Submitted by akhaliq 27 Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning · 7 authors 4
Submitted by akhaliq 13 GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest · 8 authors 555
Submitted by akhaliq 7 Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation · 4 authors
Submitted by akhaliq 7 One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention · 3 authors