Wed Jul 13 2022
Tue Jul 12 2022

Language Models (Mostly) Know What They Know

Natural Language Processing

Studies whether LMs can evaluate the validity of their own claims and predict which questions they will be able to answer correctly.

Provides insights on self-evaluation of language models on open-ended sampling tasks and predicting the probability of knowing the answer to a question, which could be used for training more honest models.

Inner Monologue: Embodied Reasoning through Planning with Language Models

Robotics
Simulated and real table top rearrangement tasks
Long-horizon mobile manipulation tasks in a kitchen environment

Closed-loop language feedback significantly improves high-level instruction completion.

Recommends using closed-loop language feedback to improve high-level instruction completion in robotic control scenarios.

HelixFold: An Efficient Implementation of AlphaFold2 using PaddlePaddle

Protein Structure Prediction
Life Science
CASP14 and CAMEO datasets

HelixFold saves costs about half the training time of original AlphaFold2 and OpenFold when using hybrid parallelism.

Suggests using HelixFold, implemented using PaddlePaddle, to improve training and inference speed and reduce memory consumption for protein structure prediction, which could accelerate the development of life science.

Mon Jul 11 2022
Thu Jul 07 2022
Sun Jul 03 2022
Thu Jun 30 2022