← Search

Akshit Achara

2 accepted papers

2026

Multi-Way Representation Alignment

ICML 2026poster

The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces. However, current strategies for mapping these representations are inherently pairwise, scaling quadratically with the number of models and failing to yield a con…

Cited by 0SourceScholar
2025

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers

NAACL 2025short

AI Safety Moderation (ASM) classifiers are designed to moderate content on social media platforms and to serve as guardrails that prevent Large Language Models (LLMs) from being fine-tuned on unsafe inputs. Owing to their potential for disparate impact, it is crucial to ensure that these classifiers…