Author

Dipesh Mahato

h-index 1 View on Semantic Scholar

We have 2 of 6 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.

Preprint Aug 2026

ProxyGuard: Direct Reliability Inference for Randomized Data Release Mechanisms with Shared Targets

It is shown that the mean-only penalty is sharp and derive a smooth-score certificate with additive target concentration, and direct shared-target mode evaluates independent mechanism draws on a common target, lower-bounds their favorable-score rate, and subtracts a bound on favorable scores contributed by invalid rele...

Dipesh Mahato, Pramod Dhungana · 0 citations

Jul 2026

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

Activation steering controls model behavior by editing internal activations at inference time, and finds that a single MLP neuron is eval-correlated but not causal at both scales, and that scanning the real Pile yields a natural-text baseline competitive with the optimizer for the internal direction.

Deepanshu Mody, Samar Agarwal, Utkarsh Mittal et al. · arXiv.org · 0 citations