The paper introduces Right In-Place (RiP) convolution, a memory‑efficient strategy that corrects and generalizes previous in‑place convolution formulations to arbitrary stride, dilation, padding, and rectangular kernels. RiP aligns each layer’s input and output within a shared workspace, enabling safe, row‑major access with minimal memory overhead. Experiments on 10,000 random layers and 84 layers from 25 architectures show no corruption, matching or improving on existing herringbone workspaces while reducing memory usage by up to 24.8% and lowering peak activation memory on Raspberry Pi Pico MCUs by 12.5–33.3% without affecting cycle counts.
By Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye Eigbe
arXiv:2607. 14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.
By A. C. Opus, J. Q. Lu
arXiv:2610.23328v1 Announce Type: new
Abstract: Real-time inference on small devices needs low activation memory without extra latency, which makes operator order the most valuable memory lever: it i...
By Ivan Fomin, Ivan Koryabkin, Boris Sheludko
arXiv:2607. 01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation.
By Tasnim Shahriar
arXiv:2512. 06208v3 Announce Type: replace-cross Abstract: Inference of standard convolutional neural networks (CNNs) on FPGAs often incurs high latency and a long initiation interval due to the deep nested loops required to densely convolve every input pixel regardless of its feature value.
By Ho Fung Tsoi, Dylan Rankin, Vladimir Loncar, Philip Harris
arXiv:2505. 03303v3 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.
By Tasnim Shahriar
arXiv:2505. 03303v4 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.
By Tasnim Shahriar
arXiv:2609.21058v1 Announce Type: cross
Abstract: Language models can now write GPU kernels that outperform PyTorch. We evaluate five model configurations on KernelBench level 1 and find that a front...
By Gaurav Agarwal, Ashish Garg, Isha Singhal
arXiv:2607. 19456v1 Announce Type: cross Abstract: We derive four memory-optimal inference artifacts for transformer attention using the Mathematics of Arrays (MoA), each following directly from the forward-pass Denotational Normal Form (DNF) of with the query-row index fixed to the current decode step.
By Lenore Mulin, Gaetan Hains
arXiv:2608. 06177v1 Announce Type: new Abstract: Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference.
By Quentin Luquet de Saint-Germain, Massil Ait Abdeslam, Jean Pierre David
FORGE is a forward‑only test‑time adaptation technique designed for integer‑only vision models running on microcontrollers. It restores batch‑normalization statistics after BN folding by re‑normalizing each convolution’s per‑channel output using only forward‑pass estimates, enabling adaptation on deployed, folded integer models. The method achieves accuracy gains comparable to gradient‑based TENT, requires adapting only a few layers, works with single‑sample streaming, and has been validated on an ESP32‑S3 with minimal energy and latency overhead.
By Muhammad Rehan, Haider Ali, Muhammad Ali Munir, Moaz Amjad
arXiv:2608.20725v1 Announce Type: cross
Abstract: Convolution is a principal computational bottleneck in deep neural networks, and its efficiency depends on tight integration between algorithms and G...
By Xiang Fu, Jixiang Ma, Xinpeng Zhang, Peng Zhao, Shuai Lu, Xu Tony Liu