KI-Forschungspapiere Täglich

GenCA: A Text-conditioned Generative Model for Realistic and Drivable Codec Avatars

DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification

LLM-3D Print: Large Language Models To Monitor and Control 3D Printing

Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation

Writing in the Margins: Better Inference Pattern for Long Context Retrieval

Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing

Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation

Temporally-consistent 3D Reconstruction of Birds

Platypus: A Generalized Specialist Model for Reading Text in Various Forms

Text2SQL is Not Enough: Unifying AI and Databases with TAG

Diffusion Models Are Real-Time Game Engines

The Mamba in the Llama: Distilling and Accelerating Hybrid Models