Reducing Hallucinations in Multimodal AI with V-STAR
Discover how V-STAR enhances multimodal reasoning by reducing hallucinations through visual anchoring and improved attention mechanisms.
Edu-MMBias: Auditing Social Bias in Vision-Language Models
Discover Edu-MMBias, a benchmark for auditing social bias in vision-language models within education, ensuring fairness across cognitive, affective, and be...
Credit-Budgeted ICPC Coding: Efficient Agent Decision Costs
Explore credit-budgeted ICPC-style coding where autonomous agents balance accuracy and resource costs for efficient decision-making.
PoreDiT: Scalable Model for Large-Scale Digital Rock Reconstruction
Discover PoreDiT, a scalable generative model enabling efficient, high-fidelity digital rock reconstruction at gigavoxel scales for advanced geoscience res...
MAVEN-T: Advanced Multi-Agent Neural Trajectory Predictor
Discover MAVEN-T, a multi-agent neural trajectory predictor using reinforcement learning for real-time autonomous driving with high accuracy and efficiency...