Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder

2 code implementations • CVPR 2021 • Tal Daniel, Aviv Tamar

However, the original IntroVAE loss function relied on a particular hinge-loss formulation that is very hard to stabilize in practice, and its theoretical convergence analysis ignored important terms in the loss.

Image Generation Out-of-Distribution Detection

Unsupervised Image Representation Learning with Deep Latent Particles

1 code implementation • 31 May 2022 • Tal Daniel, Aviv Tamar

We propose a new representation of visual data that disentangles object position from appearance.

Image Manipulation Model Selection +3

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

1 code implementation • 9 Jun 2023 • Tal Daniel, Aviv Tamar

We propose a new object-centric video prediction algorithm based on the deep latent particle (DLP) representation.

Object Position +2

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

1 code implementation • 1 Apr 2024 • Dan Haramati, Tal Daniel, Aviv Tamar

Manipulating objects is a hallmark of human intelligence, and an important task in domains such as robotics.

reinforcement-learning Reinforcement Learning (RL)

Exploring Long-Term Temporal Trends in the Use of Multiword Expressions

no code implementations • WS 2016 • Tal Daniel, Mark Last

Time Series Analysis

Deep Variational Semi-Supervised Novelty Detection

no code implementations • 12 Nov 2019 • Tal Daniel, Thanard Kurutach, Aviv Tamar

In this work, we propose two variational methods for training VAEs for SSAD.

Anomaly Detection Astronomy +2