HEAT introduces a fine‑tuning method that treats the number of iterations used to approximate nonlinearities in fully homomorphic encryption (FHE) as learnable parameters, allowing them to co‑adapt with model weights. By optimizing iteration counts per nonlinearity, HEAT reduces the required iterations, bootstraps, and overall latency for encrypted GPT‑2 decoding while improving decode agreement. The approach achieves a 3.1× reduction in iterations, a 1.6× reduction in bootstraps, and a 1.4× speed‑up in end‑to‑end latency without changing the model architecture or requiring retraining from scratch.
By Alessandro Zirilli, Davide Marincione, Evgenios M. Kornaropoulos, Giuseppe Ateniese, Emanuele Rodol\`a
arXiv:2607. 04819v1 Announce Type: new Abstract: Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlinear blocks.
By Ligong Han, Kai Xu, Hao Wang, Ruijiang Gao, Akash Srivastava
arXiv:2607. 29221v1 Announce Type: cross Abstract: We address the challenge of securely and efficiently outsourcing AI computations from a trusted but computationally weak client to an untrusted but powerful server, in the setting where the client holds both the input and the model, and the server must learn neither.
By James Hsin-yu Chiang, Sheila Zingg, Kari Kostiainen, Srdjan Capkun
arXiv:2606. 16359v1 Announce Type: cross Abstract: Fully Homomorphic Encryption (FHE) enables privacy-preserving machine learning but incurs extreme computational and memory overhead.
By Ran Ran, Zhaoting Gong, Nuo Xu, Yuanchao Xu, Fan Yao, Wujie Wen
arXiv:2609.35883v1 Announce Type: cross
Abstract: Genome foundation models are growing into sparse mixture-of-experts (MoE) networks whose expert weights no longer fit on the machines that hold the s...
By Guang Yang, Fengchen Liu
arXiv:2608. 06912v1 Announce Type: new Abstract: The top-$k$ operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and attention pruning.
By {\L}ukasz Struski, Joanna Wojciechowicz, Jakub Antczak, Marcin Mazur, Kamil Ksi\k{a}\.zek, Jacek Tabor
arXiv:2609.16898v1 Announce Type: cross
Abstract: Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with...
By Jiangrui Yu, Ye Yu, Si Chen, Chenqi Lin, Wenxuan Zeng, Junfeng Fan, Mingyu Gao, Meng Li
arXiv:2608.31067v1 Announce Type: new
Abstract: Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and lengt...
By Takuya Ito, Ruchir Puri, Murray Campbell, Parikshit Ram
arXiv:2608.06912v2 Announce Type: replace
Abstract: Selecting the top-$k$ elements is a fundamental operation for inducing sparsity in large-scale models and optimization problems, enabling robust ex...
By Jakub Antczak, Joanna Wojciechowicz, Kamil Ksi\k{a}\.zek, Marcin Mazur, {\L}ukasz Struski, Jacek Tabor
arXiv:2510. 16028v4 Announce Type: replace-cross Abstract: Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces).
By Jianzhu Yao, Hongxu Su, Taobo Liao, Zerui Cheng, Huan Zhang, Xuechao Wang, Pramod Viswanath
ExFold is a training‑free expert‑folding framework that jointly accelerates the prefill and decode phases of Mixture‑of‑Experts (MoE) models by projecting the contributions of excluded experts onto a retained expert set using calibrated scalar projectors. It treats both phases as a budgeted output‑approximation problem, achieving token‑level Top‑K folding for prefill and batch‑level expert‑pool folding for decode. Implemented as a plug‑and‑play plugin in vLLM with a lightweight CUDA kernel, ExFold delivers up to 1.41× TTFT and 2.45× TPOT speedups while preserving about 99% of the original model quality.
By Juntong Wu, Yifei Liu, Junyi Chen, Siqi Fan, Chaoran Feng, Minghao Li, Liujie Zhang, Weihang Chen, Li Yuan
arXiv:2609.01343v1 Announce Type: new
Abstract: Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating archit...
By Shaowen Wang, Ge Zhang, Kairong Luo, Yuhao Wu, Shaofan Liu, Jiaheng Liu, Wenhao Huang, Shen Yan, Jian Li