Today at #CogSci2023, I'll be presenting my #SocialVR work investigating the interactive behaviors that scaffold collaborative solution insight, using our social 'shepherding' game, and quantified using multidimensional recurrence analyses escholarship.org/uc/item/1nr…

We're thrilled to release & open-source Hunyuan3D World Model 1.0! This model enables you to generate immersive, explorable, and interactive 3D worlds from just a sentence or an image. It's the industry's first open-source 3D world generation model, compatible with CG pipelines for full editability & simulation. Set to transform game development, VR, digital content creation and so on. Get started now👇🏻 Project Page：3d-models.hunyuan.tencent.co… Try it now：3d.hunyuan.tencent.com/scene… Github：github.com/Tencent-Hunyuan/H… Hugging Face：huggingface.co/tencent/Hunyu…

We deployed 100 deep RL cruise controllers into rush-hour highway traffic to smooth traffic flow and reduce everyone’s energy consumption. Our AVs were decentralized and used standard radar, making our controllers deployable on most cars 1/n

🔮Demystifying Coordination in #LLMs: We are excited to announce LLM-Coordination, a new benchmark for the evaluation and analysis of #LLMs in Multi-agent coordination tasks. Our benchmark studies two task settings: 1. 🤖 Agentic Coordination, where LLMs act as proactive participants for cooperation in 4 pure coordination games; 2. ❓Coordination Question Answering (CoordQA), where LLMs are prompted to answer questions from coordination games for evaluation of three key reasoning abilities: Environment Comprehension, #ToM Reasoning, and Joint Planning. Interestingly, we find that LLM agents excel at coordination games where the primary challenge is common-sense reasoning about the environment 🌎 and following the rules of the game. However, they struggle at games requiring an advanced Theory Of Mind🤔 #ToM, which is the ability to reason about the beliefs and intentions of their partners! Keep Reading 🧵 for the details and discoveries! Website: eric-ai-lab.github.io/llm_co… 📜paper: arxiv.org/abs/2310.03903 🔗data & code: github.com/eric-ai-lab/llm_c…

Wrenching news: Dan Dennett has died. He's been a great friend and incredible inspiration for me throughout my career. I will miss him enormously. dailynous.com/2024/04/19/dan…

It’s amazing how many empirical features of interactions and collective response can emerge from a simple imperative: to minimize surprise. Out today in PNAS @PNASNews - with @conorheins @richardpmann Karl Friston and colleagues! @CBehav @maxplanckpress pnas.org/doi/10.1073/pnas.23…

Excited by our new perspective piece! 😊 Why is it that not all social engagement consistently increases inter-brain synchrony? Irruption theory predicts that more subjective involvement increases interference. Next step: experimentally test this idea! frontiersin.org/articles/10.…

I am really excited to reveal what @GoogleDeepMind's Open Endedness Team has been up to 🚀. We introduce Genie 🧞, a foundation world model trained exclusively from Internet videos that can generate an endless variety of action-controllable 2D worlds given image prompts.

Foundation models are well-established in vision and language, but time series forecasting has lagged behind - it still relies on dataset-specific models. Meet Lag-Llama: the first open-source foundation model for time series forecasting!

what's happening 👇

New paper from @ThaliaWheatley, me, @StolkArjen & @lukejchang at Perspectives on Psychological Science! "The Emerging Science of Interacting Minds" Read about why we think that this is a particularly auspicious moment for interaction science! Link: journals.sagepub.com/doi/10.…

Together with the Ego4D consortium, today we're releasing Ego-Exo4D, the largest ever public dataset of its kind to support research on video learning & multimodal perception — including 1,400 hours of videos of skilled human activities. Download ➡️ bit.ly/3teP49w

Today is my first day as Lecturer @PsyMQ! Excited to continue working with my colleagues and collaborators in 🧍↔️🧍, 🧍↔️🤖, and #SocialVR 🤿!

Autocurricula can produce more general agents...but can be expensive to run 💸. Today, we're releasing minimax, a JAX library for RL autocurricula with 120x faster baselines. Runs that took 1 week now take < 3 hours. Paper: arxiv.org/abs/2311.12716 github.com/facebookresearch/…

📢Just published! Our new paper looks at some of the processes people use to hear and be heard when (mis)communicating in noise 🗣️🔊Spoiler: adapt and coordinate! #CommunicationDifficulty #CommunicationBreakdowns nature.com/articles/s41598-0…

Announcing Habitat 3.0, simulating humanoid avatars and robots collaborating! - Humanoid sim: diverse skinned avatars - Human-in-the-loop control: mouse/keyboard or VR - Tasks: social navigation and rearrangement Over 1,000 steps per second on 1 GPU for large-scale learning!

Interested in #OpenScience, machine learning, motion tracking, and/or (social) signal processing? envisionbox.org has officially launched! 🚀 This is a community-driven platform for learning and sharing methods, with everything open-source (using R and Python).

RIP to Dr. Michael Turvey… an intellectual pioneer and wonderful mentor to so many. echovita.com/us/obituaries/c…

Collective Behavior from Surprise Minimization arxiv.org/abs/2307.14804 —🍿 @icouzin meets Friston! cc @C4computation