XIA SONG
28 papers · 2019–2026 · 7 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (59) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π§
Keyword Pioneer
π₯
Mega-Team Β· Squad
π€
Dynamic Duo
(12)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(125)
Top co-authors
Research topics
Deep Learning
(19)
Natural Language Processing
(18)
Machine Learning
(17)
Artificial Intelligence
(13)
Learning Types Β· Machine Learning
(13)
Resources & Methods
(12)
Core AI
(10)
Learning Types Β· Deep Learning
(10)
Techniques
(8)
Architectures
(7)
Applications
(6)
Generation
(5)
Optimization & Theory
(5)
Models
(4)
Application Areas
(3)
Keywords
cross-lingual transfer
(7)
large language model
(6)
cross-lingual language model
(5)
language model
(3)
zero-shot learning
(3)
transformer architecture
(3)
multilingual language model
(3)
question answering
(3)
replaced token detection
(2)
text-to-text transformer
(2)
representation learning
(2)
scaling law
(2)
knowledge distillation
(2)
embedding learning
(2)
contrastive learning
(2)
preference optimization
(2)
machine translation
(2)
preference alignment
(2)
visual question answering
(1)
text classification
(1)
Papers
WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering
ACL 2026
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
ACL 2026
A Practical Analysis of Human Alignment with *PO
NAACL 2025
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation
ACL 2025
Group Preference Alignment: Customizing LLM Responses from In-Situ Conversations Only When Needed
EMNLP 2025
POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
ICML 2025
Scaling Laws for Multilingual Language Models
ACL 2025
Scaling Optimal LR Across Token Horizons
ICLR 2025
Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
ACL 2024
On the Adaptation of Unlimiformer for Decoder-Only Transformers
COLING 2024
A Length-Extrapolatable Transformer
ACL 2023
Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning
ACL 2023
Language Is Not All You Need: Aligning Perception with Language Models
NeurIPS 2023
Magneto: A Foundation Transformer
ICML 2023
Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
ACL 2023
On the Representation Collapse of Sparse Mixture of Experts
NeurIPS 2022
Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators
ICLR 2022
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
ACL 2022
Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training
EMNLP 2021
COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
NeurIPS 2021
Consistency Regularization for Cross-Lingual Fine-Tuning
ACL 2021
InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training
NAACL 2021
Language Scaling for Universal Suggested Replies Model
NAACL 2021
mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs
EMNLP 2021
Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task
EMNLP 2021
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point
NeurIPS 2020
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention
ICLR 2020
Towards Language Agnostic Universal Representations
ACL 2019