AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 4 of 21 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
It is found that although several guard models are nearly calibrated on clean inputs, adversarial attacks degrade their calibration by an order of magnitude, turning false negatives into high-confidence errors indistinguishable from correct detections, highlighting a mismatch between guard confidence and base model unc...
Rigorous expert validation confirms seed plausibility and realism for meaningful LLM safety evaluation, and provides an expert-validated, finance-specific rubric that goes beyond disclaimer checks, aligns more closely with human experts than static one-size-fits-all rubrics, and reduces critical false negatives from 28...
SSDi8 is presented, the first post-training quantization framework specifically designed for SSD to maintain a persistent INT8 path, and introduces a reformulation that decouples element-wise multiplications from matrix multiplications, enabling reuse of quantized activations across modules.
A retraining-free VLM pruning framework called PORTA is introduced that derives a task- and modality-agnostic importance formulation based on activation variation, estimated from generic calibration data, which reliably captures feature-level representation utility across modalities.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.