Allan Jabri

Aaron Hurst, Adam Lerer, Adam P. Goucher et al. · openai

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

Dave Epstein, Allan Jabri, Ben Poole et al. · berkeley

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 through text. We introduce self-guidance, a method that provides greater control over generated images by guiding the internal representations of diffusion models. We demonstrate that properties such as the shape, location, and appearance of objects can be extracted from these representations and used to steer sampling. Self-guidance works similarly to classifier guidance, but uses signals present in the pretrained model itself, requiring no additional models or training. We show how a simple set of properties can be composed to perform challenging image manipulations, such as modifying the position or size of objects, merging the appearance of objects in one image with the layout of another, composing objects from many images into one, and more. We also show that self-guidance can be used to edit real images. For results and an interactive demo, see our project page at https://dave.ml/selfguidance/

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 attention-based architecture that decouples its core computation from the dimensionality of the data, enabling adaptive computation for more scalable generation of high-dimensional data. RINs focus the bulk of computation (i.e. global self-attention) on a set of latent tokens, using cross-attention to read and write (i.e. route) information between latent and data tokens. Stacking RIN blocks allows bottom-up (data to latent) and top-down (latent to data) feedback, leading to deeper and more expressive routing. While this routing introduces challenges, this is less problematic in recurrent computation settings where the task (and routing problem) changes gradually, such as iterative generation with diffusion models. We show how to leverage recurrence by conditioning the latent tokens at each forward pass of the reverse diffusion process with those from prior computation, i.e. latent self-conditioning. RINs yield state-of-the-art pixel diffusion models for image and video generation, scaling to 1024X1024 images without cascades or guidance, while being domain-agnostic and up to 10X more efficient than 2D and 3D U-Nets.

Zhipeng Bao, Pavel Tokmakov, Allan Jabri et al.

This paper studies the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. However, by relying on appearance alone, these methods fail to separate objects from the background in cluttered scenes. This is a fundamental limitation since the definition of an object is inherently ambiguous and context-dependent. To resolve this ambiguity, we choose to focus on dynamic objects -- entities that can move independently in the world. We then scale the recent auto-encoder based frameworks for unsupervised object discovery from toy synthetic images to complex real-world scenes. To this end, we simplify their architecture, and augment the resulting model with a weak learning signal from general motion segmentation algorithms. Our experiments demonstrate that, despite only capturing a small subset of the objects that move, this signal is enough to generalize to segment both moving and static instances of dynamic objects. We show that our model scales to a newly collected, photo-realistic synthetic dataset with street driving scenarios. Additionally, we leverage ground truth segmentation and flow annotations in this dataset for thorough ablation and evaluation. Finally, our experiments on the real-world KITTI benchmark demonstrate that the proposed approach outperforms both heuristic- and learning-based methods by capitalizing on motion cues.

Allan Jabri, Sjoerd van Steenkiste, Emiel Hoogeboom et al.

Recent progress in 3D scene understanding enables scalable learning of representations across large datasets of diverse scenes. As a consequence, generalization to unseen scenes and objects, rendering novel views from just a single or a handful of input images, and controllable scene generation that supports editing, is now possible. However, training jointly on a large number of scenes typically compromises rendering quality when compared to single-scene optimized models such as NeRFs. In this paper, we leverage recent progress in diffusion models to equip 3D scene representation learning models with the ability to render high-fidelity novel views, while retaining benefits such as object-level scene editing to a large degree. In particular, we propose DORSal, which adapts a video diffusion architecture for 3D scene generation conditioned on frozen object-centric slot-based representations of scenes. On both complex synthetic multi-object scenes and on the real-world large-scale Street View dataset, we show that DORSal enables scalable neural rendering of 3D scenes with object-level editing and improves upon existing approaches.

Pavel Tokmakov, Allan Jabri, Jie Li et al.

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 the choice of learning signal in cases of total occlusion. Rather than directly supervising the locations of invisible objects, we propose a self-supervised objective that requires neither human annotation, nor assumptions about object dynamics. We show that object permanence can emerge by optimizing for temporal coherence of memory: we fit a Markov walk along a space-time graph of memories, where the states in each time step are non-Markovian features from a sequence encoder. This leads to a memory representation that stores occluded objects and predicts their motion, to better localize them. The resulting model outperforms existing approaches on several datasets of increasing complexity and realism, despite requiring minimal supervision, and hence being broadly applicable.

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 "novelty" of states, transitions, or trajectories with deep networks. Prior works have shown that conditional prediction objectives such as masked autoencoding can be seen as stochastic estimation of pseudo-likelihood. We show how this perspective naturally leads to a unified view on existing intrinsic reward approaches: they are special cases of conditional prediction, where the estimation of novelty can be seen as pseudo-likelihood estimation with different mask distributions. From this view, we propose a general framework for deriving intrinsic rewards -- Masked Input Modeling for Exploration (MIMEx) -- where the mask distribution can be flexibly tuned to control the difficulty of the underlying conditional prediction task. We demonstrate that MIMEx can achieve superior results when compared against competitive baselines on a suite of challenging sparse-reward visuomotor tasks.

Zhangxing Bian, Allan Jabri, Alexei A. Efros et al.

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 dominate each space differ. We take a step towards bridging this gap by extending the recent contrastive random walk formulation to much denser, pixel-level space-time graphs. The main contribution is introducing hierarchy into the search problem by computing the transition matrix between two frames in a coarse-to-fine manner, forming a multiscale contrastive random walk when extended in time. This establishes a unified technique for self-supervised learning of optical flow, keypoint tracking, and video object segmentation. Experiments demonstrate that, for each of these tasks, the unified model achieves performance competitive with strong self-supervised approaches specific to that task. Project webpage: https://jasonbian97.github.io/flowwalk

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 space-time graph constructed from video. In this graph, the nodes are patches sampled from each frame, and nodes adjacent in time can share a directed edge. We learn a representation in which pairwise similarity defines transition probability of a random walk, so that long-range correspondence is computed as a walk along the graph. We optimize the representation to place high probability along paths of similarity. Targets for learning are formed without supervision, by cycle-consistency: the objective is to maximize the likelihood of returning to the initial node when walking along a graph constructed from a palindrome of frames. Thus, a single path-level constraint implicitly supervises chains of intermediate comparisons. When used as a similarity metric without adaptation, the learned representation outperforms the self-supervised state-of-the-art on label propagation tasks involving objects, semantic parts, and pose. Moreover, we demonstrate that a technique we call edge dropout, as well as self-supervised adaptation at test-time, further improve transfer for object-centric correspondence.

Richard Li, Allan Jabri, Trevor Darrell et al.

Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require manipulation of multiple objects, and the complexity of such tasks increases with the number of objects. Learning from a curriculum of increasingly complex tasks appears to be a natural solution, but unfortunately, does not work for many scenarios. We hypothesize that the inability of the state-of-the-art algorithms to effectively utilize a task curriculum stems from the absence of inductive biases for transferring knowledge from simpler to complex tasks. We show that graph-based relational architectures overcome this limitation and enable learning of complex tasks when provided with a simple curriculum of tasks with increasing numbers of objects. We demonstrate the utility of our framework on a simulated block stacking task. Starting from scratch, our agent learns to stack six blocks into a tower. Despite using step-wise sparse rewards, our method is orders of magnitude more data-efficient and outperforms the existing state-of-the-art method that utilizes human demonstrations. Furthermore, the learned policy exhibits zero-shot generalization, successfully stacking blocks into taller towers and previously unseen configurations such as pyramids, without any further training.

Allan Jabri, Kyle Hsu, Ben Eysenbach et al.

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined distributions of training tasks, and hand-crafting these task distributions can be challenging and time-consuming. Can "useful" pre-training tasks be discovered in an unsupervised manner? We develop an unsupervised algorithm for inducing an adaptive meta-training task distribution, i.e. an automatic curriculum, by modeling unsupervised interaction in a visual environment. The task distribution is scaffolded by a parametric density model of the meta-learner's trajectory distribution. We formulate unsupervised meta-RL as information maximization between a latent task variable and the meta-learner's data distribution, and describe a practical instantiation which alternates between integration of recent experience into the task distribution and meta-learning of the updated tasks. Repeating this procedure leads to iterative reorganization such that the curriculum adapts as the meta-learner's data distribution shifts. In particular, we show how discriminative clustering for visual representation can support trajectory-level task acquisition and exploration in domains with pixel observations, avoiding pitfalls of alternatives. In experiments on vision-based navigation and manipulation domains, we show that the algorithm allows for unsupervised meta-learning that transfers to downstream tasks specified by hand-crafted reward functions and serves as pre-training for more efficient supervised meta-learning of test task distributions.

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 learning visual representations from scratch. At training time, our model learns a feature map representation to be useful for performing cycle-consistent tracking. At test time, we use the acquired representation to find nearest neighbors across space and time. We demonstrate the generalizability of the representation -- without finetuning -- across a range of visual correspondence tasks, including video object segmentation, keypoint tracking, and optical flow. Our approach outperforms previous self-supervised methods and performs competitively with strongly supervised methods.

Aravind Srinivas, Allan Jabri, Pieter Abbeel et al.

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 universal planning networks (UPN). UPNs embed differentiable planning within a goal-directed policy. This planning computation unrolls a forward model in a latent space and infers an optimal action plan through gradient descent trajectory optimization. The plan-by-gradient-descent process and its underlying representations are learned end-to-end to directly optimize a supervised imitation learning objective. We find that the representations learned are not only effective for goal-directed visual imitation via gradient-based trajectory optimization, but can also provide a metric for specifying goals using images. The learned representations can be leveraged to specify distance-based rewards to reach new target states for model-free reinforcement learning, resulting in substantially more effective learning when solving new tasks described via image-based goals. We were able to achieve successful transfer of visuomotor planning strategies across robots with significantly different morphologies and actuation capabilities.

Douwe Kiela, Alexis Conneau, Allan Jabri et al.

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. We train a grounded sentence encoder that achieves good performance on COCO caption and image retrieval and subsequently show that this encoder can successfully be transferred to various NLP tasks, with improved performance over text-only models. Lastly, we analyze the contribution of grounding, and show that word embeddings learned by this system outperform non-grounded ones.

Marco Baroni, Armand Joulin, Allan Jabri et al.

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 instead on important but narrow applications, such as image classification or machine translation. We believe this to be largely due to the lack of objective ways to measure progress towards broad machine intelligence. In order to fill this gap, we propose here a set of concrete desiderata for general AI, together with a platform to test machines on how well they satisfy such desiderata, while keeping all further complexities to a minimum.

Ang Li, Allan Jabri, Armand Joulin et al.

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 of images per class for training is infeasible in such a scenario, prompting the use of webly supervised data. This paper explores the training of image-recognition systems on large numbers of images and associated user comments. In particular, we develop visual n-gram models that can predict arbitrary phrases that are relevant to the content of an image. Our visual n-gram models are feed-forward convolutional networks trained using new loss functions that are inspired by n-gram models commonly used in language modeling. We demonstrate the merits of our models in phrase prediction, phrase-based image retrieval, relating images and captions, and zero-shot transfer.

Allan Jabri, Armand Joulin, Laurens van der Maaten

Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding. Many of the recently proposed VQA systems include attention or memory mechanisms designed to support "reasoning". For multiple-choice VQA, nearly all of these systems train a multi-class classifier on image and question features to predict an answer. This paper questions the value of these common practices and develops a simple alternative model based on binary classification. Instead of treating answers as competing choices, our model receives the answer as input and predicts whether or not an image-question-answer triplet is correct. We evaluate our model on the Visual7W Telling and the VQA Real Multiple Choice tasks, and find that even simple versions of our model perform competitively. Our best model achieves state-of-the-art performance on the Visual7W Telling task and compares surprisingly well with the most complex systems proposed for the VQA Real Multiple Choice task. We explore variants of the model and study its transferability between both datasets. We also present an error analysis of our model that suggests a key problem of current VQA systems lies in the lack of visual grounding of concepts that occur in the questions and answers. Overall, our results suggest that the performance of current VQA systems is not significantly better than that of systems designed to exploit dataset biases.

Armand Joulin, Laurens van der Maaten, Allan Jabri et al.

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 improvements of these visual features will likely require even larger manually labeled data sets, which severely limits the pace at which progress can be made. In this paper, we explore the potential of leveraging massive, weakly-labeled image collections for learning good visual features. We train convolutional networks on a dataset of 100 million Flickr photos and captions, and show that these networks produce features that perform well in a range of vision problems. We also show that the networks appropriately capture word similarity, and learn correspondences between different languages.