Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Unlocking the Power of LLMs for Smarter Recommendations

Xinfeng Wang|Jin Cui|Fumiyo Fukumoto|Yoshimi Suzuki

Can AI Hallucinate Even With the Facts? Introducing FaithEval

Yifei Ming|Senthil Purushwalkam|Shrey Pandit|Zixuan Ke|Xuan-Phi Nguyen|Caiming Xiong|Shafiq Joty

Can LLMs Be Hacked? Exploring Backdoor Threats to AI

Qin Liu|Wenjie Mo|Terry Tong|Jiashu Xu|Fei Wang|Chaowei Xiao|Muhao Chen

Do Influence Functions Really Work on Large Language Models?

Zhe Li|Wei Zhao|Yige Li|Jun Sun

Leaking Secrets: Timing Attacks Expose LLM Vulnerabilities

Linke Song|Zixuan Pang|Wenhao Wang|Zihao Wang|XiaoFeng Wang|Hongbo Chen|Wei Song|Yier Jin|Dan Meng|Rui Hou

Unlocking Speech AI's Potential: Instruction-Following Without Specific Training

Ke-Han Lu|Zhehuai Chen|Szu-Wei Fu|Chao-Han Huck Yang|Jagadeesh Balam|Boris Ginsburg|Yu-Chiang Frank Wang|Hung-yi Lee

Unlocking AI’s Potential: Understanding Long Videos

Hongchen Wei|Zhenzhong Chen

Beyond Grades: How AI Gives Personalized Feedback

Menna Fateen|Bo Wang|Tsunenori Mine

How to Fix AI’s Bad Recommendations

Guixian Zhang|Guan Yuan|Debo Cheng|Lin Liu|Jiuyong Li|Shichao Zhang

The first platform built for prompt engineering