115 citations · 334 across the 15 of their papers we have counts for
16 papers
Diffusion Self-Guidance for Controllable Image Generation
Dave Epstein, Allan Jabri, Ben Poole +2
Large-scale generative models are capable of producing high-quality images from detailed text descriptions. However, many aspects of an image are difficult or impossible to convey…
DORSal: Diffusion for Object-centric Representations of Scenes et al
Allan Jabri, Sjoerd van Steenkiste, Emiel Hoogeboom +2
Recent progress in 3D scene understanding enables scalable learning of representations across large datasets of diverse scenes. As a consequence, generalization to unseen scenes an…
MIMEx: Intrinsic Rewards from Masked Input Modeling
Toru Lin, Allan Jabri
Exploring in environments with high-dimensional observations is hard. One promising approach for exploration is to use intrinsic rewards, which often boils down to estimating "nove…
Scalable Adaptive Computation for Iterative Generation
Allan Jabri, David Fleet, Ting Chen
Natural data is redundant yet predominant architectures tile computation uniformly across their input and output space. We propose the Recurrent Interface Networks (RINs), an atten…
Object Permanence Emerges in a Random Walk along Memory
Pavel Tokmakov, Allan Jabri, Jie Li +1
This paper proposes a self-supervised objective for learning representations that localize objects under occlusion - a property known as object permanence. A central question is th…
Discovering Objects that Can Move
Zhipeng Bao, Pavel Tokmakov, Allan Jabri +3
This paper studies the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, text…
Learning Pixel Trajectories with Multiscale Contrastive Random Walks
Zhangxing Bian, Allan Jabri, Alexei A. Efros +1
A range of video modeling tasks, from optical flow to multiple object tracking, share the same fundamental challenge: establishing space-time correspondence. Yet, approaches that d…
Space-Time Correspondence as a Contrastive Random Walk
Allan Jabri, Andrew Owens, Alexei A. Efros
This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. We cast correspondence as prediction of links in a spa…
Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
Richard Li, Allan Jabri, Trevor Darrell +1
Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require…
Unsupervised Curricula for Visual Meta-Reinforcement Learning
Allan Jabri, Kyle Hsu, Ben Eysenbach +3
In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. Howe…
Learning Correspondence from the Cycle-Consistency of Time
Xiaolong Wang, Allan Jabri, Alexei A. Efros
We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for lear…
Universal Planning Networks
Aravind Srinivas, Allan Jabri, Pieter Abbeel +2
A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization. To this end, we introduce…
Learning Visually Grounded Sentence Representations
Douwe Kiela, Alexis Conneau, Allan Jabri +1
We introduce a variety of models, trained on a supervised image captioning corpus to predict the image features for a given caption, to perform sentence representation grounding. W…
CommAI: Evaluating the first steps towards a useful general AI
Marco Baroni, Armand Joulin, Allan Jabri +4
With machine learning successfully applied to new daunting problems almost every day, general AI starts looking like an attainable goal. However, most current research focuses inst…
Learning Visual N-Grams from Web Data
Ang Li, Allan Jabri, Armand Joulin +1
Real-world image recognition systems need to recognize tens of thousands of classes that constitute a plethora of visual concepts. The traditional approach of annotating thousands…
Learning Visual Features from Large Weakly Supervised Data
Armand Joulin, Laurens van der Maaten, Allan Jabri +1
Convolutional networks trained on large supervised dataset produce visual features which form the basis for the state-of-the-art in many computer-vision problems. Further improveme…