Ashmita Bhattacharyya — accepted AI-conference papers

2026

One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models

Chris Cameron, Wangzheng Wang, Nikita Ivanov, Ashmita Bhattacharyya, Didier Chételat, Yingxue Zhang

ICML 2026poster

Looped transformers scale computational depth independent of parameter count by repeatedly applying the same layer. However, training these models over long horizons creates significant optimization challenges. Specifically, it is difficult for looped transformers that start from noise to steer towa…

Cited by 0 Source ↗Scholar ↗

2025

Leveraging Per-Instance Privacy for Machine Unlearning

Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou +2

ICML 2025poster

We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearning (Chien et al., 2024), obtaining a better utility–unlearning trade-off by replacing worst-case privacy loss bounds wi…

Cited by 0 Source ↗PDF ↗Scholar ↗