Lara J. Martin | @laramartin.net

I am a guest editor for a @IEEETxnOnGames special issue on LLMs and Games! If you have any work at the incredible intersection of fields, please consider submitting by December 1! transactions.games/special-issue/…

The always-amazing #In2Writng workshop will be at #NAACL2025 @naaclmeeting this time! #NLProc #HCI Paper deadline: Feb 28, 2025, AoE (no extensions!) Come submit your cool work! More: in2writing.glitch.me

As much as it was fun watching this reel (in the comments) I now better understand that #AIart and #writercommunity taking issue with what’s going on with AI being able to create character specific voicelines through AI-powered character imitation.

ngl working with @lucy3_li is one of highlights of my career 🥹 few have such amazing breadth of work from technical NLP/ML to cultural analytics 🌎 get Lucy in your department!!

IEEE Transaction on Games (ToG) is having a special issue on #LLMs and #Games, which I am a guest editor for! Papers are due December 1! More information here: transactions.games/special-issue/… #ChatGPT #procgen

@alphachar You can do an "onsite" (aka during the conference) registration for just the ACL workshops and sign up for the virtual registration: 2024.aclweb.org/registration

@LangTechLara Wow this sounds amazing! I didn't hear about it til now; is it possible to watch online somehow?

I'm excited to host the Wordplay Workshop tomorrow at #ACL2024! wordplay-workshop.github.io My co-organizers and I have pulled together a great line up of guest speakers + come check out the amazing poster presentations from work in language & games!

First Microsoft, now Google are failing to meet their climate targets, citing AI's electricity use: "Rather than declining, [Google's] emissions grew 13% in 2023 over the year before. Compared to [...] 2019, emissions have soared 48%." This is what we should be concerned about, not AGI.

Hello community, we are looking for a few emergency reviewers to help reviewing some papers within 2 days. Please email us at wordplay.workshop.organizers@gmail.com to let us know your OpenReview account if you are willing to help! Thanks!

So proud to have hooded my first five PhDs today: @tuvllms, @kalpeshk2011, @simeng_ssun, @mrdrozdov, and Nader Akoury. Now, they're either training LLMs at Google, Nvidia, and Databricks, or staying in academia at Virginia Tech and Cornell. Excited to watch their careers blossom!

We are very excited to announce our new work: "Word2World: Generating Stories and Worlds through Large Language Models" [arxiv.org/abs/2405.06686]. All the thanks to my supervisors Dr. Steven James and Prof. @togelius. Word2World is an LLM-based text-to-env, game-design system.

Happy to share that I just put our D&D FIREBALL (aclanthology.org/2023.acl-long.…) data up on HuggingFace🤗! huggingface.co/datasets/lara-… It's a cool dataset that I'd love to see more people using. It contains structured state information and narrative to help make D&D-playing AI!

I'm excited to co-organizing the WordPlay workshop at #ACL2024. You still have 3 weeks to prepare your submission and papers accepted/undersubmission to other venues are welcome! Look forward to seeing you in Bangkok!!

Reminder that there's only a couple more weeks (May 31) until the deadline for the Wordplay: When Language Meets Games workshop at ACL in Bangkok!! Submit all your papers on language agents, simulations, narrative, AI for games, and more!!

🏳️‍⚧️📱Participate in a design workshop for trans technology! Design future technologies with members of the trans community! 📼🏳️‍⚧️screening survey: bit.ly/TransTech2024

Very excited to finally put out my work on #AAC (communication accessibility) devices for autistic adults. Working with masters student Malathy Nagalakshmi during my postdoc at Penn, we did a deep dive into how AAC can be improved from both society & tech. arxiv.org/abs/2404.17730

I'd also like to commend @zhuexe for getting the NSF's GRFP! The folks at Penn are on 🔥fire🔥!

We've got a new study comparing AI directors, please take part and help spread the word! Info in images below and in follow-up tweets.

ChatGPT plays text games at the same level as KG-A2C, an RL language agent I made 5+ years ago with ~5 million params. They're puzzles that need perfect reasoning over thousands of steps in language A surprising result & a limitation of LLM agents rn👇 arxiv.org/abs/2304.02868

Our work "This Land is {Your, My} Land: Evaluating Geopolitical Biases in LMs" has been accepted to NAACL 2024 🇲🇽! TL;DR LLMs are inconsistent across languages & prompts can amplify/mitigate this🌐 Paper arxiv.org/abs/2305.14610 Code github.com/manestay/borde… @samarhdr @upennnlp