Mingxuan Xia
8 papers · 2022–2025 · 6 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
⚡
Prolific Year · Productive
📈
Trend Setter
Top co-authors
Research topics
Keywords
large language model
(3)
text classification
(2)
unbiased risk estimator
(2)
data annotation
(2)
partial label learning
(2)
prototype learning
(1)
multi-label learning
(1)
zero-shot learning
(1)
multimodal classification
(1)
knowledge distillation
(1)
hierarchical text classification
(1)
label disambiguation
(1)
class imbalance
(1)
weakly supervised learning
(1)
generalization error bound
(1)
sinkhorn algorithm
(1)
ensemble method
(1)
language model
(1)
optimal transport
(1)
domain adaptation
(1)
Papers
CrowdAgent: Multi-Agent Managed Multi-Source Annotation System
EMNLP 2025
Ensembling Prompting Strategies for Zero-Shot Hierarchical Text Classification with Large Language Models
EMNLP 2025
Multi-Instance Multi-Label Classification from Crowdsourced Labels
AAAI 2025
Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation
ACL 2025
Towards Robust Incremental Learning Under Ambiguous Supervision
IJCAI 2025
A Separation and Alignment Framework for Black-Box Domain Adaptation
AAAI 2024
Unbiased Multi-Label Learning from Crowdsourced Annotations
ICML 2024
SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
NeurIPS 2022