conftrace_
← Authors

Xidong Feng

11 papers · 2020–2025 · 5 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+7 more ↓ 🏃 Academic Marathon (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (15)
🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) 🏃 Academic Marathon (5) 🏆 Grand Slam 💎 Century Club (11) 🔥 Unstoppable (6) 🗃️ Keyword Collector (53)

Conferences

NIPS (5) AAAI (2) ICML (2) ICLR (1) JMLR (1)

Top co-authors

Jun Wang (6) Yaodong Yang (5) Ying Wen (2) Haifeng Zhang (2) Mengyue Yang (2) Stephen Mcaleer (2) Bo Liu (2) Stephen Marcus McAleer (2) Ziyu Wan (2) Chumin Liu (1)

Research topics

Reinforcement Learning (1)

Keywords

multi-agent reinforcement learning (4) large language model (2) reinforcement learning (2) meta-reinforcement learning (2) interpretable machine learning (1) policy learning (1) offline reinforcement learning (1) question answering (1) contrastive learning (1) language modeling (1) uncertainty quantification (1) image reconstruction (1) nash equilibrium (1) question generation (1) markov decision process (1) game theory (1) magnetic resonance imaging (1) stochastic process (1) exploration policy (1) compressed sensing (1)

Papers

Efficient Reinforcement Learning with Large Language Model Priors ICLR 2025 AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training ICML 2024 Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs NIPS 2024 Heterogeneous-Agent Reinforcement Learning JMLR 2024 MANSA: Learning Fast and Slow in Multi-Agent Systems ICML 2023 ChessGPT: Bridging Policy Learning and Language Modeling NIPS 2023 A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning NIPS 2022 Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning NIPS 2022 Neural Auto-Curricula in Two-Player Zero-Sum Games NIPS 2021 Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning AAAI 2021 MRI Reconstruction with Interpretable Pixel-Wise Operations Using Reinforcement Learning AAAI 2020