paper-with-me

Papers

Deep Reasoning Networks: Thinking Fast and Slow, for Pattern De-mixing

2019-09-25 · Di Chen, Yiwei Bai, Wenting Zhao, Sebastian Ament, John M. Gregoire, Carla P. Gomes

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving pattern de-mixing problems, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining logic and constraint reasoning with stochastic-gradient-based neural network optimization. We illustrate the power of DRNets on de-mixing overlapping hand-written Sudokus (Multi-MNIST-Sudoku) and on a substantially more complex task in scientific discovery that concerns inferring crystal structures of materials from X-ray diffraction data (Crystal-Structure-Phase-Mapping). DRNets significantly outperform the state of the art and experts' capabilities on Crystal-Structure-Phase-Mapping, recovering more precise and physically meaningful crystal structures. On Multi-MNIST-Sudoku, DRNets perfectly recovered the mixed Sudokus' digits, with 100% digit accuracy, outperforming the supervised state-of-the-art MNIST de-mixing models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

scientific discovery

Similar Papers 제목 키워드 기반

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

2024-10-31 · Ming Li, Yanhong Li, Tianyi Zhou

What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs), through the lens of gradient, when training with different responses and ini…

MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy

2026-06-26 · Zhiyuan Han, Beier Zhu, Wenwen Tong, Chengwei Qin 외 arxiv

We find that explicit reasoning does not necessarily translate into better multimodal emotion recognition (MER) accuracy, even though it makes predictions more interpretable. Specifically, for reasoning-based MLLMs, fast…

Multimodal Emotion RecognitionReinforcement Learning

Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting

2025-05-30 · Jiahao Wang, Mingyue Cheng, Qi Liu

Time series forecasting (TSF) is a fundamental and widely studied task, spanning methods from classical statistical approaches to modern deep learning and multimodal language modeling. Despite their effectiveness, these …

Language ModelingLanguage ModellingTime SeriesTime Series Forecasting

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

2024-10-13 · DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat, Yuandong Tian 외

In human cognition theory, human thinking is governed by two systems: the fast and intuitive System 1 and the slower but more deliberative System 2. Recent studies have shown that incorporating System 2 process into Tran…

Computational EfficiencyMath

Deep Reasoning Networks: Thinking Fast and Slow

2019-06-03 · Di Chen, Yiwei Bai, Wenting Zhao, Sebastian Ament 외

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit probl…

Decoderscientific discovery