McCast uses a Drift-Corrective Memory Bank to actively correct latent drift in autoregressive precipitation nowcasting for more coherent long-horizon forecasts.
Dna: Uncovering universal latent forgery knowledge
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Precise Shield identifies safety neurons in VLLMs via activation contrasts and aligns only them with gradient masking, boosting safety, preserving generalization, and enabling zero-shot cross-lingual and cross-modal transfer.
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.
citing papers explorer
-
McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting
McCast uses a Drift-Corrective Memory Bank to actively correct latent drift in autoregressive precipitation nowcasting for more coherent long-horizon forecasts.
-
Precise Shield: Explaining and Aligning VLLM Safety via Neuron-Level Guidance
Precise Shield identifies safety neurons in VLLMs via activation contrasts and aligns only them with gradient masking, boosting safety, preserving generalization, and enabling zero-shot cross-lingual and cross-modal transfer.
-
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.