Tal Daniel

Postdoc @ CMU Robotics Institute
Ph.D. from the Technion ECE
Research interests include self-supervsied learning, generative modeling, RL, robotics.

[Tal Daniel @TalDaniel8]

🚀 #ICLR2026 Oral 💥
How can we design world models that capture object interactions directly from pixels?
Introducing Latent Particle World Models-the first end-to-end self-supervised, object-centric world model, trained from videos, supporting action/img/lang conditioning.
1/n

[Aviv Tamar @AvivTamar1]

VLA is 95% certain about current action. Will it 95% succeed in the task?

Obviously, not necessarily. But if you’re clever, you can *calibrate* action prob. to task success.

Our #ICML2026 paper formulates this + SOTA algorithms based on new connection to RL temporal differences

[Tal Daniel @TalDaniel8]

@AvivTamar1 ❤️

[Tal Daniel @TalDaniel8]

I’m attending #ICLR2026 in Rio this week to present LPWM! Friday April 24 Poster Session 3 10:30, Oral Session 4B 3:15p. Happy to chat about self-sup object-centric learning and world models. I’ll be on the job market soon and looking for exciting opportunities!

#ICLR @iclr_conf

[Tal Daniel @TalDaniel8]

🚀 #ICLR2026 Oral 💥
How can we design world models that capture object interactions directly from pixels?
Introducing Latent Particle World Models-the first end-to-end self-supervised, object-centric world model, trained from videos, supporting action/img/lang conditioning.
1/n

[Dan Haramati @DanHrmti]

I will be at #ICLR2026 this week to present our work on Hierarchical Entity-centric Reinforcement Learning!

Come by our poster (Thursday Poster Session 2 P4-#4712) and reach out anytime to talk about #ReinforcementLearning #WorldModels #HierarchicalRL

[ML@CMU @mlcmublog]

Check out our latest post on CMU@ICLR 2026!

https://t.co/TzSd2zs4sT

[Sandeep Routray @SandeepRoutra11]

🚀 Excited to share ViPRA: Video Prediction for Robot Actions

📍 Accepted to #ICLR2026 @iclr_conf
🏆 Best Paper — #NeurIPS2025 Embodied World Models Workshop

Robot learning today still needs millions of action labeled videos.

Yet videos are abundant — from humans and the web — but lack action labels. Meanwhile, pretrained video models already learn rich dynamics.

ViPRA is a recipe for turning pretrained video models into robot policies while enabling robot learning to scale with actionless videos.
🧵 Thread ↓

[Tal Daniel @TalDaniel8]

Join us for live paper (Latent Particle World Models) overview + Q&A today (March 24) at 4pm PT / 7pm ET!
https://t.co/KRgXI2RGWe

[Cecile Tamura @ceciletamura]

🎤 Dr. @TalDaniel8 (@CarnegieMellon ) In a deep dive
w/ @ceciletamura of @ploutosai

How can AI discover objects, model uncertainty, and predict the future from raw video alone?

🔴 [https://t.co/yimiKyJeYV](https://t.co/yimiKyJeYV)

[Tal Daniel @TalDaniel8]

@DanHrmti @carl_qi98 @LambdaAPI @AvivTamar1 @davheld @pathak2206 🌐 Learn more about Latent Particle World Models (LPWM):
Website: https://t.co/nqDE1UyviV
Paper: https://t.co/cMFrfsN00p
Code (+ tutorial): https://t.co/0kJskfdm8O
16/n

[Tal Daniel @TalDaniel8]

During training, the posterior latent actions condition the dynamics module that predicts the next-frame prior.
A KL regularization term aligns this prediction with the latent policy’s output, forming a VAE-style objective over particle transitions.
7/n

[Tal Daniel @TalDaniel8]

Huge thanks to @DanHrmti, @carl_qi98, Amir Zadeh and Chuan Li (@LambdaAPI), @AvivTamar1, @davheld, and @pathak2206 — incredible collaborators who made LPWM possible.
15/n

[Tal Daniel @TalDaniel8]

The inverse dynamics observes particles at t and t+1, inferring the latent actions that caused the change.
The latent policy sees only particles at t and outputs a distribution over possible latent actions from the current state.
6/n

[Tal Daniel @TalDaniel8]

🚀 #ICLR2026 Oral 💥
How can we design world models that capture object interactions directly from pixels?
Introducing Latent Particle World Models-the first end-to-end self-supervised, object-centric world model, trained from videos, supporting action/img/lang conditioning.
1/n

[Tal Daniel @TalDaniel8]

To address this, we introduce a context module that predicts latent actions per particle, enabling fine-grained, multi-entity dynamics
It has two heads: (1) an inverse dynamics (posterior) and (2) a latent policy (prior).
5/n

[Tal Daniel @TalDaniel8]

Building a world model means capturing stochastic particle dynamics.
Existing “latent action” models help, but (1) need strong regularization (e.g., VQ) and (2) rely on a single global latent—missing interactions among multiple entities.
4/n

[Tal Daniel @TalDaniel8]

DLP decomposes scenes to particles with several attributes (keypoints, bounding-boxes, masks), fully unsupervised.
These act as visual “tokens,” making cross-modal long-horizon reasoning (vision ↔ language) far more natural than the standard pixel patches.
3/n