Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
【DL輪読会】Emergent temporal abstractions in autoregressive models enable hierarchical re more
Category:
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
【DL輪読会】DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos by @De more
“Ctrl-World: A Controllable Generative World Model for Robot Manipulation”
【DL輪読会】"Ctrl-World: A Controllable Generative World Model for Robot Manipulation more
“COSMOS POLICY: FINE-TUNING VIDEO MODELS FOR VISUOMOTOR CONTROL AND PLANNING”
【DL輪読会】"COSMOS POLICY: FINE-TUNING VIDEO MODELS FOR VISUOMOTOR CONTROL AND PLANN more
AutoQVLA: Not All Channels Are Equal in Vision-Language-Action Model’s Quantization
【DL輪読会】AutoQVLA: Not All Channels Are Equal in Vision-Language-Action Model's Qu more
mHC: Manifold-Constrained Hyper-Connections
https://www.docswell.com/s/DeepLearning2023/K9MJDM-2026-02-09-104805
Reasoning Models Generate Societies of Thought
https://www.docswell.com/s/DeepLearning2023/ZLVW63-2026-02-05-105236
Self-Adapting Language Models(SEAL)
【DL輪読会】Self-Adapting Language Models(SEAL) by @DeepLearning2023
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
【DL輪読会】1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal- more
SOP: A Scalable Online Post-Training System for Vision-Language-Action Models
【DL輪読会】SOP: A Scalable Online Post-Training System for Vision-Language-Action Models more