Yaxin Du
PhD Student
Shanghai Jiao Tong University
I am a Ph.D. student at Shanghai Jiao Tong University, supervised by Prof. Siheng Chen. My research focuses on building reliable and intelligent systems at the intersection of large language models and software engineering. Specifically, I work on code generation, multi-agent systems, and federated learning for LLMs. I aim to develop autonomous systems that can collaborate, and evolve in environments.
Publications
-
Under Review $ G^2 $-Reader: Dual Evolving Graphs for Multimodal Document QA
[arXiv] -
ICLR 2026 InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
-
NeurIPS 2025 Workshop SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development
[Code] -
ICML 2025 MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
-
ICLR 2025 Self-evolving Multi-agent Collaboration Networks for Software Development
-
ACL 2025 Findings Data Quality Control in Federated Instruction-tuning of Large Language Models
-
EMNLP 2025 Findings Federated Instruction Tuning of LLMs with Domain Coverage Augmentation
-
NeurIPS 2024 FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
-
ICLR 2024 Workshop Enhancing Data Quality in Federated Fine-tuning of Large Language Models
-
IET RSN 2024 Radar-based Human Activity Recognition using Denoising Techniques
-
ICLR 2024 Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
-
RadarConf 2022 A ViT Approach for Short-range Behaviour Recognition Using Radar Signals
-
CIE Radar 2021 Radar-based Human Activity Classification with Cyclostationarity
Blog
Coming soon.