ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Ashwinee Panda

Ashwinee Panda

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

6

papers

380

total citations

papers (6)

Safety Alignment Should be Made More Than Just a Few Tokens Deep

Differentially Private Image Classification by Learning Priors from Random Processes

NEURIPS 2023arXiv

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

Gemstones: A Model Suite for Multi-Faceted Scaling Laws

NEURIPS 2025arXiv

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models