsi…
Efficient License Plate Recognition in Videos Using Visual Rhythm and Accumulative Line Analysis
Victor Nascimento Ribeiro, Nina S. T. Hirata
Video-based Automatic License Plate Recognition (ALPR) involves extracting vehicle license plate text information from video captures. Traditional systems typically rely heavily on…