A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 7roles
dataset 1polarities
use dataset 1representative citing papers
SIGMA-ASL is a multimodal dataset with 93,545 word-level ASL clips from Kinect RGB-D, mmWave radar, and dual IMUs, plus benchmarking protocols for single- and multi-modal recognition.
DynLP is a parallel dynamic batch update algorithm for label propagation that achieves significant speedups by updating only relevant parts of the graph on GPUs.
UAU-Net improves facial action unit detection by modeling uncertainty at both representation learning via conditional VAE and evidential classification via asymmetric Beta network.
citing papers explorer
-
What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers
A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.
-
SIGMA-ASL: Sensor-Integrated Multimodal Dataset for Sign Language Recognition
SIGMA-ASL is a multimodal dataset with 93,545 word-level ASL clips from Kinect RGB-D, mmWave radar, and dual IMUs, plus benchmarking protocols for single- and multi-modal recognition.
-
DynLP: Parallel Dynamic Batch Update for Label Propagation in Semi-Supervised Learning
DynLP is a parallel dynamic batch update algorithm for label propagation that achieves significant speedups by updating only relevant parts of the graph on GPUs.
-
UAU-Net: Uncertainty-aware Representation Learning and Evidential Classification for Facial Action Unit Detection
UAU-Net improves facial action unit detection by modeling uncertainty at both representation learning via conditional VAE and evidential classification via asymmetric Beta network.
- HeadRoom: Lightweight, Edge-deployable Pipeline for Adaptive Notification Routing
- Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution
- SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis