3 papers
cs.AR2026
A3C3: AI Algorithm and Accelerator Co-design, Co-search, and Co-generation
Selin Yildirim, Yingbing Huang, Deming Chen
We present a holistic methodology for artificial intelligence algorithm and accelerator co-design, co-search, and co-generation (A3C3), which jointly optimizes neural network archi…
cs.CV2026
CASCADE: Context-Aware Relaxation for Speculative Image Decoding
Selin Yildirim, Subhajit Dutta Chowdhury, Mohammad Mahdi Kamani +2
Autoregressive generation is a powerful approach for high-fidelity image synthesis, but it remains computationally demanding and slow even on the most advanced accelerators. While…
cs.AR2025
StreamTensor: Make Tensors Stream in Dataflow Accelerators for LLMs
Hanchen Ye, Deming Chen
Efficient execution of deep learning workloads on dataflow architectures is crucial for overcoming memory bottlenecks and maximizing performance. While streaming intermediate resul…