XIA SONG
29 papers · 2019–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🏃 Academic Marathon (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) 🐝 Cross-Pollinator (11)
🌍
Conference Polyglot
(8)
🏃
Academic Marathon
(6)
🤝
Dynamic Duo
(13)
👥
Mega-Team
(24)
🧬
Topic Evolution
⚡
Prolific Year
(6)
💎
Century Club
(27)
🗃️
Keyword Collector
(104)
🔥
Unstoppable
(7)
Conferences
ACL (11)
EMNLP (4)
NIPS (4)
ICLR (3)
NAACL (3)
ICML (2)
COLING (1)
IJCNLP (1)
Top co-authors
Keywords
cross-lingual transfer
(8)
cross-lingual language model
(5)
large language model
(5)
zero-shot learning
(3)
language model
(3)
text-to-text transformer
(2)
representation learning
(2)
multilingual model
(2)
consistency regularization
(2)
transformer architecture
(2)
language model fine-tuning
(2)
embedding learning
(2)
machine translation
(2)
multilingual language model
(2)
knowledge distillation
(2)
contrastive learning
(2)
data augmentation
(2)
preference alignment
(2)
question answering
(2)
direct preference optimization
(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
POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
ICML 2025
A Practical Analysis of Human Alignment with *PO
NAACL 2025
Scaling Optimal LR Across Token Horizons
ICLR 2025
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation
ACL 2025
Scaling Laws for Multilingual Language Models
ACL 2025
Group Preference Alignment: Customizing LLM Responses from In-Situ Conversations Only When Needed
EMNLP 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
Language Is Not All You Need: Aligning Perception with Language Models
NIPS 2023
Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
ACL 2023
Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning
ACL 2023
Magneto: A Foundation Transformer
ICML 2023
A Length-Extrapolatable Transformer
ACL 2023
On the Representation Collapse of Sparse Mixture of Experts
NIPS 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
mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs
EMNLP 2021
COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
NIPS 2021
Consistency Regularization for Cross-Lingual Fine-Tuning
ACL 2021
Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training
EMNLP 2021
Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task
EMNLP 2021
Consistency Regularization for Cross-Lingual Fine-Tuning
IJCNLP 2021
InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training
NAACL 2021
Language Scaling for Universal Suggested Replies Model
NAACL 2021
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention
ICLR 2020
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point
NIPS 2020
Towards Language Agnostic Universal Representations
ACL 2019