runtime-adaptive

Tag

Cards List
#runtime-adaptive

TRINE: A Token-Aware, Runtime-Adaptive FPGA Inference Engine for Multimodal AI

arXiv cs.AI · 2026-06-01 Cached

TRINE is a single-bitstream FPGA accelerator and compiler for end-to-end multimodal inference, unifying diverse layers and incorporating runtime-adaptive compute modes, token pruning, and dependency-aware offloading, achieving up to 22.57x latency reduction over an RTX 4090 at 20-21W.

0 favorites 0 likes
#runtime-adaptive

FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence

arXiv cs.LG · 2026-05-25 Cached

FusionSense introduces a tri-stage near-sensor learning framework for multimodal edge intelligence that jointly reduces compute and communication by using fusion-aware filtering, achieving up to 33× energy savings and significant data-reduction gains on RGB-Depth/LiDAR tasks.

0 favorites 0 likes
← Back to home

Submit Feedback