Almanac
benchmark

CIFAR-10

benchmarkactivecifar-10-ff5cfc9e·2 events·first seen 1mo ago

Aliases: CIFAR-10

Co-occurring entities

More like this (12)

Recent events (2)

5arXiv · cs.LG·1mo ago·source ↗

Dynamics-Level Watermarking of Flow Matching Models with Random Codes

This paper proposes embedding watermarks directly into the velocity field (continuous dynamics) of flow matching generative models, rather than into weights or outputs. The method uses key-dependent perturbations added during training, formulated as random coding over a continuous channel, allowing black-box message recovery at detection time. The perturbation is designed to leave the generated distribution unchanged. Experiments on MNIST and CIFAR-10 demonstrate reliable message recovery, preserved generation quality, and chance-level decoding without the secret key.

4arXiv · cs.LG·14d ago·source ↗

FlashbackCL extends federated learning to mitigate temporal distribution shift and forgetting

FlashbackCL is a proposed extension to the Flashback federated learning method that addresses temporal forgetting — the degradation caused by client data distributions drifting over time, a scenario existing FL methods do not handle. The approach introduces temporally-decayed label counts, a device-aware replay buffer with Class-Balanced Reservoir Sampling, and server-side coreset curation. On CIFAR-10 with 50 clients, FlashbackCL achieves 6.9–10.0% relative improvement over Flashback while reducing temporal forgetting by up to 68%, with CBRS replay identified as the critical component.