KI-Forschungspapiere Täglich

From Elements to Design: A Layered Approach for Automatic Graphic Design Composition

VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models

SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models

CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era

HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

The Superposition of Diffusion Models Using the Itô Density Estimator

1.58-bit FLUX

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging

Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey