Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Can AI Really Grasp Difficulty? A New Benchmark for LLMs

Mucong Ding|Chenghao Deng|Jocelyn Choo|Zichu Wu|Aakriti Agrawal|Avi Schwarzschild|Tianyi Zhou|Tom Goldstein|John Langford|Anima Anandkumar|Furong Huang

Why AI Struggles With Specific Questions (And How To Fix It)

Saptarshi Sengupta|Wenpeng Yin|Preslav Nakov|Shreya Ghosh|Suhang Wang

Unlocking Insights from Mountains of Data: How AI Masters Multi-Document Summarization

Aditi Godbole|Jabin Geevarghese George|Smita Shandilya

Do We Really Need Domain-Specific Embeddings in the Age of LLMs?

Yixuan Tang|Yi Yang

Unlocking AI's Potential: A Deep Dive into Goal-Oriented Agents

Mareike Hartmann|Alexander Koller

Supercharging AI: Teaching Multimodal Models to Learn More With Less

Hongzhe Huang|Jiang Liu|Zhewen Yu|Li Cai|Dian Jiao|Wenqiao Zhang|Siliang Tang|Juncheng Li|Hao Jiang|Haoyuan Li|Yueting Zhuang

Unlocking AI Potential: The Power of Span-Level Ensembling

Yangyifan Xu|Jianghao Chen|Junhong Wu|Jiajun Zhang

Can LLMs Build Decision Trees From Scratch?

Ricardo Knauer|Mario Koddenbrock|Raphael Wallsberger|Nicholas M. Brisson|Georg N. Duda|Deborah Falla|David W. Evans|Erik Rodner

Revolutionizing Grading: Can AI Score Your Next Test?

Gérôme Meyer|Philip Breuer|Jonathan Fürst

The first platform built for prompt engineering