NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#cifar-100

1 stories this week · 2 this month · 4 in 6 months · mostly AI

Stories per day · 30 days

Relatedbayes-risk1 continual-learning1 dinov21 flow-matching1 generative-models1 imagenet-r1 prompt-tuning1 vision-transformer1

4 stories, newest first · one card per story

arXiv cs.AI / cs.LG / cs.CL2d ago

TEA-Prompt anchors attention for rehearsal-free continual learning

The method uses 0.38M parameters and stores Gaussian query statistics instead of old images.

continual-learning vision-transformer

arXiv cs.AI / cs.LG / cs.CL21d ago

Velocity Ambiguity Profiles split flow-matching loss by interpolation time

Guided time sampling cuts DINOv2 feature velocity loss 6.78% and Fréchet distance 23.6%, with no class-conditional KID gain.

flow-matching generative-models

1

arXiv cs.CROct 6, 2026

TwinViT-DeepJSCC: Adversarially Robust Semantic Image Communication

TwinViT-DeepJSCC defends semantic image links, gaining up to 10.8 dB PSNR under adversarial channel attacks.

adversarial-robustness semantic-communication

3

arXiv cs.AI / cs.LG / cs.CLSep 18, 2026

RACER: Role-Aligned Competence Estimation for Human-AI Routing

RACER estimates an unseen expert's instance-level competence to route queries between a model and a human.

learning-to-defer human-ai

2