DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
LoRA: Low-rank adaptation of large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
M⁴-SAM equips SAM2 with modality-aware MoE-LoRA, gated multi-level fusion, and pseudo-guided initialization to reach state-of-the-art on RGB-D video salient object detection.
citing papers explorer
-
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
-
M$^4$-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection
M⁴-SAM equips SAM2 with modality-aware MoE-LoRA, gated multi-level fusion, and pseudo-guided initialization to reach state-of-the-art on RGB-D video salient object detection.