”OMNIGROK: GROKKING BEYOND ALGORITHMIC DATA” ICRL2023
【DL輪読会】”OMNIGROK: GROKKING BEYOND ALGORITHMIC DATA” ICRL2023 by @DeepLearning2023
Author: Emma Nishioka
MoE-LLaVA: Mixture of Experts for LargeVision-Language Models
【DL輪読会】MoE-LLaVA: Mixture of Experts for Large Vision-Language Models by @DeepLearnin more
Generative Time Series Models with InterpretableLatent Processes for Complex Disease Trajectories(NIPS 2023)
【DL輪読会】Generative Time Series Models with InterpretableLatent Processes for Complex D more
Diffusion Models Without Attention
【DL輪読会】Diffusion Models Without Attention by @DeepLearning2023
Grokking Group Multiplication with Cosets
【DL輪読会】Grokking Group Multiplication with Cosets by @DeepLearning2023
In-Context Pretraining: Language Modeling Beyond Document Boundaries
【DL輪読会】In-Context Pretraining: Language Modeling Beyond Document Boundaries by @DeepL more
Don’t Get Too Technical with Me’:A Discourse Structure-Based Framework for Science Journalism
【DL輪読会】Don’t Get Too Technical with Me’:A Discourse Structure-Based Framework for Sci more
Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation
【DL輪読会】Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation by @Dee more
Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations
【DL輪読会】Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between more