[11/18/2025] SWE-bench Verified and Multilingual now only accepts submissions from academic teams and research institutions with open source methods and peer-reviewed publications. Click to read full ...

Abstract: Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries.

A mechanistic understanding of how MLPs do computation in deep neural networks remains elusive. Current interpretability work can extract features from hidden activations over an input dataset but ...