Xiaohu Zhao
9 papers · 2022–2026 · 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 · Silver
🗺️
Taxonomy Completionist
(25)
🐣
Hot Topic Early Bird
🗃️
Keyword Collector
(55)
Venues
Top co-authors
Research topics
Artificial Intelligence
(6)
Deep Learning
(6)
Natural Language Processing
(6)
Core AI
(6)
Applications
(5)
Learning Types · Deep Learning
(5)
Machine Learning
(4)
Speech & Audio
(2)
Architectures
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Recognition
(2)
Application Areas
(1)
Core Methods
(1)
Generation
(1)
Keywords
machine translation
(3)
speech translation
(3)
end-to-end model
(2)
sparse autoencoder
(2)
preference alignment
(1)
text generation
(1)
multi-task learning
(1)
quality estimation
(1)
cross-modal learning
(1)
model interpretability
(1)
error detection
(1)
low-resource language
(1)
benchmark dataset
(1)
language model
(1)
representation disentanglement
(1)
data selection
(1)
supervised fine-tuning
(1)
mechanistic interpretability
(1)
preference optimization
(1)
knowledge distillation
(1)
Papers
Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs
AAAI 2026
From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models
ACL 2026
Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation
ACL 2026
M2PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation
ACL 2026
Marco Large Translation Model at WMT2025: Transforming Translation Capability in LLMs via Quality-Aware Training and Decoding
EMNLP 2025
CCSRD: Content-Centric Speech Representation Disentanglement Learning for End-to-End Speech Translation
EMNLP 2023
CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech Translation
ACL 2023
Towards a Deep Understanding of Multilingual End-to-End Speech Translation
EMNLP 2023
TGEA 2.0: A Large-Scale Diagnostically Annotated Dataset with Benchmark Tasks for Text Generation of Pretrained Language Models
NeurIPS 2022