https://www.docswell.com/s/DeepLearning2023/K6N2XW-2026-11-09-112813
【DL輪読会】Readout Bottleneck in Vision-Language Models by @DeepLearning2023
投稿者: risa.murata
“Multi-Agent LLM Systems: Do They Work, Which Structures Help, and Do They Beat a Single Agent?”
【DL輪読会】“Multi-Agent LLM Systems: Do They Work, Which Structures Help, and Do They Bea more
Native Video-Action Pretraining for Generalizable Robot Control
【DL輪読会】Native Video-Action Pretraining for Generalizable Robot Control by @DeepLearni more
Multi²: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments
【DL輪読会】Multi²: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Inte more
Humans and transformer LMs: Abstraction drives language learning
【DL輪読会】Humans and transformer LMs: Abstraction drives language learning by @DeepLearn more
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
【DL輪読会】Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players by @Deep more
Learning Latent Action World Models In The Wild
【DL輪読会】Learning Latent Action World Models In The Wild by @DeepLearning2023
ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
【DL輪読会】ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning more
TRINITY: An Evolved LLM Coordinator
【DL輪読会】TRINITY: An Evolved LLM Coordinator by @DeepLearning2023
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