TrilinearCIM enables complete in-memory Transformer attention computation via DG-FeFET three-operand MAC without runtime NVM reprogramming, delivering up to 46.6% energy reduction and 20.4% latency improvement on BERT and ViT benchmarks at 37.3% area cost.
Vaqf: Fully automatic software-hardware co-design frame- work for low-bit vision transformer,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.AR 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
FlexViT is an FPGA accelerator for edge ViTs that unifies FC and conv layers on a single GEMM engine with dual-mode dataflow and depth-first tiling, delivering up to 1.40x end-to-end speedup versus CPU.
DxPTA is a constraint-aware architecture search algorithm for photonic transformer accelerators that achieves up to 15.2x faster exploration than exhaustive search while meeting area, power, energy, and latency constraints for DeiT and BERT models.
citing papers explorer
-
Trilinear Compute-in-Memory Architecture for Energy-Efficient Transformer Acceleration
TrilinearCIM enables complete in-memory Transformer attention computation via DG-FeFET three-operand MAC without runtime NVM reprogramming, delivering up to 46.6% energy reduction and 20.4% latency improvement on BERT and ViT benchmarks at 37.3% area cost.
-
FlexViT: A Flexible FPGA-based Accelerator for Edge Vision Transformers
FlexViT is an FPGA accelerator for edge ViTs that unifies FC and conv layers on a single GEMM engine with dual-mode dataflow and depth-first tiling, delivering up to 1.40x end-to-end speedup versus CPU.
-
DxPTA: An Architecture Design Space Exploration with Optical Dataflow-guided Strategy for HW/SW Co-Design of Photonic Transformer Accelerators
DxPTA is a constraint-aware architecture search algorithm for photonic transformer accelerators that achieves up to 15.2x faster exploration than exhaustive search while meeting area, power, energy, and latency constraints for DeiT and BERT models.