Neural Decoding with Optimization of Node Activations

2022-06-01 · Eliya Nachmani, Yair Be'ery

The problem of maximum likelihood decoding with a neural decoder for error-correcting code is considered. It is shown that the neural decoder can be improved with two novel loss terms on the node's activations. The first loss term imposes a sparse constraint on the node's activations. Whereas, the second loss term tried to mimic the node's activations from a teacher decoder which has better performance. The proposed method has the same run time complexity and model size as the neural Belief Propagation decoder, while improving the decoding performance by up to $1.1dB$ on BCH codes.

📄 PDF Abstract BibTeX arXiv:2206.00786

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets

2026-08-19 · Tate Berenbaum, Muthaiah Venkatachalam arxiv

Modern Intel AI PCs ship capable integrated GPUs and NPUs with 16+ GB of unified memory, and they spend considerable time idle. That is not enough memory to fit a large model such as a 70B-parameter LLM. We show that a h…

Towards Creativity Characterization of Generative Models via Group-based Subset Scanning

2022-03-01 · Celia Cintas, Payel Das, Brian Quanz, Girmaw Abebe Tadesse 외

Deep generative models, such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), have been employed widely in computational creativity research. However, such models discourage out-of-distribut…

Towards creativity characterization of generative models via group-based subset scanning

2021-04-01 · Celia Cintas, Payel Das, Brian Quanz, Skyler Speakman 외

Deep generative models, such as Variational Autoencoders (VAEs), have been employed widely in computational creativity research. However, such models discourage out-of-distribution generation to avoid spurious sample gen…

Efficient Neural Combinatorial Optimization Solver for the Min-max Heterogeneous Capacitated Vehicle Routing Problem

2025-07-28 · Xuan Wu, Di Wang, Chunguo Wu, Kaifang Qi 외 arxiv

Numerous Neural Combinatorial Optimization (NCO) solvers have been proposed to address Vehicle Routing Problems (VRPs). However, most of these solvers focus exclusively on single-vehicle VRP variants, overlooking the mor…

Reinforcement Learning

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

2026-05-27 · Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta, Denis Kleyko 외 arxiv

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that…