iiinova — where your digital self keeps evolving

Reposted by Christian Gumbsch

Nicklas Hansen @ncklashansen.bsky.social · 26/06/2026

Super excited to share the last paper of my PhD: "Hallucination in World Models is Predictable and Preventable" ✨ We train a 350M-parameter generative world model on a large dataset spanning 210 tasks and show that we can predict *when* hallucination will happen and use that info to fix it! 🧵1/n

15514

Reposted by Christian Gumbsch

Nicklas Hansen @ncklashansen.bsky.social · 15/01/2026

Interested in ✨world models✨? I just open-sourced an implementation of the Dreamer 4 world model. It's in PyTorch and comes with a pretrained model + a neat little web interface that lets you interact with any of 30 DMControl tasks that I trained it on! Link: github.com/nicklashanse...

14912

Reposted by Christian Gumbsch

Nicklas Hansen @ncklashansen.bsky.social · 25/11/2025

🎉 New work: “Learning Massively Multitask World Models for Continuous Control” We introduce MMBench: a 200-task RL benchmark, and Newt: a language-conditioned multitask world model trained with large-scale online RL. www.nicklashansen.com/NewtWM/ Code, checkpoints, dataset etc. are open-source!

0319

Reposted by Christian Gumbsch

Max Seitzer @maxseitzer.bsky.social · 14/08/2025

Introducing DINOv3 🦕🦕🦕 A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale. High quality dense features, combining unprecedented semantic and geometric scene understanding. Three reasons why this matters👇

2269

Reposted by Christian Gumbsch

Katherine Liu @katherineliu.bsky.social · 04/08/2025

Are you working on real-to-sim, sim-to-real, learning world models, or using physics based simulators to do interesting robotics tasks? There are 15 days to the submission deadline for our CoRL workshop Learning to Simulate Robot Worlds. More details here simulatingrobotworlds.github.io/submit.html

simulatingrobotworlds.github.io

Learning to Simulate Robot Worlds

051

Reposted by Christian Gumbsch

Katherine Liu @katherineliu.bsky.social · 01/08/2025

🚀 We’re pleased to announce our workshop at CoRL 2025: Learning to Simulate Robot Worlds! Workshop website: simulatingrobotworlds.github.io The workshop aims to cover topics like physics-grounded simulation, photorealistic digital twins, AI-controlled simulators, to learned neural world models.

simulatingrobotworlds.github.io

Learning to Simulate Robot Worlds

Join the Learning to Simulate Robot Worlds workshop.

173

Reposted by Christian Gumbsch

Charley Wu @thecharleywu.bsky.social · 24/07/2025

SCMs often assume overly-dense causal graphs in dynamic settings 👉⚽🥎, since any object interaction is a potential causal edge, making them hard to scale. In joint work with @turanorujlu.bsky.social @cgumbsch.bsky.social & Martin Butz we propose a new Causal Process Model to tackle this. Thread👇

arxiv.org

Reframing attention as a reinforcement learning problem for causal discovery

Formal frameworks of causality have operated largely parallel to modern trends in deep reinforcement learning (RL). However, there has been a revival of interest in formally grounding the representati...

0207

Reposted by Christian Gumbsch

Georg Martius @gmartius.bsky.social · 19/07/2025

Sergey Levine was just presenting in the Exploration in AI @ #ICML2025 and promoted that exploration needs to be grounded, and that VLMs are a good source ;-) Check our paper below 👇

0104

Reposted by Christian Gumbsch

Georg Martius @gmartius.bsky.social · 16/07/2025

I am going to present the poster during the next poster session. 11am Wed. Poster W #707

052

Reposted by Christian Gumbsch

Seth Karten @sethkarten.ai · 14/07/2025

🚀 Launch day! The NeurIPS 2025 PokéAgent Challenge is live. @neuripsconf.bsky.social Two tracks: ① Showdown Battling – imperfect-info, turn-based strategy ② Pokemon Emerald Speedrunning – long horizon RPG planning 5 M labeled replays • starter kit • baselines. Bring your LLM, RL, or hybrid agent!

Banner reading “PokéAgent Challenge @ NeurIPS 2025” with two panels: Track 1 – Competitive Pokémon Battle Bots, Track 2 – Long-Horizon RPG Gameplay. Call-to-action: “Create video-game AI! Win prizes! Live now at pokeagent.github.io.”

185

Reposted by Christian Gumbsch

Cansu Sancaktar @cansusancaktar.bsky.social · 14/07/2025

✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs. With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk. Accepted at ICML 2025🎉 Joint work with @cgumbsch.bsky.social 🧵

1205

Reposted by Christian Gumbsch

EWRL @ewrl-org.bsky.social · 08/04/2025

Mark your calendars, EWRL is coming to Tübingen! 📅 When? September 17-19, 2025. More news to come soon, stay tuned!

03714