Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Published 6 papers (according to Google Scholar).
Paper 'gigiProfiler: Diagnosing Performance Issues by Uncovering Application Resource Bottlenecks' introduces OmniResource Profiling to diagnose bottlenecks using hybrid LLM-static analysis.
Published 'Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation' at ICCV 2025.
Two papers accepted at AAAI 2025: 'SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression' and 'Towards Efficient Low-order Hybrid Optimizer for Language Model Fine-tuning'.
Published 'MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition' at ICML 2025.
Oral presentation at WWW 2025: 'When Large Vision Language Models Meet Multimodal Sequential Recommendation: An Empirical Study', introducing MSRBench and Amazon Review Plus dataset.
Published 'Is contrastive learning necessary? a study of data augmentation vs contrastive learning in sequential recommendation' at WWW 2024.
Published 'StyleTerrain: A novel disentangled generative model for controllable high-quality procedural terrain generation' in Computers & Graphics, applying disentangled representation learning to GAN-based terrain generation.