Tal Daniel

Postdoctoral Researcher · ML & Robotics

Postdoctoral Fellow at the Carnegie Mellon University Robotics Institute, working with Prof. Deepak Pathak and Prof. David Held. Research spanning unsupervised & self-supervised representation learning, generative modeling, reinforcement learning, and robotics.

Ph.D. from the Technion ECE Department, advised by Prof. Aviv Tamar. B.Sc. and M.Sc. both in ECE from the Technion (Cum Laude / Summa Cum Laude).

Fellowships

2024 Irwin & Joan Jacobs Ph.D. Excellence Fellowship

2023 Miriam & Aaron Gutwirth Memorial Ph.D. Excellence Fellowship

✉ tdaniel at andrew dot cmu dot edu

Publications & Pre-Prints

Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling

Tal Daniel, Carl Qi, Dan Haramati, Amir Zadeh, Chuan Li, Aviv Tamar, Deepak Pathak and David Held

ICLR 2026 Oral

TL;DR — A self-supervised object-centric world model that learns keypoints, and masks directly from videos, supports multi-modal conditioning, scaled to real-world multi-object datasets

Paper Website Code Video

Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion

Dan Haramati, Carl Qi, Tal Daniel, Amy Zhang, Aviv Tamar and George Konidaris

ICLR 2026

TL;DR — An entity-centric hierarchical RL framework using diffusion subgoals for improved long-horizon tasks.

Paper Website Code Video

EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation

Carl Qi, Dan Haramati, Tal Daniel, Aviv Tamar and Amy Zhang

ICLR 2025

TL;DR — Multi-object control policies for robotics from pixels using deep latent particles (DLP) and diffusion models.

Paper Website Code

DDLP: Unsupervised Object-centric Video Prediction with Deep Dynamic Latent Particles

Tal Daniel and Aviv Tamar

TMLR 2024

TL;DR — Object-centric video prediction, generation, and modification via the deep latent particle (DLP) representation.

Paper Website Code Video

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

Dan Haramati, Tal Daniel and Aviv Tamar

ICLR 2024 Spotlight

TL;DR — Using DLP instead of raw pixels unlocks compositional capabilities in reinforcement learning.

Paper Website Code Video

Unsupervised Image Representation Learning with Deep Latent Particles

Tal Daniel and Aviv Tamar

ICML 2022 Spotlight

TL;DR — Represent images as latent particles for unsupervised object detection, segmentation, and manipulation.

Paper Website Code Video

Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder

Tal Daniel and Aviv Tamar

CVPR 2021 Oral Best Paper — MLIS-TCE 2022

TL;DR — Stable adversarial VAE training without a discriminator; applicable to density estimation, image generation, OOD detection, and more.

Paper Website Code Video

Deep Variational Semi-Supervised Novelty Detection

Tal Daniel, Thanard Kurutach and Aviv Tamar

NeurIPS 2021 Workshop — Deep Generative Models

TL;DR — Principled incorporation of negative samples in the VAE framework for meaningful representations.

Paper

Beyond Credential Stuffing: Password Similarity Models Using Neural Networks

Bijeeta Pal, Tal Daniel, Rahul Chatterjee and Thomas Ristenpart

IEEE S&P 2019

TL;DR — Cracking passwords with neural networks — and building defenses against such attacks.

Paper

Teaching

Course materials from my time at the Technion — all freely available on GitHub. Tutorials are in Jupyter Notebook format with theory, Python & PyTorch code, and PDF versions.

ECE 046211 — Deep Learning

2021 – 2024

CNNs, RNNs, Transformers, AutoDiff, Self-Supervised Learning, Transfer Learning & more.

GitHub Projects Videos

ECE 046746 — Computer Vision

Spring 2020, Spring 2021

Image Processing, Segmentation, Object Detection & Tracking, GANs, 3D Deep Learning.

GitHub

ECE 046202 — Unsupervised Learning & Data Analysis

Winter 2020, Winter 2021

PCA, t-SNE, VAE, GAN, Clustering, Hypothesis Testing.

GitHub

CS 236756 — Introduction to Machine Learning

Spring 2019, Spring 2020

Linear Models, Decision Trees, SVM, EM, Boosting, PAC Learning, Deep Learning intro.

GitHub

Tal Daniel

Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling

Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion

EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation

DDLP: Unsupervised Object-centric Video Prediction with Deep Dynamic Latent Particles

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

Unsupervised Image Representation Learning with Deep Latent Particles

Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder

Deep Variational Semi-Supervised Novelty Detection

Beyond Credential Stuffing: Password Similarity Models Using Neural Networks

ECE 046211 — Deep Learning

ECE 046746 — Computer Vision

ECE 046202 — Unsupervised Learning & Data Analysis

CS 236756 — Introduction to Machine Learning

Interactive GUI for Deep (Dynamic) Latent Particles — D(D)LP

Latent Space Interpolation: Airplane → Car (3D Soft-IntroVAE)

Interactive Beta Distribution Applet

Python: Pencil Drawing by Sketch & Tone (Lu et al., NPAR 2012)

PyTorch: Least-Squares DQN (DuelingDQN, Boosted FQI)

TensorFlow: Bayesian Gradient Descent (Zeno et al., 2019)

Android App: Scrypt Coin (Litecoin) Miner with Custom Options