Sai Kartheek Reddy

UVSKKR

·

AI & ML interests

AI Alignment and Interpretability

Recent Activity

upvoted a paper 10 days ago

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

liked a dataset 10 days ago

UVSKKR/when-the-cot-knows-better

updated a dataset 4 months ago

UVSKKR/when-the-cot-knows-better

View all activity

Organizations

New activity in UVSKKR/Ethical-Reasoning-in-Mental-Health-v1 about 1 year ago

Update task categories and add paper link

#2 opened about 1 year ago by

commented 2 papers about 1 year ago

EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

Paper • 2509.11648 • Published Sep 15, 2025 • 2 •

D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

Paper • 2509.06771 • Published Sep 8, 2025 • 6 •

commented a paper over 1 year ago

Deceptive Humor: A Synthetic Multilingual Benchmark Dataset for Bridging Fabricated Claims with Humorous Content

Paper • 2503.16031 • Published Mar 20, 2025 • 3 •