Talk on MLLM

【20 July 2024】 MLLM Talk: 🍀 OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning 📷Tairan He @TairanHe99 | Carnegie Mellon University tairanhe.com 📷More mllm-ai.com #LLM #Robot

@TairanHe99 @chuang_yu_ @ppsunrise @QianqianXie727 @huang_guanyu @Siyang_Song_05 @Garyxiehd @tangjiabin7 @Jiachen_Gu

@TairanHe99 @chuang_yu_ @ppsunrise @QianqianXie727 @huang_guanyu @Siyang_Song_05 @Garyxiehd @tangjiabin7 @weizhe_lin_flmr

【7 July 2024】 MLLM Talk: 🍀 MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning 📷Xiangru Tang @XiangruTang | Yale University xiangrutang.github.io 📷mllm-ai.com #AGI #LLM

#ICRA2024 How are vision language models changing our approach to navigation and manipulation? Come find out and hang out! vlmnm-workshop.github.io

Come check out our Poster at The ACM Web Conference 2024. #TheWebConf24 - via #Whova event app

🫡 We are sorry for that. It’s been a while since we’ve released a model months ago😅, so we’re unfamiliar with the new release process now: We accidentally missed an item required in the model release process - toxicity testing. We are currently completing this test quickly and then will re-release our model as soon as possible. 🏇 ❤️Do not worry, thanks for your kindly caring and understanding.

【24 April 2024】 MLLM Talk: 🍀 In-context Learning of Large Language Model 🏂Ruiqi Zhang | University of California, Berkeley rqzhangberkeley.github.io 🧐 mllm-ai.com

Super excited about my new paper on in-context learning of linear models with transformers: arxiv.org/abs/2306.09927 The lead author on this work is Ruiqi Zhang, a super talented first-year PhD student in Statistics at UC Berkeley, and this is joint work with Peter Bartlett.

【6th April 2024】 MLLM Talk: 🍀 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models 🏂Ming Jin | Monash University mingjin.dev 🧐 mllm-ai.com

Coming MLLM Talk: 🍀 Large Language Models as Commonsense Knowledge for Large-Scale Task Planning 🏂 Zirui Zhao | National University of Singapore 1989ryan.github.io ⌚️ 7PM (GMT+8) @Singapore | 11AM (GMT+0) @London| 30th March 2024 🧐 mllm-ai.com

Just present our paper @ecir2024. As I mentioned at the end of the talk, I am looking for PhD students who have a shared interest with me on the topic of Personalisation in Conversational AI to join @SheffieldNLP. Feel free to get in touch with the details.

Interactive visualization of chatgpt completion probabilities, I ask it to to complete the prompt "When " hundreds of times.

by @tangjiabin7

Coming MLLM Talk: 🍀 Graph Language Models 📷 Jiabin Tang | Data Intelligence Lab, The University of Hong Kong 📷 12PM(GMT+0) Noon @ London Time | 24th March 2024 🧐 mllm-ai.com #LLM #ChatGPT #mllmtalk

Interested in LLM + Tool-Use, via Tree-Search? This afternoon in #NeurIPS2023, #215, I'll present "AVIS: Autonomous Visual Information Seeking with Large Language Model Agent" (blog.research.google/2023/08/autono…) Feel free to drop by and chat.

How can robots perform a wide range of skills? At #CoRL2023, we presented PlayFusion – a language-conditioned discrete diffusion model capable of performing many different tasks! 🌐play-fusion.github.io 1/n

🔥#NeurIPS2023 Tutorial🔥 Language Models meet World Models @tianminshu & I are excited to give tutorial on machine reasoning by connecting LLMs🗣️ world models🌎 agent models🤖 w/ amazing panelists @jiajunwu_cs @du_yilun Ishita Dasgupta,Noah Goodman sites.google.com/view/neurips20…

Our new RSS paper shows that neural networks can help robots plan in a kitchen faster. Our PIGINet plan feasibility classifier uses Transformer and pre-trained CLIP model to speed up task and motion planning in geometrically complex environments. @NVIDIAAIDEV @MIT_CSAIL @RSS2023