Search Results for author:
Found 26 papers, 11 papers with code
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback
Then, it uses two VLMs to select the best generation: a Visual Question Answering model that measures the alignment of generated images to the text, and another that measures the generation's aesthetic quality.
A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models
A central component of rational behavior is logical inference: the process of determining which conclusions follow from a set of premises.
The Impact of Depth on Compositional Generalization in Transformer Language Models
Because model latency is approximately linear in the number of layers, these results lead us to the recommendation that, with a given total parameter budget, transformers can be made shallower than is typical without sacrificing performance.
DyST: Towards Dynamic Neural Scene Representations on 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.
DORSal: Diffusion for Object-centric Representations of Scenes et al
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.
Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
Self-supervised methods for learning object-centric representations have recently been applied successfully to various datasets.
Scaling Vision Transformers to 22 Billion Parameters
The scaling of Transformers has driven breakthrough capabilities for language models.
Ranked #1 on
Zero-Shot Transfer Image Classification
on ObjectNet
Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning.
Exploring through Random Curiosity with General Value Functions
Furthermore, RC-GVF significantly outperforms previous methods in the absence of ground-truth episodic counts in the partially observable MiniGrid environments.
SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
The visual world can be parsimoniously characterized in terms of distinct entities with sparse interactions.
Object Scene Representation Transformer
A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition.
Unsupervised Learning of Temporal Abstractions with Slot-based Transformers
The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems.
Test-time Adaptation with Slot-Centric Models
In our work, we find evidence that these losses are insufficient for the task of scene decomposition, without also considering architectural inductive biases.
On the Binding Problem in Artificial Neural Networks
Contemporary neural networks still fall short of human-level generalization, which extends far beyond our direct experiences.
Unsupervised Object Keypoint Learning using Local Spatial Predictability
We propose PermaKey, a novel approach to representation learning based on object keypoints.
Hierarchical Relational Inference
Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics.
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through efficient recombination of functional building blocks, interpretability, preventing catastrophic interference, etc.
Improving Generalization in Meta Reinforcement Learning using Learned Objectives
Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans.
A Perspective on Objects and Systematic Generalization in Model-Based RL
In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment.
Are Disentangled Representations Helpful for Abstract Visual Reasoning?
A disentangled representation encodes information about the salient factors of variation in the data independently.
A Case for Object Compositionality in Deep Generative Models of Images
In this work we propose to structure the generator of a GAN to consider objects and their relations explicitly, and generate images by means of composition.
FVD: A new Metric for Video Generation
While recent generative models of video have had some success, current progress is hampered by the lack of qualitative metrics that consider visual quality, temporal coherence, and diversity of samples.
Towards Accurate Generative Models of Video: A New Metric & Challenges
To this extent we propose Fr\'{e}chet Video Distance (FVD), a new metric for generative models of video, and StarCraft 2 Videos (SCV), a benchmark of game play from custom starcraft 2 scenarios that challenge the current capabilities of generative models of video.
Investigating Object Compositionality in Generative Adversarial Networks
We present a minimal modification of a standard generator to incorporate this inductive bias and find that it reliably learns to generate images as compositions of objects.
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world.
Neural Expectation Maximization
Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities.
