Scholar
Weiran Huang (黄维然)
Google Scholar ID: AjJ2rf8AAAAJ
Associate Professor, Shanghai Jiao Tong University
Citations & Impact
Citations
1,961
H-index
19
i10-index
29
Publications
20
Co-authors
52
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- 2025: Paper “Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO” accepted by NeurIPS 2025
- 2025: Paper “PANTHER: Hybrid Pretraining for Billion-Scale Risk Detection via Sequential User Behavior Modeling” accepted by NeurIPS 2025
- 2025: Paper “Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization” accepted by ICML 2025
- 2025: Paper “FinLLM-B: When Large Language Models Meet Financial Breakout Trading” accepted by NAACL 2025
- 2024: Paper “Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models” accepted by NeurIPS 2024
- 2024: Paper “SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models” accepted by NeurIPS 2024
- 2024: Paper “AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering” accepted by ECCV 2024
- 2024: Six papers accepted by ICML 2024, including “Provable Contrastive Continual Learning”, “OTMatch”, “Unveiling the Dynamics of Information Interplay in Supervised Learning”, “A Statistical Theory of Regularization-Based Continual Learning”, “Information Flow in Self-Supervised Learning”, and “Matrix Information Theory for Self-Supervised Learning”
- 2024: Selected as one of 17 Microsoft Research Asia StarTrack Scholars globally
- 2023: Team won 1st place in the NeurIPS 2023 Competition “Foundation Model Prompting for Medical Image Classification Challenge 2023”
- 2023: Paper “When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method” accepted (incomplete information)
