Get started
Author

Yifu Huo

ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation
2024 · Chenglong Wang, Hang Zhou, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 4
PDF
RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data
2025 · Chenglong Wang, Yang Gan, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2
PDF
PEAR: Adaptive Advantage Reshaping for Perception and Exploration in Large Vision-Language Models
2026 · Wang, Junxin, Luo, Yingfeng, et al. · arXiv (Cornell University)
PDF
Preference-Emergence Anchor Distillation for Efficient Generative Reward Modeling
2026 · Kaiwei Wang, Chenglong Wang, et al. · Data Intelligence
Learning from Environmental Feedback: Credit Assignment across Multiple Timescales for Agentic Reinforcement Learning
2026 · Huo, Yifu, Xing, Shunjie, et al. · arXiv (Cornell University)
PDF
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
2026 · Wang, Chenglong, Zhu, Ziming, et al. · arXiv (Cornell University)
PDF
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
2026 · Huo, Yifu, Wang, Chenglong, et al. · arXiv (Cornell University)
PDF
MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning
2026 · Wang, Chenglong, Huo, Yifu, et al. · arXiv (Cornell University)
PDF
GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning
2026 · Chenglong Wang, Yongyu Mu, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
PDF
Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
2026 · Chenglong Wang, Yifu Huo, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
PDF
APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards
2026 · Chang, Kaiyan, Zhu, Chenwei, et al. · arXiv (Cornell University)
PDF
SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams
2026 · Wang, Chenglong, Li, Canjia, et al. · arXiv (Cornell University)
PDF
Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
2026 · Association for Artificial Intelligence 2026, Gan, Yang, et al. · Underline Science Inc.
165 - GRAM-R$^2$: Self-Training Generative Foundation Reward Models for Reward Reasoning
2026 · Association for Artificial Intelligence 2026, Hao, Xiaoyang, et al. · Underline Science Inc.
GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning
2026 · Association for Artificial Intelligence 2026, Hao, Xiaoyang, et al. · Underline Science Inc.
When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning
2026 · Ruixiang Mao, Xiangnan Ma, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
2026 · Yifu Huo, Chenglong Wang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams
2026 · Chenglong Wang, Canjia Li, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
LaTeXTrans Structure-Aware Translation of Complex LaTeX Documents
2026 · Ziming Zhu, Chenglong Wang, et al.
PDF
Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
2025 · Wang, Chenglong, Huo, Yifu, et al. · arXiv (Cornell University)
PDF
GRAM-R$^2$: Self-Training Generative Foundation Reward Models for Reward Reasoning
2025 · Wang, Chenglong, Mu, Yongyu, et al. · arXiv (Cornell University)
PDF
GRAM: A Generative Foundation Reward Model for Reward Generalization
2025 · Wang, Chenglong, Gan, Yang, et al. · arXiv (Cornell University)
PDF
HEAL: A Hypothesis-Based Preference-Aware Analysis Framework
2025 · Yifu Huo, Chenglong Wang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
LRHP: Learning Representations for Human Preferences via Preference Pairs
2024 · Wang, Chenglong, Gan, Yang, et al. · arXiv (Cornell University)
PDF
Works count: 28
Citation count: 6
H-index: 2
I10-index:
Year
Topic
Type