Scholar
Yixia Li
Google Scholar ID: LrYjRNYAAAAJ
Southern University of Science and Technology
Citations & Impact
Citations
83
H-index
4
i10-index
2
Publications
10
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- 1. ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs. ACL Main, 2025
- 2. SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation. NeurIPS, 2024
- 3. LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy. NAACL Findings, 2025
- 4. UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization. TNNLS, 2024
- 5. G2: Guided Generation for Enhanced Output Diversity in LLMs. EMNLP Main, 2025
- 6. MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning. NAACL Main, 2025
- 7. Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning. Under Review, 2025
- 8. PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning. ACL Findings, 2024
- 9. FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only. ACL Findings, 2025
- 10. Vis-Codex: Unified Multimodal Code Generation via Merging Vision and Coding Models. Under Review, 2025
- 11. Cantonese Natural Language Processing in the Transformers Era, Survey and Challenges. Journal of Language Resources and Evaluation, 2024
- 12. Electric Power Grid Invulnerability Under Intentional Edge-Based Attacks. Communications in Computer and Information Science, 2019
Research Experience
- - Microsoft Research Asia | GenAI, Beijing, China, Supervisor: Dr. Dongdong Zhang, 2025.06 - Present, Research Areas: Efficient Large Language Models, Reasoning Models
- - PolyU SMART Lab, Hong Kong, China, Supervisor: Dr. Jing Li, 2022.08 - 2023.07, Research Areas: Social Media Opinion Polling, Cantonese Medical Dialogue System
- - Huawei, Shenzhen, China, Supervisor: Jingyuan Yang, 2022.06 - 2022.08, Research Areas: Extractive Document Q&A, Knowledge-enhanced Dialogue System, Chinese ASR Entity Correction
Education
- - Southern University of Science and Technology, Shenzhen, China, Ph.D. in Mathematics, 2023 - 2027, Supervisor: Dr. Guanhua Chen
- - The Hong Kong Polytechnic University, Hong Kong, China, M.Sc. in Computer Science (Data Science) with Distinction, 2021 - 2023, Top 5%, GPA: 3.8/4.0
- - Guangzhou University, Guangzhou, China, B.Sc. in Statistics, 2017 - 2021, Top 5%, GPA: 3.7/4.0
Background
- Research Interests: Efficient Methods in LLMs and Agentic Reinforcement Learning.
Miscellany
- Academic Services: Reviewer for ACL Rolling Review (ARR), Conference on Neural Information Processing Systems (NeurIPS, Top Reviewer in 2025), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), International Conference on Natural Language Processing and Chinese.
