3 papers
cs.CV2026
LPM 1.0: Video-based Character Performance Model
Ailing Zeng, Casper Yang, Chauncey Ge +22
Performance, the externalization of intent, emotion, and personality through visual, vocal, and temporal behavior, is what makes a character alive. Learning such performance from v…
cs.CR2025
GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors
Wenlong Meng, Shuguo Fan, Chengkun Wei +5
In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text (AIGT) detectors. GradEscape overcomes the undifferentiable computation…
cs.CV2025
ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models
Pu Zhang, Yuwei Li, Xingyuan Xian +1
As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and l…