LVLMs show vocabulary hijacking by inert tokens that decode to hijacking anchors; HABI locates them, NHAR finds resilient heads, and HAVAE boosts those heads to cut hallucinations.
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
MACS improves inference speed in multimodal MoE models by entropy-weighted balancing of visual tokens and real-time modality-adaptive expert capacity allocation.
Video-LLaVA creates a unified visual representation for images and videos via pre-projection alignment, enabling mutual enhancement from joint training and strong results on image and video benchmarks.
citing papers explorer
-
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
LVLMs show vocabulary hijacking by inert tokens that decode to hijacking anchors; HABI locates them, NHAR finds resilient heads, and HAVAE boosts those heads to cut hallucinations.
-
MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
MACS improves inference speed in multimodal MoE models by entropy-weighted balancing of visual tokens and real-time modality-adaptive expert capacity allocation.
-
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
Video-LLaVA creates a unified visual representation for images and videos via pre-projection alignment, enabling mutual enhancement from joint training and strong results on image and video benchmarks.