Artículos de Investigación en IA Diarios

GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Details

LLaMo: Large Language Model-based Molecular Graph Assistant

Adaptive Length Image Tokenization via Recurrent Allocation

Zebra-Llama: A Context-Aware Large Language Model for Democratizing Rare Disease Knowledge

DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution

Controlling Language and Diffusion Models by Transporting Activations

Inference Optimal VLMs Need Only One Visual Token but Larger Models

DreamPolish: Domain Score Distillation With Progressive Geometry Generation

Correlation of Object Detection Performance with Visual Saliency and Depth Estimation

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Sample-Efficient Alignment for LLMs