A current limitation of video generative video models is that they generate plausible looking frames, but poor motion — an issue that is not well captured by FVD and other popular methods for evaluating generated videos. Here we go beyond FVD by developing a metric which better measures plausible object interactions and motion. Our novel approach is based on auto-encoding point tracks and yields motion features that can be used to not only compare distributions of videos (as few as one generated and one ground truth, or as many as two datasets), but also for evaluating motion of single videos. We show that using point tracks instead of pixel reconstruction or action recognition features results in a metric which is markedly more sensitive to temporal distortions in synthetic data, and can predict human evaluations of temporal consistency and realism in generated videos obtained from open-source models better than a wide range of alternatives. We also show that by using a point track representation, we can spatiotemporally localize generative video inconsistencies, providing extra interpretability of generated video errors relative to prior work. An overview of the results and link to the code can be found on the project page: trajan-paper.github.io.

Jiao Sun, Deqing Fu, Yushi Hu, Su Wang, Royi Rassin, Da-Cheng Juan, Dana Alon, Charles Herrmann, Sjoerd Van Steenkiste, Ranjay Krishna, Cyrus Rashtchian. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Shravan Nayak, Kanishk Jain, Rabiul Awal, Siva Reddy, Sjoerd Van Steenkiste, Lisa Anne Hendricks, Karolina Stanczak, Aishwarya Agrawal. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene Transformer (DyST) model leverages recent work in neural scene representation to learn a latent decomposition of monocular real-world videos into scene content, per-view scene dynamics, and camera pose. This separation is achieved through a novel co-training scheme on monocular videos and our new synthetic dataset DySO. DyST learns tangible latent representations for dynamic scenes that enable view generation with separate control over the camera and the content of the scene.

Tiwalayo Eisape, Michael Tessler, Ishita Dasgupta, Fei Sha, Sjoerd Steenkiste, Tal Linzen. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Jackson Petty, Sjoerd Steenkiste, Ishita Dasgupta, Fei Sha, Dan Garrette, Tal Linzen. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Current vision models typically maintain a fixed correspondence between their representation structure and image space. Each layer comprises a set of tokens arranged “on-the-grid,” which biases patches or tokens to encode information at a specific spatio(-temporal) location. In this work we present *Moving Off-the-Grid* (MooG), a self-supervised video representation model that offers an alternative approach, allowing tokens to move “off-the-grid” to better enable them to represent scene elements consistently, even as they move across the image plane through time. By using a combination of cross-attention and positional embeddings we disentangle the representation structure and image structure. We find that a simple self-supervised objective—next frame prediction—trained on video data, results in a set of latent tokens which bind to specific scene structures and track them as they move. We demonstrate the usefulness of MooG’s learned representation both qualitatively and quantitatively by training readouts on top of the learned representation on a variety of downstream tasks. We show that MooG can provide a strong foundation for different vision tasks when compared to “on-the-grid” baselines.

We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, *Neural Assets*, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooling visual representations of objects from a reference image, such as a frame in a video, and are trained to reconstruct the respective objects in a different image, e.g., a later frame in the video. Importantly, we encode object visuals from the reference image while conditioning on object poses from the target frame, which enables learning disentangled appearance and position features. Combining visual and 3D pose representations in a sequence-of-tokens format allows us to keep the text-to-image interface of existing models, with Neural Assets in place of text tokens. By fine-tuning a pre-trained text-to-image diffusion model with this information, our approach enables fine-grained 3D pose and placement control of individual objects in a scene. We further demonstrate that Neural Assets can be transferred and recomposed across different scenes. Our model achieves state-of-the-art multi-object editing results on both synthetic 3D scene datasets, as well as two real-world video datasets (Objectron, Waymo Open).

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture to image and video modelling, but these have not yet been successfully scaled to nearly the same degree; the largest dense ViT contains 4B parameters (Chen et al., 2022). We present a recipe for highly efficient and stable training of a 22B-parameter ViT (ViT-22B) and perform a wide variety of experiments on the resulting model. When evaluated on downstream tasks (often with a lightweight linear model on frozen features), ViT-22B demonstrates increasing performance with scale. We further observe other interesting benefits of scale, including an improved tradeoff between fairness and performance, state-of-the-art alignment to human visual perception in terms of shape/texture bias, and improved robustness. ViT-22B demonstrates the potential for "LLM-like" scaling in vision, and provides key steps towards getting there.

Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress in this direction. However, they typically fall short at adequately capturing spatial symmetries present in the visual world, which leads to sample inefficiency, such as when entangling object appearance and pose. In this paper, we present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We incorporate equivariance to per-object pose transformations into the attention and generation mechanism of Slot Attention by translating, scaling, and rotating position encodings. These changes result in little computational overhead, are easy to implement, and can result in large gains in terms of data efficiency and overall improvements to object discovery. We evaluate our method on a wide range of synthetic object discovery benchmarks namely CLEVR, Tetrominoes, CLEVRTex, Objects Room and MultiShapeNet, and show promising improvements on the challenging real-world Waymo Open dataset.

Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-supervised losses to adapt the network parameters to each test example independently and have shown promising results towards generalization outside the training distribution for the task of image classification. In our work, we find evidence that these losses are insufficient for the task of scene decomposition, without also considering architectural inductive biases. Recent slot-centric generative models attempt to decompose scenes into entities in a self-supervised manner by reconstructing pixels. Drawing upon these two lines of work, we propose Slot-TTA, a semi-supervised slot-centric scene decomposition model that at test time is adapted per scene through gradient descent on reconstruction or cross-view synthesis objectives. We evaluate Slot-TTA across multiple input modalities, images or 3D point clouds, and show substantial out-of-distribution performance improvements against state-of-the-art supervised feed-forward detectors, and alternative test-time adaptation methods. Project Webpage: http://slot-tta.github.io/

The discovery of reusable subroutines simplifies decision making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in an unsupervised fashion through observing state-action trajectories gathered from executing a policy. However, a current limitation is that they process each trajectory in an entirely sequential manner, which prevents them from revising earlier decisions about subroutine boundary points in light of new incoming information. In this work, we propose slot-based transformer for temporal abstraction (SloTTAr), a fully parallel approach that integrates sequence processing transformers with a slot attention module to discover subroutines in an unsupervised fashion while leveraging adaptive computation for learning about the number of such subroutines solely based on their empirical distribution. We demonstrate how SloTTAr is capable of outperforming strong baselines in terms of boundary point discovery, even for sequences containing variable amounts of subroutines, while being up to seven times faster to train on existing benchmarks.

The visual world can be parsimoniously characterized in terms of distinct entities with sparse interactions. Discovering this compositional structure in dynamic visual scenes has proven challenging for end-to-end computer vision approaches unless explicit instance-level supervision is provided. Slot-based models leveraging motion cues have recently shown great promise in learning to represent, segment, and track objects without direct supervision, but they still fail to scale to complex real-world multi-object videos. In an effort to bridge this gap, we take inspiration from human development and hypothesize that information about scene geometry in the form of depth signals can facilitate object-centric learning. We introduce SAVi++, an object-centric video model which is trained to predict depth signals from a slot-based video representation. By further leveraging best practices for model scaling, we are able to train SAVi++ to segment complex dynamic scenes recorded with moving cameras, containing both static and moving objects of diverse appearance on naturalistic backgrounds, without the need for segmentation supervision. Finally, we demonstrate that by using sparse depth signals obtained from LiDAR, SAVi++ is able to learn emergent object segmentation and tracking from videos in the real-world Waymo Open dataset.

Efficient exploration in reinforcement learning is a challenging problem commonly addressed through intrinsic rewards. Recent prominent approaches are based on state novelty or variants of artificial curiosity. However, directly applying them to partially observable environments can be ineffective and lead to premature dissipation of intrinsic rewards. Here we propose random curiosity with general value functions (RC-GVF), a novel intrinsic reward function that draws upon connections between these distinct approaches. Instead of using only the current observation’s novelty or a curiosity bonus for failing to predict precise environment dynamics, RC-GVF derives intrinsic rewards through predicting temporally extended general value functions. We demonstrate that this improves exploration in a hard-exploration diabolical lock problem. Furthermore, RC-GVF significantly outperforms previous methods in the absence of ground-truth episodic counts in the partially observable MiniGrid environments. Panoramic observations on MiniGrid further boost RC-GVF's performance such that it is competitive to baselines exploiting privileged information in form of episodic counts.

A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition. Facilitating the learning of such a representation in neural networks holds promise for substantially improving labeled data efficiency. As a key step in this direction, we make progress on the problem of learning 3D-consistent decompositions of complex scenes into individual objects in an unsupervised fashion. We introduce Object Scene Representation Transformer (OSRT), a 3D-centric model in which individual object representations naturally emerge through novel view synthesis. OSRT scales to significantly more complex scenes with larger diversity of objects and backgrounds than existing methods. At the same time, it is multiple orders of magnitude faster at compositional rendering thanks to its light field parametrization and the novel Slot Mixer decoder. We believe this work will not only accelerate future architecture exploration and scaling efforts, but it will also serve as a useful tool for both object-centric as well as neural scene representation learning communities.

Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics. The notion of an abstract object, however, encompasses a wide variety of physical objects that differ greatly in terms of the complex behaviors they support. To address this, we propose a novel approach to physical reasoning that models objects as hierarchies of parts that may locally behave separately, but also act more globally as a single whole. Unlike prior approaches, our method learns in an unsupervised fashion directly from raw visual images to discover objects, parts, and their relations. It explicitly distinguishes multiple levels of abstraction and improves over a strong baseline at modeling synthetic and real-world videos.

A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream tasks, there is little empirical evidence that supports this claim. In this paper, we conduct a large-scale study that investigates whether disentangled representations are more suitable for abstract reasoning tasks. Using two new tasks similar to Raven's Progressive Matrices, we evaluate the usefulness of the representations learned by 360 state-of-the-art unsupervised disentanglement models. Based on these representations, we train 3600 abstract reasoning models and observe that disentangled representations do in fact lead to better down-stream performance. In particular, they enable quicker learning using fewer samples.

Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities. A first step towards solving these tasks is the automated discovery of distributed symbol-like representations. In this paper, we explicitly formalize this problem as inference in a spatial mixture model where each component is parametrized by a neural network. Based on the Expectation Maximization framework we then derive a differentiable clustering method that simultaneously learns how to group and represent individual entities. We evaluate our method on the (sequential) perceptual grouping task and find that it is able to accurately recover the constituent objects. We demonstrate that the learned representations are useful for next-step prediction.

A new indirect scheme for encoding neural network connection weights as sets of wavelet-domain coefficients is proposed in this paper. It exploits spatial regularities in the weight-space to reduce the gene-space dimension by considering the low-frequency wavelet coefficients only. The wavelet-based encoding builds on top of a frequency-domain encoding, but unlike when using a Fourier-type transform, it offers gene locality while preserving continuity of the genotype-phenotype mapping. We argue that this added property allows for more efficient evolutionary search and demonstrate this on the octopus-arm control task, where superior solutions were found in fewer generations. The scalability of the wavelet-based encoding is shown by evolving networks with many parameters to control game-playing agents in the Arcade Learning Environment.