カテゴリー: seminar
Learning to Theorize the World from Observation
【DL輪読会】Learning to Theorize the World from Observation by @DeepLearning2023
LaST₀: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
【DL輪読会】LaST₀: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Act more
Improving Robotic Generalist Policies via Flow Reversal Steering
【DL輪読会】Improving Robotic Generalist Policies via Flow Reversal Steering by @DeepLearn more
CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
【DL輪読会】CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Mani more
SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation
【DL輪読会】SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manip more
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
【DL輪読会】Interpretability in the Wild: a Circuit for Indirect Object Identification in more
The Topological Trouble With Transform
【DL輪読会】The Topological Trouble With Transformers by @DeepLearning2023
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens | alphaXiv
【DL輪読会】A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tok more
Flow-OPD: On-Policy Distillation for Flow Matching Models
【DL輪読会】Flow-OPD: On-Policy Distillation for Flow Matching Models by @DeepLearning2023