Scholar
Chaojun Xiao
Google Scholar ID: xoC8smYAAAAJ
Postdoctoral Researcher, Tsinghua University
Citations & Impact
Citations
3,436
H-index
22
i10-index
31
Publications
20
Co-authors
13
list available
Contact
Publications
Resume (English only)
Academic Achievements
- 1. Densing Law of LLMs, Nature Machine Intelligence 2025
- 2. InfLLM-V2: Dense-sparse switchable attention for seamless short-to-long adaptation, Preprint 2025
- 3. BlockFFN: Towards end-side acceleration-friendly mixture-of-experts with chunk-level activation sparsity, COLM 2025
- 4. Document Segmentation Matters for Retrieval-Augmented Generation, ACL 2025 Findings
- 5. MiniCPM4: Ultra-efficient LLMs on end devices, Preprint 2025
- 6. APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs, ACL 2025
- 7. Ultra-FineWeb: Efficient data filtering and verification for high-quality LLM training data, Preprint 2025
- 8. InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory, NeurIPS 2024
- 9. Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training, COLING 2024
- 10. Exploring the Benefit of Activation Sparsity in Pre-training, ICML 2024
- 11. Configurable Foundation Models: Building LLMs from a Modular Perspective, Preprint 2024
- 12. Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs, EMNLP 2024
Research Experience
- Post-Doctoral Researcher, Natural Language Processing Lab, Department of Computer Science and Technology, Tsinghua University.
Education
- Ph.D., Department of Computer Science and Technology, Tsinghua University, Advisors: Professor Maosong Sun and Professor Zhiyuan Liu; B.S., Department of Computer Science and Technology, Tsinghua University.
Background
- Research Interests: Intersection of natural language processing and large-scale language models. Received doctoral and bachelor degrees from Tsinghua University.
