KI-Forschungspapiere Täglich

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web

When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method

Training-Free Long-Context Scaling of Large Language Models

DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Model

Video as the New Language for Real-World Decision Making

Evaluating Very Long-Term Conversational Memory of LLM Agents

Towards Optimal Learning of Language Models

Sora Generates Videos with Stunning Geometrical Consistency

Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners

Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation

Disentangled 3D Scene Generation with Layout Learning

VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction