paper-with-me

Papers

ProTo: Program-Guided Transformer for Program-Guided Tasks

2021-10-02 · NeurIPS 2021 12 · Zelin Zhao, Karan Samel, Binghong Chen, Le Song

Programs, consisting of semantic and structural information, play an important role in the communication between humans and agents. Towards learning general program executors to unify perception, reasoning, and decision making, we formulate program-guided tasks which require learning to execute a given program on the observed task specification. Furthermore, we propose the Program-guided Transformer (ProTo), which integrates both semantic and structural guidance of a program by leveraging cross-attention and masked self-attention to pass messages between the specification and routines in the program. ProTo executes a program in a learned latent space and enjoys stronger representation ability than previous neural-symbolic approaches. We demonstrate that ProTo significantly outperforms the previous state-of-the-art methods on GQA visual reasoning and 2D Minecraft policy learning datasets. Additionally, ProTo demonstrates better generalization to unseen, complex, and human-written programs.

📄 PDF Abstract BibTeX arXiv:2110.00804

Code (1)

sjtuytc/Neurips21-ProTo-Program-guided-Transformers-for-Program-guided-Tasks 공식 구현 pytorch

Tasks

Decision MakingLearning to ExecuteMinecraftVisual Question Answering (VQA)Visual Reasoning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A

2025-08-04 · Chen Li, Chinthani Sugandhika, Yeo Keat Ee, Eric Peh 외 arxiv

Existing human motion Q\&A methods rely on explicit program execution, where the requirement for manually defined functional modules may limit the scalability and adaptability. To overcome this, we propose an implicit pr…

Are Transformers All That Karel Needs?

2021-10-08 · NeurIPS Workshop AIPLANS 2021 12 · Abhay Garg, Anand Sriraman, Kunal Pagarey, Shirish Karande

Recent works have shown the incredible promise of using neural networks for the task of program synthesis from input-output examples. In this paper, we propose using Transformer-based architectures as a baseline for the …

AllDecoderProgram Synthesis

Syntax-Guided Program Reduction for Understanding Neural Code Intelligence Models

2022-05-28 · Md Rafiqul Islam Rabin, Aftab Hussain, Mohammad Amin Alipour

Neural code intelligence (CI) models are opaque black-boxes and offer little insight on the features they use in making predictions. This opacity may lead to distrust in their prediction and hamper their wider adoption i…

Method name prediction

Toward Neural-Network-Guided Program Synthesis and Verification

2021-03-17 · Naoki Kobayashi, Taro Sekiyama, Issei Sato, Hiroshi Unno

We propose a novel framework of program and invariant synthesis called neural network-guided synthesis. We first show that, by suitably designing and training neural networks, we can extract logical formulas over integer…

Program Synthesis

Program-Guided Image Manipulators

2019-09-04 · ICCV 2019 10 · Jiayuan Mao, Xiuming Zhang, Yikai Li, William T. Freeman 외

Humans are capable of building holistic representations for images at various levels, from local objects, to pairwise relations, to global structures. The interpretation of structures involves reasoning over repetition a…

Image Inpainting