CAGE attack aligns perturbations with token compression to achieve lower robust accuracy on compressed LVLMs than baseline attacks across mechanisms and datasets.
DART: Dif- ferentiable dynamic adaptive region tokenizer for vision foundation models.arXiv preprint arXiv:2506.10390
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Adaptive patching for time-series Transformers yields no consistent gain over a tuned uniform baseline on long-horizon benchmarks once evaluated with fixed backbones.
citing papers explorer
-
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
CAGE attack aligns perturbations with token compression to achieve lower robust accuracy on compressed LVLMs than baseline attacks across mechanisms and datasets.
-
Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting
Adaptive patching for time-series Transformers yields no consistent gain over a tuned uniform baseline on long-horizon benchmarks once evaluated with fixed backbones.