Oliver Lemon ( @oliverlemon@sigmoid.social ) (@oliverlemon) 's Twitter Profile
Oliver Lemon ( @[email protected] )

@oliverlemon

Chief AI Officer and Co-founder, Alana AI Ltd.
Academic Co-Lead of UK National Robotarium.
Professor, Director of Interaction Lab: conversational AI and LLMs.

ID: 149096802

linkhttp://sites.google.com/site/olemon calendar_today28-05-2010 12:00:55

2,2K Tweet

2,2K Takipçi

2,2K Takip Edilen

Oliver Lemon ( @oliverlemon@sigmoid.social ) (@oliverlemon) 's Twitter Profile Photo

Looking to do PhD in AI ? Our new CDT program in Dependable and Deployable AI for Robotics (CDT-D2AIR) offers funded PhDs & a supportive research environment Interaction Lab Edinburgh Robotics The National Robotarium #GenAI #NLProc #HRI #Conversational_AI #PhD edinburgh-robotics.org/apply

Oliver Lemon ( @oliverlemon@sigmoid.social ) (@oliverlemon) 's Twitter Profile Photo

In the last year our PhD students Interaction Lab achieved: finalists in Amazon Alexa Simbot challenge; Best Demo paper at EACL; papers at NAACL, HRI, NeurIPS, EMNLP, SIGDIAL, Interspeech … full list at sites.google.com/site/hwinterac…

Andreas Vlachos (@vlachos_nlp) 's Twitter Profile Photo

Interested in fact-checking? Just announced: Next FEVERworkshop at EMNLP shared task: fever.ai/task.html aiming to evaluate systems verifying real-world claims with evidence from the Web, based on the AVERITEC dataset: arxiv.org/abs/2305.13117 With the amazing team:

Andreas Vlachos (@vlachos_nlp) 's Twitter Profile Photo

The call for papers for the 7th FEVERworkshop at #EMNLP is out: fever.ai/workshop.html Deadline for ARR and non-ARR papers on August 15th! And the deadline for the new shared task on real-world #factchecking using the AVERITEC dataset is July 20th fever.ai/task.html !

Oliver Lemon ( @oliverlemon@sigmoid.social ) (@oliverlemon) 's Twitter Profile Photo

Very excited about this new embodied AI model from the fantastic team Alana -- outperforming Claude 3 and Gemini Pro Vision 1.0 on the OpenEQA benchmark

Malvina Nikandrou (@mnikandrou) 's Twitter Profile Photo

🚀 Excited to share our latest paper: "Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillation"! Paper: arxiv.org/abs/2406.19297 (1/5)

🚀 Excited to share our latest paper: "Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillation"!

Paper: arxiv.org/abs/2406.19297 (1/5)
Alessandro Suglia (@ale_suglia) 's Twitter Profile Photo

We decided to understand how resilient robotics foundation models are to different input perturbations when performing robot manipulation tasks. The answer? Not so much! See the thread below for more info and read our paper for details: arxiv.org/abs/2407.03967

Alessandro Suglia (@ale_suglia) 's Twitter Profile Photo

LLMs are great but they are brittle to minimal prompt perturbations (e.g., typos, indentation, ...). Q: How do we create truly multimodal foundation models? A: Do as we humans do: text as visual perception! Enter PIXAR, our work at #ACL2024NLP! arxiv.org/abs/2401.03321

Raffaella Bernardi (@raffagbernardi) 's Twitter Profile Photo

📢 #NLP Are you interested in the wonderful SemDial 2024 Program semdialmeeting, organized by CIMeC UniTrento, but cannot travel to Italy? Upon request, we've opened the registration form for online participation. Hurry up, it closes on September 5 event.unitn.it/semdial2024/