Search Results for author:
Found 5 papers, 4 papers with code
Introducing v0.5 of the AI Safety Benchmark from MLCommons
We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0. 5 benchmark.
StarCoder: may the source be with you!
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.
Ranked #50 on
Code Generation
on MBPP
Exploiting Invariance in Training Deep Neural Networks
Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks.
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
Our training procedure builds on insights from recent video classification literature and uses a trainable 3D CNN to learn the visual features.
Ranked #5 on
Zero-Shot Action Recognition
on ActivityNet
Diverse mini-batch Active Learning
We study the problem of reducing the amount of labeled training data required to train supervised classification models.
