Forget About Catastrophic Forgetting: Google’s Continual HyperTransformer Enables Efficient Continual Few-Shot Learning https://
syncedreview.com/2023/01/24/for
get-about-catastrophic-forgetting-googles-continual-hypertransformer-enables-efficient-continual-few-shot-learning/
…
@jiqizhixin
-
Google’s Continual HyperTransformer Solves Catastrophic Forgetting Problem
By
–
-
Tracr: DeepMind’s Interpretability Tool Compiling Code to Transformers
By
–
Meet Tracr: DeepMind & ETH Zurich’s Novel Interpretability Tool Compiles Human-Readable Code to Transformers’ Weights
-
BERT-Style Pretraining on Convnets With Sparse Masked Modelling
By
–
BERT-Style Pretraining on Convnets? Peking U, ByteDance & Oxford U’s Sparse Masked Modelling With Hierarchy Leads the Way https://
syncedreview.com/2023/01/19/ber
t-style-pretraining-on-convnets-peking-u-bytedance-oxford-us-sparse-masked-modelling-with-hierarchy-leads-the-way/
… -
Memory-Augmented LLMs Achieve Computational Universality
By
–
Google Brain & Alberta U Paper Confirms the Computational Universality of Memory-Augmented Large Language Models https://
syncedreview.com/2023/01/18/goo
gle-brain-alberta-u-paper-confirms-the-computational-universality-of-memory-augmented-large-language-models/
… -
CMU DensePose WiFi: Affordable Human Sensing Technology
By
–
CMU’s DensePose From WiFi: An Affordable, Accessible and Secure Approach to Human Sensing
-
Absci’s Generative AI Advances De Novo Antibody Design
By
–
Absci’s Generative AI Approach Opens a Promising New Path for De Novo Antibody Design
-
DeepMind Connects Gradient Meta-Learning with Convex Optimization
By
–
DeepMind Explores the Connection Between Gradient-Based Meta-Learning and Convex Optimization
-
Microsoft Neural Codec Models Generate Personalized Speech From 3-Second Sample
By
–
Microsoft’s Neural Codec Language Models Synthesize High-Quality Personalized Speech From a 3-Second Sample https://
syncedreview.com/2023/01/11/mic
rosofts-neural-codec-language-models-synthesize-high-quality-personalized-speech-from-a-3-second-sample/
… -
Baidu Strategy for AI-Enhanced Creative Innovation
By
–
Baidu Create 2022 Forum Details Strategy for Next-Level AI-Enhanced Creativity via Feedback-Driven Innovation https://
syncedreview.com/2023/01/10/bai
du-create-2022-forum-details-strategy-for-next-level-ai-enhanced-creativity-via-feedback-driven-innovation/
… -
Google’s Masked Transformers Achieve SOTA Text-To-Image Performance
By
–
Google’s Masked Generative Transformers Achieve SOTA Text-To-Image Performance With Improved Efficiency https://
syncedreview.com/2023/01/09/goo
gles-masked-generative-transformers-achieve-sota-text-to-image-performance-with-improved-efficiency/
…