Sai Kartheek Reddy

UVSKKR

·

AI & ML interests

AI Alignment and Interpretability

Recent Activity

upvoted a paper 1 day ago

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

liked a dataset 1 day ago

UVSKKR/when-the-cot-knows-better

upvoted a paper 1 day ago

A Gravitational Interpretation of Fine-Tuning Reversion

View all activity

Organizations

Papers 6

arxiv:2606.10740

arxiv:2603.02684

arxiv:2601.03194

arxiv:2509.11648

models 0

None public yet

datasets 5

UVSKKR/when-the-cot-knows-better

Viewer • Updated Jul 7 • 14k • 12 • 3

UVSKKR/HateMirage

Updated Mar 29 • 26 • 1

UVSKKR/X-MuTeST

Updated Mar 29 • 7 • 1

UVSKKR/D-Humor

Updated Sep 17, 2025 • 5 • 2

UVSKKR/Ethical-Reasoning-in-Mental-Health-v1

Viewer • Updated Sep 17, 2025 • 125 • 357 • 4