Welcome to the DLER website.

Welcome to the Deep Learning Efficiency Research (DLER) team at NVIDIA Research led by Dr. Pavlo Molchanov.

Founded in 2023, we are a vibrant and dynamic research lab. Many of our team members have been with NVIDIA for over five years. We operate under the umbrella of the Learning and Perception Research (LPR) group, led by Dr. Jan Kautz.

Our mission is to drive advancements in the efficiency of deep learning technologies, focusing on reducing memory footprint, minimizing inference latency, and lowering energy consumption.

We are particularly interested in:

  • Exploring applications of Large Language Models (LLMs) and Multi-Modal Language Models.
  • Enhancing post-training model optimization through techniques such as compression, sparsity, quantization, and Neural Architecture Search (NAS).
  • Designing novel and efficient architectures.
  • Dynamic and adaptive model inference
  • Developing innovative training paradigms


We are actively seeking exceptional deep learning researchers. Explore opportunities at the NVIDIA Careers website or reach out directly to our team members via email.

News

June 2024

Congratulations to Shizhe Diao for winning the Best Demo Paper Award and Outstanding Paper award at NAACL 2024.

June 2024

Shizhe Diao joins the group. Welcome!

June 2024

Members of our group are attending CVPR’24 and presenting RADIO and VILA.

May 2024

Flextron and DoRA are accepted to ICML’24 as Oral.

May 2024

Members of the group are attending ICLR’24 and presenting FasterViT and AdaSAP.

April 2024

Peter Belcak joins the group. Welcome!

March 2024

Xin Dong joins the group. Welcome!

February 2024

Our paper, FasterViT, was accepted to ICLR’24.

... see all News