Systematic Generalization
61 papers with code • 0 benchmarks • 7 datasets
Benchmarks
These leaderboards are used to track progress in Systematic Generalization
Libraries
Use these libraries to find Systematic Generalization models and implementationsLatest papers with no code
Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models
There have recently been large advances both in pre-training visual representations for robotic control and segmenting unknown category objects in general images.
A Neural Rewriting System to Solve Algorithmic Problems
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
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
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
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
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
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
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
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
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.