Matthias Gerstgrasser
@MGerstgrasser
Followers
157
Following
49
Media
7
Statuses
57
I teach AIs to play nice with each other, and sometimes with us humans.
Palo Alto, CA
Joined July 2018
RT @RylanSchaeffer: 📢New preprint📢. 🔄Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World 🔄. A deeper dive….
0
48
0
RT @zswitten: On one end of the line: ELIZA, the psychotherapist from the 60s. First chatbot to make people believe it was human. Rulebound….
0
198
0
RT @RylanSchaeffer: I sadly couldn't attend #ICML2024 but our paper received ✨Outstanding Paper ✨ at the @TiFA_ICML2024 workshop!. 📈🤔 Why H….
0
25
0
RT @DMLRWorkshop: thank you authors, reviewers and speakers for your contributions to a great DMLR @icmlconf. presentations by @AdtRaghunat….
0
9
0
Joint work with @RylanSchaeffer. @ApratimDey2. @rm_rafailov. @sanmikoyejo. @danintheory. @Andr3yGR. @Diyi_Yang. David Donoho @___rajashree___. @tomekkorbak. @sleight_henry. @McHughes288. @dhruv31415. 3/3.
0
0
5
Friday 14:30: FM-WILD poster session.Saturday 11:00: DMLR panel discussion.Saturday 14:45: DMLR talk. Preprint: 2/n.
2
1
6
Are you worried that training your generative AI models on synthetic data will lead to bad things happening? Are you at ICML this week? Join us at the DMLR and FM-WILD workshops, where I'll be talking about our most recent work on model collapse, and how there is hope yet! 1/n.
7
5
15
Huge thanks to my fantastic co-authors @RylanSchaeffer @ApratimDey2 @rm_rafailov @sanmikoyejo @danintheory @Andr3yGR @Diyi_Yang David Donoho @___rajashree___ @tomekkorbak @sleight_henry @McHughes288 @dhruv31415.
0
0
7
Excited that our paper on model collapse has been accepted @COLM_conf . Is model collapse inevitable? As we show: No! It may well not be as catastrophic as feared in practice. Preprint:
Woke up to find out our paper was accepted at @COLM_conf !!. 📉📉 Is Model Collapse Inevitable? 📉📉. No! Model collapse is largely avoided if data accumulate over model-fitting iterations. Previous papers found model collapse by discarding all data after each iteration. 1/2
2
7
9
Really amazing work by awesome people. Very excited to see what people will make with this.
Super excited to share what I’ve been working on: @odysseyml! . We’re building Hollywood-grade visual AI, to enable storytellers to create new, amazing movies, TV shows, and video games. We believe this technology is what comes after text-to-video. More below.👇
0
0
0
UoE's fantastic multi-agent RL talk series is now available on youtoube for free - fantastic resource for anyone wanting to get up to speed with the latest research. (Including my own talk on SUPER: ).
(1/2) Exciting news - our RL Reading Group meetings will now be on YouTube 🎉 Subscribe to stay up-to-date with SOTA RL research: Our (virtual) meetings are open to all, sign up here!
0
0
2
Excited to be speaking at the AI Talk Series about Generative AI and LLMs in San Mateo tonight!.
Join our Gen AI and LLM talk today in San Mateo to connect with fellow AI founders and engineers from Stanford, Harvard and MIT building the future:.
0
0
3
RT @RylanSchaeffer: @nvidia announces Nemotron 340B, designed explicitly for producing synthetic data to train other models!. https://t.co/….
0
2
0
RT @RylanSchaeffer: Come join @MGerstgrasser and I TODAY at 9 am PT / 12 pm ET to discuss our recent preprint "Is Model Collapse Inevitable….
0
3
0
tacheles isn’t meant to replace existing general-purpose LLM UIs, but to give you a solid foundation on which to build your own custom & specialized apps. 🏗️ It’s designed to be extensible and easy to understand, with core features in just a couple hundred lines of code. 💡 4/4.
0
0
0
Streaming responses? ✅ Markdown Rendering? ✅ Inference through vllm, sglang or OpenAI?✅ Dockerized & scalable setup? ✅ Complete unit and end-to-end tests? ✅ Development through docker? ✅ (You want to write a web app but don’t want javascript touching your host OS? ✅) 3/4.
1
0
0
Originally an internal tool for one of my research projects, I’ve decided to release this as a standalone project to help others get started faster! tacheles includes a lightweight but complete LLM chat UI and backend, plus all the scaffolding for development and deployment.🚀2/4.
1
0
0
💬Have you wanted to build an LLM chat app but don’t know where to start? I’ve done all the tedious bits for you! 🔧Check out 1/4.
1
2
7
@RylanSchaeffer @ApratimDey2 @rm_rafailov @sanmikoyejo @danintheory @Andr3yGR @Diyi_Yang @___rajashree___ @tomekkorbak @sleight_henry @McHughes288 @dhruv31415 Work done at / supported by @StanfordAILab @hseas and @coop_ai and others.
0
0
6