Longzheng Wang
4 papers · 2022–2026 · 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(12)
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
generative reward model
(2)
reinforcement learning from human feedback
(2)
question answering
(1)
named entity recognition
(1)
multimodal learning
(1)
visual grounding
(1)
preference modeling
(1)
cross-modal alignment
(1)
mixture of expert
(1)
social media
(1)
dialogue system
(1)
positional bia
(1)
span-based method
(1)
false information
(1)
large language model
(1)
fact verification
(1)
consistency-aware reward
(1)
preference alignment
(1)
Papers
ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training
ACL 2026
ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework
ACL 2026
An Effective Span-based Multimodal Named Entity Recognition with Consistent Cross-Modal Alignment
COLING 2024
QaDialMoE: Question-answering Dialogue based Fact Verification with Mixture of Experts
EMNLP 2022