Maxime Kayser

@glasgowfilmfest @TronTheatre Hi, is not possible to buy two tickets for each film with a cinecard?

Are you a GFT CineCard holder? Well it’s your lucky day, because you can now access tickets to the full GFF25 Programme! 🎉 Pick your favs and book now here: bit.ly/GFF25_alllisti… General sale commences Monday 27 Jan at 10:00. Costumes by @trontheatre

Are you scared users might misappropriate your LLM system? 😱 We were scared too! Now we introduce adversarial certificates on the misuse of LLMs. 🤖 Come and see our poster @solarneurips tomorrow. #NeurIPS2024 #NeurIPS #AI #NLP #LLM #DomainCertification #Shhhhhhhh

🥳🎉Incredibly happy that our paper received an ✨Outstanding Paper Award✨ at #EMNLP2024! Huge congrats particularly to @maximek3, who did an incredible job! So lucky to have you as my student! Check out our paper below ⬇️

@oanacamb @neuralisa @CorEmde @RayscapeAI @UniofOxford and of course to Susanne Gaube, Bogdan Bercean, Thomas Lukasiewicz, Alex Novak, Abdala Espinosa, Bartlomiej W. Papiez, and all 85 study participants

Huge thanks to @oanacamb @neuralisa @CorEmde @RayscapeAI @UniofOxford

Are self-rationalizing VLMs helpful in a real-world, safety-critical setting? In our new #EMNLP2024 paper 🩺 we recruited 85 medics 🩻 and made them each collaborate with an AI on 80 X-rays under 4 different XAI scenarios arxiv.org/abs/2410.12284 It turns out that: 🧵 (1/n)

There are openings to come work with us on robots and recovery :)! Apply below or ping me if you are interested about doing applied research around robots :) Great chances to do some research before doing a PhD if you are not sure yet whether research if for you. 🤖🦎

@vegancokee Love it

📏 Benchmarking different approaches We adapt several models for this new task and compare their performance using automatic and clinician-based evaluations. The results indicate that this is a promising new direction for explaining automated medical image analysis. (5/5)

🗂 Introducing MIMIC-NLE We investigate this by proposing MIMIC-NLE, a high-quality dataset of 44,935 image-diagnosis-NLE triplets extracted from the radiology reports in MIMIC-CXR. The dataset is available at github.com/maximek3/MIMIC…. (4/5)

✨New Paper✨ at #MICCAI2022🩺 🔎 Explaining Chest X-ray Pathologies in Natural Language arxiv.org/abs/2207.04343 with @CorEmde, @oanacamb, Guy Parsons, @bwpapiez, and Thomas Lukasiewicz @UniofOxford #ML #MedicalImaging #Xray #XAI #NLProc (1/5)