Hongyi Guo
9 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (23) π Conference Polyglot (3) π Academic Marathon (5) π§ Keyword Pioneer π Cross-Pollinator (5)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
π₯
Unstoppable
(6)
Conferences
ICML (6)
NIPS (2)
EMNLP (1)
Top co-authors
Keywords
reinforcement learning
(3)
reinforcement learning from human feedback
(2)
sample efficiency
(1)
offline reinforcement learning
(1)
game theory
(1)
direct preference optimization
(1)
policy learning
(1)
mutual information
(1)
language model alignment
(1)
weak supervision
(1)
robust classification
(1)
empirical risk minimization
(1)
model alignment
(1)
nash equilibrium
(1)
adversarial learning
(1)
label noise
(1)
partially observable markov decision process
(1)
linear function approximation
(1)
bellman operator
(1)
contrastive learning
(1)
Papers
Toward Optimal LLM Alignments Using Two-Player Games
EMNLP 2025
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
ICML 2025
Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents
ICML 2024
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
NIPS 2024
Behavior Contrastive Learning for Unsupervised Skill Discovery
ICML 2023
Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes
ICML 2022
Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games
ICML 2021
Policy Learning Using Weak Supervision
NIPS 2021
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
ICML 2020