AI 연구 논문 데일리

Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

PERL: Parameter Efficient Reinforcement Learning from Human Feedback

Larimar: Large Language Models with Episodic Memory Control

SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion

Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images

LightIt: Illumination Modeling and Control for Diffusion Models

Generic 3D Diffusion Adapter Using Controlled Multi-View Editing

MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data

VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding

DiPaCo: Distributed Path Composition

LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models