From task structures to world models: what do LLMs know?
【DL輪読会】From task structures to world models: what do LLMs know? by @DeepLearning2023
Author: riyo.ono
Text2World: Benchmarking Large Language Models for Symbolic World Model Generation
【DL輪読会】Text2World: Benchmarking Large Language Models for Symbolic World Model Genera more
Comparison of Vision-Language-Action Models: Pi0, Pi0.5, and Gemini Robotics
【DL輪読会】 Comparison of Vision-Language-Action Models: Pi0, Pi0.5, and Gemini Robotics more
Training Strategies for Efficient Embodied Reasoning
【DL輪読会】 Training Strategies for Efficient Embodied Reasoning by @DeepLearning2023
Improving Vision-Language-Action Model with Online Reinforcement Learning
【輪読会】Improving Vision-Language-Action Model with Online Reinforcement Learning by @De more
Backtracking Improves Generation Safety
【DL輪読会】Backtracking Improves Generation Safety by @DeepLearning2023
MMQA: Evaluating LLMs with Multi-Table Multi- Hop Complex Questions
【DL輪読会】MMQA: Evaluating LLMs with Multi-Table Multi- Hop Complex Questions by @DeepLe more
Packing Input Frame Context in Next- Frame Prediction Models for Video Generation
【DL輪読会】Packing Input Frame Context in Next- Frame Prediction Models for Video Generat more
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
【DL輪読会】 Block Diffusion: Interpolating Between Autoregressive and Diffusion Language more
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
【DL輪読会】Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predi more