SOTAVerified

Relational Reasoning

The goal of Relational Reasoning is to figure out the relationships among different entities, such as image pixels, words or sentences, human skeletons or interactive moving agents.

Source: Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 483 papers

TitleStatusHype
AS3D: 2D-Assisted Cross-Modal Understanding with Semantic-Spatial Scene Graphs for 3D Visual GroundingCode0
ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision AssistantCode0
VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural LanguageCode0
TGraphX: Tensor-Aware Graph Neural Network for Multi-Dimensional Feature LearningCode0
Benchmarking Systematic Relational Reasoning with Large Language and Reasoning Models—0
Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models—0
OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation TriadCode0
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning—0
Generalization of CNNs on Relational Reasoning with Bar ChartsCode0
Unraveling the geometry of visual relational reasoningCode0
Show:102550
← PrevPage 2 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified