Relational Reasoning
1개 벤치마크 · 논문 604편 · 이 태스크의 논문 보기 →
Benchmarks
CLUTRR (k=3)
Most implemented
Relational inductive biases, deep learning, and graph networks
A simple neural network module for relational reasoning
Inductive Relation Prediction by Subgraph Reasoning
Graph-Based Global Reasoning Networks
Complex Embeddings for Simple Link Prediction
Relational Deep Reinforcement Learning
Papers
Let the Heads Talk: Beyond Diagonal Graph Attention
Sheaf Neural Networks generalize scalar-weighted message passing by replacing scalar edge weights with linear transport maps between local feature spaces. Yet the role of this matrix-valued transport is entangled with th…
Relational ReasoningNode ClassificationGraph LearningDo Medical Vision Models Reason About Anatomy? Probing the Spatial Inductive Biases of Learned Visual Representations
Interpreting a CT scan means comparing structures on either side, judging how far apart organs sit, and knowing where each one belongs. Medical vision encoders are evaluated on diagnostic accuracy, or through assembled m…
Relational ReasoningInvestigating Relational Reasoning in VLMs
Vision-Language Models (VLMs) achieve strong performance in visual reasoning tasks, but it remains unclear whether they understand visual relations, or simply employ shortcuts such as language cues or priors. To investig…
Relational ReasoningVisual ReasoningModeling Scientific Experiment Scenes: Dataset and Model
Scene Graph Generation (SGG) is fundamental to structured visual understanding, yet existing benchmarks focus mainly on daily life images and overlook scientific experiment scenes with specialized instruments, task-speci…
Scene Graph GenerationRelational ReasoningMultimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?
The rapid development of multimodal large language models (MLLMs) has introduced a flexible paradigm for remote sensing image scene understanding (RSISU), enabling natural-language interaction with remote sensing imagery…
Visual Question AnsweringRelational ReasoningScene UnderstandingVisual GroundingTask-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026
We present our submission to the QANTA 2026 shared challenge at the ICML 2026 Workshop on Efficient Multimodal Question Answering (EMM-QA). Quanta evaluates multimodal quizbowl systems that answer pyramid-style questions…
Relational ReasoningQuestion AnsweringAnswer Selection