Mechanistic Interpretability for AI Safety: A Review
【DL輪読会】Mechanistic Interpretability for AI Safety: A Review by @DeepLearning2023
投稿者: riyo.ono
Imagine yourself: Tuning-Free Personalized Image Generation
【DL輪読会】Imagine yourself: Tuning-Free Personalized Image Generation by @DeepLearning20 more
Improving Text Embeddings with Large Language Models
【DL輪読会】Improving Text Embeddings with Large Language Models by @DeepLearning2023
Training-Free Diffusion Models Alignment with Sampling Demons
【DL輪読会】 Training-Free Diffusion Models Alignment with Sampling Demons by @DeepLearnin more
Do Differentiable Simulators Give Better Policy Gradients?
【DL輪読会】 Do Differentiable Simulators Give Better Policy Gradients? by @DeepLearning20 more
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
【DL輪読会】DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantize more
1 RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization (ACL 2024) + An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models (2024)
【DL輪読会】RomanSetu: Efficiently unlocking multilingual capabilities of Large Language M more
Denoising Diffusion Bridge Models
【DL輪読会】Denoising Diffusion Bridge Models by @DeepLearning2023