Learning a Thousand Tasks in a Day
【DL輪読会】Learning a Thousand Tasks in a Day by @DeepLearning2023
投稿者: OKUMURA Rika
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
【DL輪読会】Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgett more
Seeing without Pixels: Perception from Camera Trajectories, CVPR 2026
【DL輪読会】Seeing without Pixels: Perception from Camera Trajectories, CVPR 2026 by @Deep more
Building a Multiplayer Video World Model in Minecraft
【DL輪読会】Building a Multiplayer Video World Model in Minecraft by @DeepLearning2023
A Step Toward World Models: A Survey on Robotic Manipulation
【DL輪読会】A Step Toward World Models: A Survey on Robotic Manipulation by @DeepLearning2 more
Synthetic continued pretraining
【DL輪読会】Synthetic continued pretraining by @DeepLearning2023
Self-Improving VLM Judges Without Human Annotation
【DL輪読会】Self-Improving VLM Judges Without Human Annotation by @DeepLearning2023