Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Taming Wild LLMs: How PaCE Keeps AI Safe and Sane

Jinqi Luo|Tianjiao Ding|Kwan Ho Ryan Chan|Darshan Thaker|Aditya Chattopadhyay|Chris Callison-Burch|René Vidal

Unlocking High-Res Vision in Multimodal AI: The DeepStack Approach

Lingchen Meng|Jianwei Yang|Rui Tian|Xiyang Dai|Zuxuan Wu|Jianfeng Gao|Yu-Gang Jiang

Unlocking Visual How-Tos: AI Generates Step-by-Step Guides

Quynh Phung|Songwei Ge|Jia-Bin Huang

Unlocking AI’s Potential: Teaching LLMs to Learn From Themselves

Dongyoung Kim|Kimin Lee|Jinwoo Shin|Jaehyung Kim

Can AI Have Morals? A New Benchmark Puts LLMs to the Test

Jianchao Ji|Yutong Chen|Mingyu Jin|Wujiang Xu|Wenyue Hua|Yongfeng Zhang

See Clearly, Hear Clearly: How AI Reads Lips to Understand Speech in Noise

Sreyan Ghosh|Sonal Kumar|Ashish Seth|Purva Chiniya|Utkarsh Tyagi|Ramani Duraiswami|Dinesh Manocha

Why ChatGPT Can’t Find What Google Can (And What This Means for Search)

Sruti Srinivasa Ragavan|Mohammad Amin Alipour

Unlocking AI's Potential: Reasoning in Code Editing

Alexander Kovrigin|Aleksandra Eliseeva|Yaroslav Zharov|Timofey Bryksin

Human-Guided AI Learns to Drive: A New Path to Safe Self-Driving Cars

Yuan Sun|Navid Salami Pargoo|Peter J. Jin|Jorge Ortiz

The first platform built for prompt engineering