カテゴリー: papers
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
【DL輪読会】LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from P more
PlayWorld: Learning Robot World Models from Autonomous Play
【DL輪読会】PlayWorld: Learning Robot World Models from Autonomous Play by @DeepLearning20 more
π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
【DL輪読会】π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabiliti more
SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation
【DL輪読会】SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation by @Deep more
Shaping Shared Languages: Human and Large Language Models’ Inductive Biases in Emergent Communication
【DL輪読会】Shaping Shared Languages: Human and Large Language Models' Inductive Bias more
Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
【DL輪読会】Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Mo more
Learning a Thousand Tasks in a Day
【DL輪読会】Learning a Thousand Tasks in a Day by @DeepLearning2023
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