Skip to content
conftrace_

model patching

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reverse denoising (1) open-vocabulary model (1) activation modification (1) skin cancer classification (1) open-vocabulary classification (1) mixture of prompt (1) trojan detection (1) activation patching (1) task-specific fine-tuning (1) speech language model (1)

Papers

Diffusion Model Patching via Mixture-of-Prompts AAAI 2025 SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025 Patching open-vocabulary models by interpolating weights NeurIPS 2022 Model Patching: Closing the Subgroup Performance Gap with Data Augmentation ICLR 2021 DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks IJCAI 2019