Search papers, labs, and topics across Lattice.
Indian Institute of Technology Kharagpur
3
0
6
Concentrated interventions on network hubs can dramatically outperform distributed strategies in combating AI-induced delusions.
One-to-many issue-commit traceability can be effectively modeled as an iterative ranking problem, yielding a 26% performance boost over traditional methods.
Captions can be made 48% more complete and hallucination reduced by 45% without retraining models, thanks to a novel prominence-aware rectification approach.
