paper-with-me

Decoder

1개 벤치마크 · 논문 10,368편 · 이 태스크의 논문 보기 →

Benchmarks

^(#$!@#$)(()))******

결과 4개

Most implemented

Attention Is All You Need

2017-06-12 · 구현 595개

Searching for MobileNetV3

2019-05-06 · 구현 67개

Papers

LINR-PCGC: Lossless Implicit Neural Representations for Point Cloud Geometry Compression

2025-07-21 · Wenjie Huang, Qi Yang, Shuting Xia, He Huang 외

Existing AI-based point cloud compression methods struggle with dependence on specific training data distributions, which limits their real-world deployment. Implicit Neural Representation (INR) methods solve the above p…

DecoderModel Compression

Making Language Model a Hierarchical Classifier and Generator

2025-07-17 · Yihong Wang, Zhonglin Jiang, Ningyuan Xi, Yue Zhao 외

Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with diff…

DecoderLanguage ModelingLanguage Modellingmodel+3

Boosting Team Modeling through Tempo-Relational Representation Learning

2025-07-17 · Vincenzo Marco De Luca, Giovanna Varni, Andrea Passerini

Team modeling remains a fundamental challenge at the intersection of Artificial Intelligence and the Social Sciences. Social Science research emphasizes the need to jointly model dynamics and relations, while practical a…

DecoderRepresentation Learning

The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting

2025-07-17 · Lefei Shen, Mouxiang Chen, Han Fu, Xiaoxue Ren 외

Transformer-based models have recently become dominant in Long-term Time Series Forecasting (LTSF), yet the variations in their architecture, such as encoder-only, encoder-decoder, and decoder-only designs, raise a cruci…

DecoderTime SeriesTime Series Forecasting

Context-Aware Search and Retrieval Over Erasure Channels

2025-07-16 · Sara Ghasvarianjahromi, Yauhen Yakimenka, Jörg Kliewer

This paper introduces and analyzes a search and retrieval model that adopts key semantic communication principles from retrieval-augmented generation. We specifically present an information-theoretic analysis of a remote…

DecoderRetrievalRetrieval-augmented GenerationSemantic Communication

Seq vs Seq: An Open Suite of Paired Encoders and Decoders

2025-07-15 · Orion Weller, Kathryn Ricci, Marc Marone, Antoine Chaffin 외

The large language model (LLM) community focuses almost exclusively on decoder-only language models, since they are easier to use for text generation. However, a large subset of the community still uses encoder-only mode…

DecoderLarge Language ModelRetrievalText Generation

전체 10,368편 보기 →