Search papers, labs, and topics across Lattice.
Asal Mohammadjafari Mamaqani, University of Technology, Michigan State University Bardiya, Kariminia Shahid, Beheshti University, University of Tehran, Amirkabir University of Technology, Sharif University of Technology
5
0
6
Hallucinations in LVLMs reveal a structured uncertainty pattern that can be effectively detected, outperforming traditional methods by up to 20% in precision metrics.
KG-FairDiff achieves substantial reductions in demographic disparities in text-to-image generation while preserving the original intent of prompts, making it a game-changer for equitable AI deployment.
LLMs may be getting smarter, but this survey reveals a fragmented understanding of abductive reasoning, highlighting critical gaps in current approaches and benchmarks.
Unlearning nudity in Stable Diffusion can severely degrade its ability to compose scenes correctly, showing that current unlearning methods struggle to balance concept removal with broader generative capabilities.
Despite advances in vision-language models, they still fail at rebus puzzles, highlighting a critical gap in cognitive visual reasoning that neither scaling nor in-context learning can fix.
