LiNR: Model Based Neural Retrieval on GPUs at LinkedIn

no code implementations • 18 Jul 2024 • Fedor Borisyuk, Qingquan Song, Mingzhou Zhou, Ganesh Parameswaran, Madhu Arun, Siva Popuri, Tugrul Bingol, Zhuotao Pei, Kuang-Hsuan Lee, Lu Zheng, Qizhan Shao, Ali Naqvi, Sen Zhou, Aman Gupta

We envisage LiNR as a step towards integrating retrieval and ranking into a single GPU model, simplifying complex infrastructures and enabling end-to-end optimization of the entire differentiable infrastructure through gradient descent.

Attribute Quantization +1

BERT for Large-scale Video Segment Classification with Test-time Augmentation

no code implementations • 2 Dec 2019 • Tianqi Liu, Qizhan Shao

We firstpre-train the model on the 4M training video-level data, andthen fine-tune the model on 237K annotated video segment-level data.

General Classification Video Understanding