Constant Field of View Display Size Effects on First-Person Aiming Time

Under constant display field of view, FPS game aiming performance improves with display size, resulting in 3% faster aiming time comparing 13 and 26 inches diagonal.

Parsimony: Enabling SIMD/Vector Programming in Standard Compiler Flows

Achieving peak throughput on modern CPUs requires maximizing the use of single-instruction, multiple-data (SIMD) or vector compute units. Single-program, multiple-data (SPMD) programming models are an effective way to use high-level programming languages to target these ISAs. Unfortunately, many SPMD frameworks have evolved to have either overly restrictive language specifications or under-specified programming models, and this has slowed the widescale adoption of SPMD-style programming.

Tianye Li

Tianye Li joined NVIDIA Research as a Research Scientist in 2023. His research interest is in computer vision and computer graphics, especially in capturing, modeling, understanding dynamic humans. He is also interested in 3D/4D reconstruction and photorealistic rendering of generic scenes and objects. He obtained his Ph.D. in Computer Science from University of Southern California (USC), where he was advised by Prof. Hao Li and Prof. Randall Hill, Jr. He was a research scientist at Epic Games, and interned at MPI for Intelligent Systems, Snap Research, and Facebook/Meta Reality Labs.

Maximilian Igl

Yao Lu (Jason)

I am a distinguished research scientist at NVResearch. My current research interest is efficient Large Language Model (LLM) and Vision Language model (VLM). Before joining NVidia, I was a TLM at Google Deepmind where I worked on reinforcement learning, imitation learning on embodied AI. I co-led "SayCan", "RT-1", "RT-2", "RT-X" etc. that have been featured extensively by media, such as New York Times, Washington Post, Forbes, Reuters, TechCrunch, The WIRED, etc.

Wen-Hao Liu

Wen-Hao Liu, received his Ph.D. degree in Computer Science from National Chiao Tung University, Taiwan in 2013. His research interests include routing, placement, clock synthesis, logic synthesis, and 3D-IC in electronic design automation (EDA) field. Wen-Hao has published more than 40 papers and 15 patents in this field, and he has served on the technical program committee of DAC, ICCAD, ISPD, and ASPDAC. Currently, Wen-Hao works at Nvidia Research as a Principal Research Scientist to explore the solutions for advanced VLSI-related challenges.

Juan Gomez Luna

Graph Neural Networks for Enhanced Decoding of Quantum LDPC Codes

In this work, we propose a fully differentiable iterative decoder for quantum low-density parity-check (LDPC) codes. The proposed algorithm is composed of classical belief propagation (BP) decoding stages and intermediate graph neural network (GNN) layers. Both component decoders are defined over the same sparse decoding graph enabling a seamless integration and scalability to large codes.

A Neural Receiver for 5G NR Multi-user MIMO

We introduce a neural network (NN)-based multiuser multiple-input multiple-output (MU-MIMO) receiver with 5G New Radio (5G NR) physical uplink shared channel (PUSCH) compatibility. The NN architecture is based on convolution layers to exploit the time and frequency correlation of the channel and a graph neural network (GNN) to handle multiple users. The proposed architecture adapts to an arbitrary number of sub-carriers and supports a varying number of multiple-input multiple-output (MIMO) layers and users without the need for any retraining.

Efficient Transformer Inference with Statically Structured Sparse Attention

Self-attention matrices of Transformers are often highly sparse because the relevant context of each token is typically limited to just a few other tokens in the sequence. To reduce the computational burden of self-attention on Transformer inference, we propose static, structured, sparse attention masks that split attention matrices into dense regions, skipping computations outside these regions while reducing computations inside these regions.

Subscribe to