SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
- Aladin Djuhera
- Swanand Ravindra Kadhe
- et al.
- 2025
- ICLR 2025
Workshop paper
Publications
866 results for Foundation Models
SMI-TED: A large-scale foundation model for materials and chemistry
- Eduardo Almeida Soares
- Emilio Ashton Vital Brazil
- et al.
- 2025
- ICLR 2025
Workshop paperOut-of-Distribution Detection using Synthetic Data Generation
- Momin Abbas
- Muneeza Azmat
- et al.
- 2025
- ICLR 2025
Workshop paperToken Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
- Xiaomeng Xu
- Pin-Yu Chen
- et al.
- 2025
- AAAI 2025
Conference paperRetention Score: Quantifying Jailbreak Risks for Vision Language Models
- Zaitang Li
- Pin-Yu Chen
- et al.
- 2025
- AAAI 2025
Conference paperEnhancing Decision Making Through the Integration of Large Language Models and Operations Research Optimization
- Segev Wasserkrug
- Leonard Boussioux
- et al.
- 2025
- AAAI 2025
Conference paperDilated Convolution for Time Series Learning
- Wang Zhang
- Subhro Das
- et al.
- 2025
- ICASSP 2025
Conference paperText-Guided Few-Shot Semantic Segmentation with Training-Free Multimodal Feature Matching
- Guillaume Buthmann
- Tomoya Sakai
- et al.
- 2025
- ICASSP 2025
Conference paperWhen Does Visual Prompting Outperform Linear Probing for Vision-Language Models? A Likelihood Perspective
- Hsi-Ai Tsao
- Lei Hsiung
- et al.
- 2025
- ICASSP 2025
Conference paperEpigraph Based Multilevel Optimization (EMO) for Enhancing Chain-of-Thought Reasoning Capabilities
- Songtao Lu
- Yanna Ding
- et al.
- 2025
- ICASSP 2025
Conference paper