Dengyun Peng
4 papers · 2024–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (2)
EMNLP (1)
ICML (1)
Top co-authors
Keywords
few-shot learning
(1)
chain-of-thought reasoning
(1)
token efficiency
(1)
prompt optimization
(1)
dynamic reasoning
(1)
large language model
(1)
attention entropy
(1)
multi-solution task
(1)
boundary preservation
(1)
adaptive reward
(1)
text-based gradient optimization
(1)
reasoning overconfidence
(1)
cognitive rigidity
(1)
Papers
Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Significant Gains in Reasoning Efficiency in Large Language Models
AAAI 2026
Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks
AAAI 2026
DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective
EMNLP 2025
Reinformer: Max-Return Sequence Modeling for Offline RL
ICML 2024