paper-with-me

Papers

Block-Based Double Decoders

2026-05-11 · Asher Labovich, Benjamin Bradley, Vanessa Alexander, Chaitanya Harsha arxiv

Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervision and dynamic sequence lengths, keeping them out of practice at scale. We propose block-based double decoders, a novel transformer architecture that utilizes doubly-causal block-based attention masks to train with full loss supervision and static sequence packing, combining decoder-only training efficiency with encoder-decoder inference efficiency. In scaling law experiments, block-based double decoders strongly outperform encoder-decoders and closely track decoder-only models across scales. At inference time, they cut KV-cache memory and per-token compute by at least 2/3 without sacrificing prefill caching or other existing inference optimizations available to decoder-only models.

📄 PDF Abstract BibTeX arXiv:2605.18807

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How to Mask in Error Correction Code Transformer: Systematic and Double Masking

2023-08-16 · Seong-Joon Park, Hee-Youl Kwak, Sang-Hyo Kim, Sunghwan Kim 외

In communication and storage systems, error correction codes (ECCs) are pivotal in ensuring data reliability. As deep learning's applicability has broadened across diverse domains, there is a growing research focus on ne…

DooDLeNet: Double DeepLab Enhanced Feature Fusion for Thermal-color Semantic Segmentation

2022-04-21 · Oriel Frigo, Lucien Martin-Gaffé, Catherine Wacongne

In this paper we present a new approach for feature fusion between RGB and LWIR Thermal images for the task of semantic segmentation for driving perception. We propose DooDLeNet, a double DeepLab architecture with specia…

DecoderSegmentationSemantic SegmentationThermal Image Segmentation

MIST: A Novel Training Strategy for Low-latencyScalable Neural Net Decoders

2019-05-22 · Kumar Yashashwi, Deepak Anand, Sibi Raj B Pillai, Prasanna Chaporkar 외

In this paper, we propose a low latency, robust and scalable neural net based decoder for convolutional and low-density parity-check (LPDC) coding schemes. The proposed decoders are demonstrated to have bit error rate (B…

Decoder

On the Design and Performance of Machine Learning Based Error Correcting Decoders

2024-10-21 · Yuncheng Yuan, Péter Scheepers, Lydia Tasiou, Yunus Can Gültekin 외

This paper analyzes the design and competitiveness of four neural network (NN) architectures recently proposed as decoders for forward error correction (FEC) codes. We first consider the so-called single-label neural net…

Action-List Reinforcement Learning Syndrome Decoding for Binary Linear Block Codes

2025-07-23 · Milad Taghipour, Bane Vasic arxiv

This paper explores the application of reinforcement learning techniques to enhance the performance of decoding of linear block codes based on flipping bits and finding optimal decisions. We describe the methodology for …

Reinforcement Learning