Shihong Deng

3 papers · 2020–2025 · 2 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 ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

EMNLP (2) IJCAI (1)

Top co-authors

Daxin Jiang (2) Linjing Li (2) Zhaohui Yang (2) Junliang Xing (1) Xiaowen Shi (1) Yuxiao Ye (1) Kai Li (1) Qiyue Yin (1) Yifan Zang (1) Yongxin Kang (1)

Research topics

Machine Learning (3) Reinforcement Learning (2) Learning Types · Machine Learning (2) Methods (2) Optimization & Theory (2) Artificial Intelligence (1) Deep Learning (1) Application Areas (1) Core AI (1) Learning Types · Deep Learning (1)

Keywords

chain of thought (2) sample efficiency (1) offline reinforcement learning (1) policy gradient (1) error propagation (1) sparse reward (1) experience replay (1) negative sample (1) potential energy (1) hard exploration (1) intrinsic state supervision (1) self-imitation learning (1) process reward model (1) negative sample augmentation (1) large language model (1) reasoning step (1) reinforcement learning (1) behavior constrained (1)

Papers

Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning EMNLP 2025 Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning EMNLP 2025 Potential Driven Reinforcement Learning for Hard Exploration Tasks IJCAI 2020