Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs (2026 · 6 citations)
Video-LLMs often give up on what they actually see in a video when a user pushes a wrong answer. This behaviour is called sycophancy. It has been studied for text LLMs and, to a lesser degree, for image models, but no systematic test existed for video. The authors built ViSE, a benchmark of multiple-choice questions…
Deciphering Cultural Representations in Large Language Models via Sparse Autoencoders (2026 · 1 citation)
LLMs tend to favor Western cultural defaults, and it is unclear how they store cultural knowledge internally.
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images (2026)
Multimodal LLMs often lose the safety behaviour of their text-only backbones, because harmful images can carry or amplify malicious intent past textual safeguards.

Co-authors here

3 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 7 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated 2 November 2026