Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
- Rickard Gabrielsson
- Jiacheng Zhu
- et al.
- 2025
- ICML 2025
Conference paper
Publications
866 results for Foundation Models
M+: Extending MemoryLLM with Scalable Long-Term Memory
- Yu Wang
- Dmitry Krotov
- et al.
- 2025
- ICML 2025
Conference paperInvariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
- Changsheng Wang
- Yihua Zhang
- et al.
- 2025
- ICML 2025
Conference paperSpeculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
- Ziyao Wang
- Muneeza Azmat
- et al.
- 2025
- ICML 2025
Conference paperSPRI: Aligning Large Language Models with Context-Situated Principles
- Hongli Zhan
- Muneeza Azmat
- et al.
- 2025
- ICML 2025
Conference paperFoundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages
- Michael Sun
- Weize Yuan
- et al.
- 2025
- ICML 2025
Conference paperDropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
- Jenny Yijian Huang
- Yunyi Shen
- et al.
- 2025
- ICML 2025
Workshop paperNoisy But Forgotten: LLM Unlearning are Robust against Perturbed Data in the Wild
- Changsheng Wang
- Yihua Zhang
- et al.
- 2025
- ICML 2025
Workshop paperLanguage Modeling with Learned Meta-Tokens
- Alok Shah
- Khush Gupta
- et al.
- 2025
- ICML 2025
Workshop paperRethinking Unlearning for Large Reasoning Models Download PDF
- Changsheng Wang
- Chongyu Fan
- et al.
- 2025
- ICML 2025
Workshop paper