Lune

Profiles2024-2026

Ying Wei

Zhejiang University

16Papers
14Last author
19Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers16

  1. Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language ModelsAuthor 6 of 6ICLR 2026 · 1 citation
  2. Concept-Guided Tokenization: Closing the Gap Between Reconstruction and GenerationAuthor 4 of 4ICML 2026
  3. Plug-and-Play Compositionality for Boosting Continual Learning with Foundation ModelsAuthor 5 of 5ICLR 2026
  4. RetrOrchestrator: A Multi-Step Retrosynthesis Agent Dynamically Orchestrating Single-Step Transition ModelsAuthor 4 of 4ICML 2026
  5. A3^3E: Towards Compositional Model EditingAuthor 4 of 4NeurIPS 2025 · 3 citations
  6. Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal ModelsAuthor 3 of 3NeurIPS 2025 · 2 citations
  7. Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-ExpertsAuthor 2 of 3ACL 2025
  8. CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained ModelsAuthor 5 of 5ICLR 2025
  9. Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank AdaptationAuthor 11 of 11ICML 2025
  10. Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task GeneralizationAuthor 3 of 4NeurIPS 2025
  11. Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction TuningAuthor 8 of 8ICLR 2025
  12. DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMsAuthor 9 of 9NeurIPS 2024 · 206 citations
  13. Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion ModelsAuthor 5 of 5NeurIPS 2024 · 18 citations
  14. Learning Where to Edit Vision TransformersAuthor 5 of 5NeurIPS 2024 · 6 citations
  15. Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model EditingAuthor 6 of 6EMNLP 2024 · 1 citation
  16. Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-TuningAuthor 3 of 3NeurIPS 2024 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines