Conor Heins (@conorheins) 's Twitter Profile
Conor Heins

@conorheins

Working on probabilistic and bayesian machine learning at @VERSESAI. Interested in probabilistic ML, collective behavior, multi-agent systems, active inference

ID: 2290819595

calendar_today19-01-2014 02:08:21

755 Tweet

1,1K Followers

1,1K Following

Ben Koger (@ben_koger) 's Twitter Profile Photo

Are you or someone you know looking for a postdoc? Consider joining my lab at University of Wyoming where we use imaging and computer vision to study animal behavior in complex natural ecosystems. Collective behavior, salmon, migration, machine learning! kogerlab.com

IWAI (@iwai_ws) 's Twitter Profile Photo

💢5th International Conference on #ActiveInference (IWAI2024) 📷iwaiworkshop.github.io ⏰When: September 9-11, 2024 Where: Oxford University --Deadlines-- Abstract: May 24th, 2024 Submission: May 31st, 2024 Acceptance: July 14, 2024

💢5th International Conference on #ActiveInference (IWAI2024) 📷iwaiworkshop.github.io 
⏰When: September 9-11, 2024
Where: Oxford University
--Deadlines--
Abstract: May 24th, 2024 
Submission: May 31st, 2024 
Acceptance: July 14, 2024
Iain Couzin (@icouzin) 's Twitter Profile Photo

We developed ‘dynamical social clamp’ (akin to ‘patch clamp’ in neuro)—using VR—allowing realtime bidirectional feedback between real and model-controlled virtual fish. We find temporal coordination considerably impacts spatial responsiveness in groups! nature.com/articles/s4146…

Lancelot Da Costa (@lancelotdacosta) 's Twitter Profile Photo

Thrilled to share a theory of generalised coordinates for stochastic differential equations arxiv.org/abs/2409.15532 🥳 We formalise a #theory for analysing and numerically studying virtually *all* #SDEs, including those driven by coloured noise. (1/3 🧵)

Shervin Safavi (@neuroprinciples) 's Twitter Profile Photo

1/14 Happy to share our brief and sweet results on "signatures of criticality in efficient coding networks" now in PNASNews Paper: pnas.org/doi/10.1073/pn… #tweeprint 👇

Marina Papadopoulou (@marinavpap) 's Twitter Profile Photo

Excited (& a bit terrified) to officially share our #R #package with the world 🤩 swaRmverse provides a pipeline to analyze #collective #motion #data, promoting more comparative work across the Swarm-Verse 🐐🦬🐦🐒🐟 🦖🐑🕸️ With @sjmgarnier Andrew King 🙏 besjournals.onlinelibrary.wiley.com/doi/10.1111/20…

Excited (& a bit terrified) to officially share our #R #package with the world 🤩 swaRmverse provides a pipeline to analyze #collective #motion #data, promoting more comparative work across the Swarm-Verse 🐐🦬🐦🐒🐟 🦖🐑🕸️
With @sjmgarnier <a href="/SHOALgroup/">Andrew King</a> 🙏

besjournals.onlinelibrary.wiley.com/doi/10.1111/20…
VERSES (@helloverses) 's Twitter Profile Photo

Agents and Robots and Inference oh my! VERSES researchers are boots on the ground this week at NeurIPS Conference, the largest annual ML and AI research conference, where they will present 3 accepted papers and share several papers in associated workshops. Our Chief Scientist, Karl

Agents and Robots and Inference oh my!

VERSES researchers are boots on the ground this week at <a href="/NeurIPSConf/">NeurIPS Conference</a>, the largest annual ML and AI research conference, where they will present 3 accepted papers and share several papers in associated workshops.

Our Chief Scientist, Karl
Nicolas Coucke (@couckenicolas) 's Twitter Profile Photo

How can agents with simple bio-inspired brains make decisions together? This is what we simulate in our new arXiv preprint: “Collective decision making by embodied neural agents”

How can agents with simple bio-inspired brains make decisions together? This is what we simulate in our new arXiv preprint: “Collective decision making by embodied neural agents”
PNASNews (@pnasnews) 's Twitter Profile Photo

Researchers challenged longhorn crazy ants and humans with the same task: maneuvering a T-shaped object through two consecutive open doorways. Single humans always outperformed single ants, but ant groups could beat human groups. In PNAS: ow.ly/5vat50UwZAo

Researchers challenged longhorn crazy ants and humans with the same task: maneuvering a T-shaped object through two consecutive open doorways. Single humans always outperformed single ants, but ant groups could beat human groups. In PNAS: ow.ly/5vat50UwZAo
Conor Heins (@conorheins) 's Twitter Profile Photo

o3-mini-high took 19 seconds to write a .py file to simulate the Vicsek model and animate the results. Not surprising given all the other results being shared on X with bouncing ball examples + more complex physics, but still cool :)

Iain Couzin (@icouzin) 's Twitter Profile Photo

I’m thrilled to be elected as a Fellow of the Royal Society. What an honour! Would not have happened without the mentors, postdocs and students who I’ve had the privilege to learn with throughout my career. ⁦Universität Konstanz⁩ ⁦Max Planck Society uni-konstanz.de/en/university/…

VERSES (@helloverses) 's Twitter Profile Photo

VERSES® Digital Brain Beats Google’s Top AI At “Gameworld 10k” Atari Challenge. Our new AXIOM model is up to 60% better, 97% more efficient and learns 39 times faster than Google® Deepmind’s DreamerV3 in third-party validated benchmark.

Alec Tschantz (@a_tschantz) 's Twitter Profile Photo

New paper from VERSES Research - AXIOM is a world model that learns to play pixel-based arcade games in minutes. Preprint: arxiv.org/abs/2505.24784 Blog: tinyurl.com/yrvj3cay Code: github.com/VersesTech/axi… 🧵

New paper from <a href="/VERSESAI/">VERSES Research</a> - AXIOM is a world model that learns to play pixel-based arcade games in minutes.

Preprint: arxiv.org/abs/2505.24784
Blog: tinyurl.com/yrvj3cay
Code: github.com/VersesTech/axi…
🧵