Heng-Tze Cheng

5 papers · 2019–2024 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+2 more ↓

🌉 Interdisciplinary Bridge · Silver 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze

👑 Triple Crown 🧭 Keyword Pioneer

Venues

ICML (2) ICLR (1) IJCAI (1) NeurIPS (1)

Top co-authors

Ed H. Chi (3) Huaixiu Steven Zheng (2) Yaguang Li (2) Swaroop Mishra (2) Quoc V Le (2) Xinyun Chen (2) Denny Zhou (2) Zhe Zhao (1) Vamsi Aribandi (1) Yun He (1)

Research topics

Artificial Intelligence (4) Core AI (4) Natural Language Processing (3) Machine Learning (2) Reinforcement Learning (2) Application Areas (2) Methods (2) Resources & Methods (2) Generation (1) Learning Types (1)

Keywords

large language model (2) temporal difference learning (1) multi-task learning (1) transfer learning (1) prompt engineering (1) user modeling (1) language model (1) parameter efficiency (1) action space (1) complex reasoning (1) prompt tuning (1) slate recommendation (1) value decomposition (1) long-term engagement (1) reasoning chain (1) controlled decoding (1) abstraction reasoning (1) reasoning structure (1) step-back prompting (1) atomic reasoning module (1)

Papers

Controlled Decoding from Language Models ICML 2024 SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures NeurIPS 2024 Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models ICLR 2024 HyperPrompt: Prompt-based Task-Conditioning of Transformers ICML 2022 SlateQ: A Tractable Decomposition for Reinforcement Learning with Recommendation Sets IJCAI 2019