1. Verification and Co-Alignment via Heterogeneous Consistency for Preference-Aligned LLM Annotations. ICLR 2026 (accepted).
2. Semantic Homogeneity as Demonstration: Batch-Structured Semi-Supervised In-Context Learning for Natural Language Understanding. CPAL 2026 (accepted).
3. Unlearning Misalignment for Personalized LLM Adaptation via Instance-Response-Dependent Discrepancies. Transactions on Machine Learning Research, 2025 (accepted).
4. RRInf: Efficient Influence Function Estimation via Ridge Regression for Large Language Models and Text-to-Image Diffusion Models. EMNLP 2025 (main conference; corresponding author).
5. Low-Hanging Fruit: Knowledge Distillation from Noisy Teachers for Open Domain Spoken Language Understanding. ECML-PKDD 2024, pp. 107-125 (oral).
6. Local and Global Guidance for Multi-Complementary Label Learning. IEEE CAI 2024, pp. 860-864 (poster).
Fine-Grained Partial Label Learning. IEEE CAI 2024, pp. 587-596 (spotlight).
7. Self-Teaching Prompting for Multi-Intent Learning with Limited Supervision. ICLR 2024 Tiny Papers Track (invited to present).
8. Evaluating LLMs without Oracle Feedback: Agentic Annotation Evaluation through Unsupervised Consistency Signals. Scaling Self-Improving Foundation Models without Human Supervision Workshop at ICLR 2025.
9. Layer-wise correlation and attention discrepancy distillation for semantic segmentation. Pattern Recognition, 112438,2025
