AI研究论文每日精选

LLM Agent Operating System

Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation

FlashFace: Human Image Personalization with High-fidelity Identity Preservation

SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

RakutenAI-7B: Extending Large Language Models for Japanese

TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models

VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation