User profiles for Lijun Yu

Lijun Yu

Google DeepMind
Verified email at google.com
Cited by 1624

Climate drives global soil carbon sequestration and crop yield changes under conservation agriculture

W Sun, JG Canadell, L Yu, L Yu, W Zhang… - Global change …, 2020 - Wiley Online Library
Conservation agriculture has been shown to have multiple benefits for soils, crop yield and
the environment, and consequently, no‐till, the central practice of conservation agriculture, …

ultralytics/yolov5: v3. 0

…, A Hogan, L Diaconu, J Poznanski, L Yu… - …, 2020 - ui.adsabs.harvard.edu
Breaking Changes This release does not contain breaking changes. Bug Fixes Hyperparameter
evolution fixed, tutorial added (https://github. com/ultralytics/yolov5/issues/607) Added …

Methane uptake in global forest and grassland soils from 1981 to 2010

L Yu, Y Huang, W Zhang, T Li, W Sun - Science of the Total Environment, 2017 - Elsevier
Methane (CH 4 ) is one of the most potent greenhouse gases. Although forest and grassland
soils generally consume atmospheric CH 4 , the quantities and spatiotemporal changes in …

ultralytics/yolov5: v3. 1-bug fixes and performance improvements

…, L Diaconu, F Ingham, J Poznanski, J Fang, L Yu… - …, 2020 - ui.adsabs.harvard.edu
This release aggregates various minor bug fixes and performance improvements since the
main v3. 0 release and incorporates PyTorch 1.7. 0 compatibility updates. v3. 1 models share …

Magvit: Masked generative video transformer

L Yu, Y Cheng, K Sohn, J Lezama… - Proceedings of the …, 2023 - openaccess.thecvf.com
We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video
synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into …

Photorealistic video generation with diffusion models

A Gupta, L Yu, K Sohn, X Gu, M Hahn, FF Li… - … on Computer Vision, 2024 - Springer
We present WALT, a diffusion transformer for photorealistic video generation from text
prompts. Our approach has two key design decisions. First, we use a causal encoder to jointly …

Videopoet: A large language model for zero-shot video generation

D Kondratyuk, L Yu, X Gu, J Lezama, J Huang… - arXiv preprint arXiv …, 2023 - arxiv.org
We present VideoPoet, a language model capable of synthesizing high-quality video, with
matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-…

Theoretical evaluation of corrosion inhibition performance of imidazoline compounds with different hydrophilic groups

J Zhang, G Qiao, S Hu, Y Yan, Z Ren, L Yu - Corrosion Science, 2011 - Elsevier
Corrosion inhibition performance of four 1-R-2-undecyl-imidazoline compounds (RCH 2
COOH (A), CH 2 CH 2 OH (B), CH 2 CH 2 NH 2 (C) and H (D)) for carbon steel was evaluated …

Spae: Semantic pyramid autoencoder for multimodal generation with frozen llms

L Yu, Y Cheng, Z Wang, V Kumar… - Advances in …, 2023 - proceedings.neurips.cc
In this work, we introduce Semantic Pyramid AutoEncoder (SPAE) for enabling frozen LLMs
to perform both understanding and generation tasks involving non-linguistic modalities such …

Probiotic potential of Bacillus velezensis JW: antimicrobial activity against fish pathogenic bacteria and immune enhancement effects on Carassius auratus

Y Yi, Z Zhang, F Zhao, H Liu, L Yu, J Zha… - Fish & shellfish …, 2018 - Elsevier
This study evaluated the probiotic potential of B. velezensis JW through experimental and
genomic analysis approaches. Strain JW showed antimicrobial activity against a broad range …