Close

Presentation

<
Torr: Towards Brain-Inspired Task-Oriented Reasoning via Cache-Oriented Algorithm-Architecture Co-Design
SessionDesign for the Unpredictable: Resilience and Adaptation in AIoT
DescriptionTask-oriented object detection on CLIP enables open-vocabulary, prompt-driven semantics but dense alignment and memory traffic block real-time edge use. We propose TorR, a brain-inspired algorithm–architecture co-design that replaces CLIP-style dense matching with hyperdimensional associative reasoning and exploits temporal coherence. TorR combines HDC similarity, graph reasoning with query caching and delta updates, and a lane-scalable, precision-gated item memory with RT-30/RT-60 control. A 28 nm TorR accelerator delivers real-time detection with millijoule energy and competitive AP at orders-of-magnitude lower energy.
Authors
Hyunwoo Oh
University of California, Irvine
SungHeon Jeong
UCI
Suyeon Jang
University of California, Irvine
Hanning Chen
University of California, Irvine
Sanggeon Yun
University of California, Irvine
Tamoghno Das
University of California, Irvine
Mohsen Imani
University of California Irvine
Event Type
Research Manuscript
TimeTuesday, July 2811:50am - 12:03pm PDT
LocationMtg Room 202C
Next PresentationNext Presentation
Hyperlidar: Adaptive Post-Deployment LiDAR Segmentation via Hyperdimensional Computing
Similar Presentations
SLC-Based Real-Time Traffic Buffering with DRAM Row-Aware Write Back
Coordinated Clip-Wise Gradient Scheduling for Full-Chip ILT via Policy Learning
Adaptive Spiking Neural Networks for Real-Time Multi-Object Detection Tasks