VeilTune fine-tunes LoRA adapters entirely inside secure MPC
From one 32-sample mini-batch of hidden states, authors copied a provider adapter on 99.2% of test inputs.
Stories per day · 30 days
4 stories, newest first · one card per story
Stories tagged #roberta
Intrinsic-Extrinsic Coupling in Learning Dynamics
Researchers show replay can erase a classifier-head intervention's gains, formalizing intrinsic-extrinsic coupling in learning.
Linguistic Features for Interpretable Textual Entailment
SLITE uses 17 linguistic features for textual entailment, reaching 83% on SICK and nearing RoBERTa.
Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents
Fine-tuned RoBERTa-large task permission classifier matches Claude Haiku 4.5 on access scoping for AI agents, cutting severity-weighted attack surface by 84.4%.