3 papers
cs.CL2024
QCQA: Quality and Capacity-aware grouped Query Attention
Vinay Joshi, Prashant Laddha, Shambhavi Sinha +2
Excessive memory requirements of key and value features (KV-cache) present significant challenges in the autoregressive inference of large language models (LLMs), restricting both…
cs.CV2021
Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusion
Anirud Thyagharajan, Benjamin Ummenhofer, Prashant Laddha +2
3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art seman…
cs.AR2020
AccSS3D: Accelerator for Spatially Sparse 3D DNNs
Om Ji Omer, Prashant Laddha, Gurpreet S Kalsi +6
Semantic understanding and completion of real world scenes is a foundational primitive of 3D Visual perception widely used in high-level applications such as robotics, medical imag…