Jiayuan Mao
Jiayuan Mao has 2 papers in our library, in 2019–2024, most of them on Reasoning; often with Chuang Gan, Daniel Fried, Graham Neubig.
OpenAlex · ORCID · h-index 12 · 82 works · 1,961 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 321 times in our library · 6 more in our library without a page yet · ⭐ Paper Stars ranking: #5334
Affiliations
🎓Massachusetts Institute of TechnologyCambridge ·
United States2019–2026 · 40 papersEmployment🎓University of PennsylvaniaPhiladelphia ·
United States2026 · 9 papers🏢AmazonSeattle ·
United States2026 · 5 papers🎓Stanford UniversityStanford ·
United States2026 · 1 paper🎓Tsinghua UniversityBeijing ·
China2017–2025 · 13 papers🔬MIT Computer Science and Artificial Intelligence LaboratoryCambridge ·
United States2019–2025 · 7 papers
Fields, topics and concepts
📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 1 workInformation Systems · 1 work
🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1 work
Works by year
2020s
2010s
Papers
- The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision (2019 · 241 citations)
Visual reasoning systems that run explicit programs are usually trained with costly extra annotations, such as ground-truth programs or labelled object attributes. - Agent Workflow Memory (2024 · 86 citations)
LM-based web agents often fail at long, multi-step tasks. They usually treat each task in isolation and rely on a fixed set of examples, so they adapt poorly when tasks or websites change. Agent Workflow Memory (AWM) addresses this by letting the agent build reusable routines ("workflows") from earlier trajectories.…
All works
- What Can Help Pedestrian Detection? ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJiayuan Mao et al.2017 · 302 citations
- The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural SupervisionarXiv:1904.12584Jiayuan Mao, Chuang Gan, Pushmeet Kohli, et al.2019 · 241 citations
- Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetHao Wu et al.2019 · 174 citations
- Visually Grounded Neural Syntax Acquisition ↗Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yetHaoyue Shi et al.2019 · 100 citations
- Agent Workflow MemoryarXiv:2409.07429Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, et al.2024 · 86 citations
- Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making ↗neural information processing systems · no summary yetFeifei Li et al.2024 · 66 citations
- Learning Iterative Reasoning through Energy Diffusion ↗arXiv:2406.11179 · no summary yetYilun Du, Jiayuan Mao, Joshua B. Tenenbaum2024 · 11 citations
- Object-Centric Diagnosis of Visual Reasoning ↗arXiv (Cornell University) · no summary yetJianwei Yang et al.2020 · 11 citations
Co-authors here
Venues
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×2
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- neural information processing systems
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/jiayuan-mao/