Zhongyuan Peng
3 papers · 2024–2026 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
Venues
Top co-authors
Research topics
Keywords
reinforcement learning
(1)
dialogue generation
(1)
multimodal learning
(1)
natural language understanding
(1)
agent interaction
(1)
knowledge graph
(1)
variational information bottleneck
(1)
supervised fine-tuning
(1)
automated theorem proving
(1)
large vision-language model
(1)
object hallucination
(1)
role-playing agent
(1)
hierarchical memory
(1)
visual token
(1)
visual-language alignment
(1)
entropy-based method
(1)
semantic fidelity
(1)
large language model
(1)
hierarchical memory system
(1)
script-based agent generation
(1)
Papers
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
ACL 2026
Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow
AAAI 2025
RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
NeurIPS 2024