Neurosymbolic Object-Centric Learning with Distant Supervision
cs.CV
Submitted: 2025-06-19
Updated: 2026-11-09
Code: https://github.com/shaohua0116/MultiDigitMNIST
Terminology
Sources
- MONet: Unsupervised Scene Decomposition and Representation
- GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
- KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI
- DeepLog: A Software Framework for Modular Neurosymbolic AI
- The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
- Bridging the Gap to Real-World Object-Centric Learning
- Object Centric Concept Bottlenecks
- Provable Compositional Generalization for Object-Centric Learning
- SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs