佐藤なつ | Deep Learning JP - Part 4

GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images

Contrastive Learning as Goal-Conditioned Reinforcement Learning

Hierarchical Text-Conditional Image Generation with CLIP Latents

DayDreamer: World Models for Physical Robot Learning

Prompting Decision Transformer for Few-Shot Policy Generalization

Diffusion Model 関連研究

Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks

Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers

An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Variable Bitrate Neural Fields

4 / 7« 先頭 «...2 345 6...»最後 »