paper-with-me

Papers

Cross-Attention and Encoder-Decoder Transformers: A Logical Characterization

2026-05-08 · Veeti Ahvonen, Damian Heiman, Antti Kuusisto, Miguel Moreno, Matias Selin arxiv

We give a novel logical characterization of encoder-decoder transformers, the foundational architecture for LLMs that also sees use in various settings that benefit from cross-attention. We study such transformers over text in the practical setting of floating-point numbers and soft-attention, characterizing them with a new temporal logic. This logic extends propositional logic with a counting global modality over the encoder input and a past modality over the decoder input. We also give an additional characterization of such transformers via a type of distributed automata, and show that our results are not limited to the specific choices in the architecture and can account for changes in, e.g., masking. Finally, we discuss encoder-decoder transformers in the autoregressive setting.

📄 PDF Abstract BibTeX arXiv:2605.07705

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey

2020-11-17 · Benyamin Ghojogh, Ali Ghodsi

This is a tutorial and survey paper on the attention mechanism, transformers, BERT, and GPT. We first explain attention mechanism, sequence-to-sequence model without and with attention, self-attention, and attention in d…

DecoderDeep AttentionNatural Language InferenceSurvey+1

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers

2023-10-05 · Anna Langedijk, Hosein Mohebbi, Gabriele Sarti, Willem Zuidema 외

In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformer…

DecoderLogical ReasoningMachine TranslationQuestion Answering+2

Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers

2022-07-27 · Junhyeong Cho, Kim Youwang, Tae-Hyun Oh

Transformer encoder architectures have recently achieved state-of-the-art results on monocular 3D human mesh reconstruction, but they require a substantial number of parameters and expensive computations. Due to the larg…

3D Hand Pose Estimation3D Human Pose Estimation3D ReconstructionDecoder

Dynamic DETR: End-to-End Object Detection With Dynamic Attention

2021-01-01 · ICCV 2021 10 · Xiyang Dai, Yinpeng Chen, Jianwei Yang, Pengchuan Zhang 외

In this paper, we present a novel Dynamic DETR (Detection with Transformers) approach by introducing dynamic attentions into both the encoder and decoder stages of DETR to break its two limitations on small feature r…

Decoderobject-detectionObject Detection

ENTP: Encoder-only Next Token Prediction

2024-10-02 · Ethan Ewer, Daewon Chae, Thomas Zeng, Jinkyu Kim 외

Next-token prediction is conventionally done using decoder-only Transformers with causal attention, as this approach allows for efficient reuse of keys and values. What if we were not compute-limited, should we still use…

DecoderIn-Context LearningPredictionTriplet