Skip to content
conftrace_

Zhihan Liu

11 papers · 2022–2026 · 5 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 ↓
+3 more ↓ 🐣 Hot Topic Early Bird 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Silver πŸ—ΊοΈ Taxonomy Completionist (24) πŸ‘‘ Triple Crown
πŸ—ƒοΈ Keyword Collector (60) πŸ’Ž Century Club Β· Bronze πŸ”₯ Unstoppable Β· Bronze

Venues

ICML (5) ICLR (2) NeurIPS (2) ACL (1) EMNLP (1)

Top co-authors

Zhaoran Wang (9) Shenao Zhang (5) Boyi Liu (4) Zhuoran Yang (4) Hongyi Guo (4) Miao Lu (3) Yingxiang Yang (2) Han Zhong (2) Hao Hu (2) Sirui Zheng (2)

Research topics

Artificial Intelligence (8) Core AI (8) Machine Learning (7) Reinforcement Learning (6) Methods (6) Learning Types (5) Natural Language Processing (2) Optimization & Theory (2) Resources & Methods (2) Mathematics & Optimization (1) Optimization (1)

Keywords

multi-agent reinforcement learning (2) reinforcement learning from human feedback (2) sublinear regret (2) nash equilibrium (2) direct preference optimization (2) sample efficiency (2) large language model (2) continuous control (1) model alignment (1) game theory (1) markov decision process (1) posterior distribution (1) probabilistic framework (1) policy optimization (1) off-policy reinforcement learning (1) language model alignment (1) linear function approximation (1) bootstrapping (1) model-based reinforcement learning (1) preference alignment (1)

Papers

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game ACL 2026 BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning ICML 2025 Reward-Augmented Data Enhances Direct Preference Alignment of LLMs ICML 2025 Toward Optimal LLM Alignments Using Two-Player Games EMNLP 2025 Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer NeurIPS 2024 Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents ICML 2024 Sample-Efficient Multi-Agent RL: An Optimization Perspective ICLR 2024 Guarded Policy Optimization with Imperfect Online Demonstrations ICLR 2023 Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration NeurIPS 2023 Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation ICML 2022 Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy ICML 2022