Research
OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models (opens in a new tab)
arXiv cs.AI ·
Your next cue,
from NOCUE.
Research
Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance (opens in a new tab)
arXiv cs.AI ·
Research
Provenance-Aware Belief Updating in Human-AI Feedback Loops (opens in a new tab)
arXiv cs.AI ·
Research
VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails (opens in a new tab)
arXiv cs.AI ·
Research
Collaborative Learning and Reasoning over Model Slices (opens in a new tab)
arXiv cs.AI ·
Research
Towards Defining, Measuring, and Leveraging Creativity in AI Applications (opens in a new tab)
arXiv cs.AI ·
Research
MathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure Generation (opens in a new tab)
arXiv cs.AI ·
Research
AI-Mediation in Retail Markets: Revenue Effects and Assortment Optimization (opens in a new tab)
arXiv cs.AI ·
Research
DeFiRank: Federated Pairwise Ranking for Governance in Decentralized Financial Networks (opens in a new tab)
arXiv cs.AI ·