Aravind Reddy

Unlearning data deletions in federated fair k-means can be orders of magnitude faster than retraining, especially when entire clients are removed.

Synthesized audio-visual datasets now retain strong cross-modal semantic correspondence, boosting downstream model accuracy by over 15 percentage points and slashing distillation costs.

VLMs are prone to critical failures that vary significantly across cultures, exposing the inadequacy of Western-centric safety benchmarks.