Xingchen Wang
4 papers · 2024–2026 · 4 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
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
federated learning
(2)
direct preference optimization
(2)
autoregressive generation
(1)
mutual information
(1)
human feedback
(1)
preference aggregation
(1)
reward hacking
(1)
supervised fine-tuning
(1)
parameter importance
(1)
tabular data generation
(1)
model heterogeneity
(1)
legal reasoning
(1)
small language model
(1)
fairness-utility tradeoff
(1)
large language model
(1)
group-level debiasing
(1)
sub-model extraction
(1)
model compression
(1)
diagnosis-driven synthesis
(1)
reinforcement learning
(1)
Papers
LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models
ACL 2026
Towards Federated RLHF with Aggregated Client Preference for LLMs
ICLR 2025
Towards Universal Debiasing for Language Models-based Tabular Data Generation
EMNLP 2025
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
NeurIPS 2024