paper-with-me

홈 › Papers

FLOWGEN: Fast and slow graph generation

2022-07-15 · Aman Madaan, Yiming Yang

Machine learning systems typically apply the same model to both easy and tough cases. This is in stark contrast with humans, who tend to evoke either fast (instinctive) or slow (analytical) thinking depending on the problem difficulty, a property called the dual-process theory of mind. We present FLOWGEN, a graph-generation model inspired by the dual-process theory of mind that generates large graphs incrementally. Depending on the difficulty of completing the graph at the current step, graph generation is routed to either a fast (weaker) or a slow (stronger) model. These modules have identical architectures, but vary in the number of parameters and consequently differ in generative power. Experiments on real-world graphs show that ours can successfully generate graphs similar to those generated by a single large model, while being up to 2x faster.

📄 PDF Abstract BibTeX arXiv:2207.07656

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Generation

Similar Papers 제목 키워드 기반

WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience

2026-03-22 · Ruocan Wei, Shufeng Wang, Ziwei Shi arxiv

Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse past experiences in complex tasks like business queries, tool use, and …

Semantic Similarity

SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents

2024-03-23 · Feng Lin, Dong Jae Kim, Tse-Husn, Chen

Software process models are essential to facilitate collaboration and communication among software teams to solve complex development tasks. Inspired by these software engineering practices, we present FlowGen - a code g…

Code GenerationHumanEvalLanguage ModelingLanguage Modelling+2

Seeing Fast and Slow: Bimodal 3D Scene Graphs for Open-set Tasks

2026-05-29 · Marcel Bartholomeus Prasetyo, Shrutika Vishal Thengane, A Manicka Praveen, Yi Loo 외 arxiv

Open-set task execution can significantly benefit from seamlessly switching between coarse and fine scene representations depending on the context and the evolving information as the robot explores the environment. For e…

Scene Graph Generation

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

2024-10-30 · Yining Hong, Beide Liu, Maxine Wu, Yuanhao Zhai 외

Human beings are endowed with a complementary learning system, which bridges the slow learning of general world dynamics with fast storage of episodic memory from a new experience. Previous video generation models, howev…

Video Generation

InstantDrag: Improving Interactivity in Drag-based Image Editing

2024-09-13 · Joonghyuk Shin, Daehyeon Choi, Jaesik Park

Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to…

Image GenerationMotion GenerationOptical Flow Estimation