Profiles2024-2026
Hao Peng
Department of Computer Science and Technology, Tsinghua University
7Papers
0Last author
1Unique co-authors
4First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers7
- WildReward: Learning Reward Models from In-the-Wild Human InteractionsAuthor 1 of 6ACL 2026 · 3 citations
- StoryAlign: Evaluating and Training Reward Models for Story GenerationAuthor 2 of 6ICLR 2026 · 2 citations
- VerIF: Verification Engineering for Reinforcement Learning in Instruction FollowingAuthor 1 of 6EMNLP 2025 · 24 citations
- Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward SystemsAuthor 1 of 7ACL 2025
- Pre-training Distillation for Large Language Models: A Design Space ExplorationAuthor 1 of 7ACL 2025
- ADELIE: Aligning Large Language Models on Information ExtractionAuthor 2 of 5EMNLP 2024 · 8 citations
- MAVEN-FACT: A Large-scale Event Factuality Detection DatasetAuthor 2 of 7EMNLP Findings 2024 · 1 citation
