CAST reduces object hallucination in LVLMs by 6.03% on average across five models and five benchmarks by identifying caption-sensitive attention heads and applying optimized steering directions to their outputs, with negligible added inference cost.
cc/paper_files/paper/2021/file/ 4f5c422f4d49a5a807eda27434231040-Paper
3 Pith papers cite this work. Polarity classification is still indexing.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
LAKE identifies sparse anomaly-sensitive neurons in pre-trained VLMs using minimal normal samples to build compact normality representations and achieve SOTA anomaly detection with neuron-level interpretability.
Tiny on-surface point perturbations trigger a bifurcation in the reverse diffusion process of 3D transformers, localized to a low-rank cross-attention write that can be reshaped at test time to suppress the failure.
citing papers explorer
-
CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
CAST reduces object hallucination in LVLMs by 6.03% on average across five models and five benchmarks by identifying caption-sensitive attention heads and applying optimized steering directions to their outputs, with negligible added inference cost.
-
Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
LAKE identifies sparse anomaly-sensitive neurons in pre-trained VLMs using minimal normal samples to build compact normality representations and achieve SOTA anomaly detection with neuron-level interpretability.
-
Meltdown: Circuits and Bifurcations in Point-Cloud-Conditioned 3D Diffusion Transformers
Tiny on-surface point perturbations trigger a bifurcation in the reverse diffusion process of 3D transformers, localized to a low-rank cross-attention write that can be reshaped at test time to suppress the failure.