Systematic Generalization

61 papers with code • 0 benchmarks • 7 datasets

This task has no description! Would you like to contribute one?

Libraries

Use these libraries to find Systematic Generalization models and implementations

Latest papers with no code

A Neural Rewriting System to Solve Algorithmic Problems

no code yet • 27 Feb 2024

Modern neural network architectures still struggle to learn algorithmic procedures that require to systematically apply compositional rules to solve out-of-distribution problem instances.

Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategies

no code yet • 27 Feb 2024

Large Language Models (LLMs) have revolutionized the field of Natural Language Processing thanks to their ability to reuse knowledge acquired on massive text corpora on a wide variety of downstream tasks, with minimal (if any) tuning steps.

Unsupervised Discovery of Object-Centric Neural Fields

no code yet • 12 Feb 2024

Extensive experiments show that uOCF enables unsupervised discovery of visually rich objects from a single real image, allowing applications such as 3D object segmentation and scene manipulation.

Interpretability Illusions in the Generalization of Simplified Models

no code yet • 6 Dec 2023

A common method to study deep learning systems is to use simplified model representations -- for example, using singular value decomposition to visualize the model's hidden states in a lower dimensional space.

Generating Interpretable Networks using Hypernetworks

no code yet • 5 Dec 2023

The hypernetwork is carefully designed such that it can control network complexity, leading to a diverse family of interpretable algorithms ranked by their complexity.

Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models

no code yet • NeurIPS 2023

Systematic compositionality, or the ability to adapt to novel situations by creating a mental model of the world using reusable pieces of knowledge, remains a significant challenge in machine learning.

Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation

no code yet • 1 Oct 2023

Strong inductive biases enable learning from little data and help generalization outside of the training distribution.

Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality

no code yet • 23 May 2023

Along with this, we propose novel negative mining techniques in the scene graph space for improving attribute binding and relation understanding.

SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models

no code yet • NeurIPS 2023

Finally, we demonstrate the scalability of SlotDiffusion to unconstrained real-world datasets such as PASCAL VOC and COCO, when integrated with self-supervised pre-trained image encoders.

On the Generalization of Learned Structured Representations

no code yet • 25 Apr 2023

In representation learning, large datasets are leveraged to learn generic data representations that may be useful for efficient learning of arbitrary downstream tasks.