Heidelberg Laureate Forum

hlforum.bsky.social

22 July 2026 14:37

💡Today, we speak with HLF alumna Letiția Pârcălăbescu @aicoffeebreak.bsky.social who will be joining us at the 13th HLF as a panelist! 🖥️🎓 During her PhD in computer science, Letitia developed tools to help multimodal LLMs complete tasks more "honestly". 👉 scilogs.spektrum.de/hlf/?p=14524

Women in AI Research - WiAIR

wiair.bsky.social

18 February 2026 18:21

🧠 Do Vision & Language Decoders Use Images and Text Equally? In our latest episode, we speak with Letitia Parcalabescu about her ICLR 2025 paper examining how vision–language *decoder* models use images and text — and how self-consistent their explanations really are. (1/8🧵)

Evangelos Kazakos

ekazakos.bsky.social

18 February 2026 18:21

Super cool work by @aicoffeebreak.bsky.social, check it out! While VLMs focus more on text than images, with CoT image contributions increase significantly!

Women in AI Research - WiAIR

wiair.bsky.social

06 February 2026 17:09

If you love @aicoffeebreak.bsky.social, this one's for you — Letitia Parcalabescu is our next guest on the #WiAIR_podcast! Stay tuned for our conversation: 🎬 YouTube: www.youtube.com/@WomeninAIRe...

Jarvin

animaznman.bsky.social

22 September 2025 14:45

I don't have time to watch all of it right now (will definitely watch it later,) but using the y output and pairing with x to make a model E reminds me of trying to get statistical importance of features for Neural Networks in general. Thanks for the video!