CVPR 2026 accepted papers on Graph learning
29 of the 4,042 papers accepted at CVPR 2026 (0.7%) are on Graph learning, compared with 0.9% at CVPR 2025. They fall into 4 topics.
See CVPR 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Graph self-supervised learning · 13 papers
- Adaptive Learned Image Compression with Graph Neural Networks
- Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
- Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter
- BrickNet: Graph-Backed Generative Brick Assembly
- DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs
- GraPHFormer: A Multimodal Graph Persistent Homology Transformer for the Analysis of Neuroscience Morphologies
- Hyperbolic Busemann Neural Networks
- SIR: Structured Image Representations for Explainable Robot Learning
- BrepVGAE: Variational Graph Autoencoder with Unified Latent Representation for B-rep
- Nestwork: Conditional 3D Furnished House Layout Generation through Latent Heterogeneous Graph Diffusion
- PP-Brep: Few-Shot B-rep Classification with Hybrid Graph Representation
- Semantic Derivative Flow: Graph-Guided Diffusion for Controllable Instance Interactions
and 1 more in the interactive map.
Knowledge and temporal graphs · 11 papers
- Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenes
- Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching
- DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime
- FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics
- Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation
- STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation
- End-to-End Hyper-Relational Information Extraction for Engineering Diagrams via Dynamically Tokenized Relation Transformer
- Gamba: Mamba-based graph convolutional network with dynamic graph topology learning for action recognition
- IEBGL:An Interpretability-Enhanced Brain Graph Learning Framework with LLM-Instructed Topology and Literature-Augmented Semantics
- Mixture-of-Experts based Feature Decoupling for Open Vocabulary Scene Graph Generation
- NeuroRule: Bridging Vision and Logic with Differentiable Rule Induction