PAR fine-tunes CLIP to remove backdoors from structured triggers while preserving standard performance, and works even with only synthetic image-text pairs.
Gonzalez, Ion Stoica, and Eric P
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
LLaVA-Octopus introduces instruction-driven adaptive fusion of multiple visual projectors in a multimodal LLM to improve video understanding performance.
citing papers explorer
-
Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
PAR fine-tunes CLIP to remove backdoors from structured triggers while preserving standard performance, and works even with only synthetic image-text pairs.
-
LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
LLaVA-Octopus introduces instruction-driven adaptive fusion of multiple visual projectors in a multimodal LLM to improve video understanding performance.