Search papers, labs, and topics across Lattice.
Affiliation:
3
0
7
0
This work introduces OmniVBench and the Omni-R2V Dataset, bringing industrial-grade training resources for diverse R2V tasks to the broader research community, and introduces factor-grounded evaluation, assessing whether intended reference factors are faithfully preserved, correctly disentangled and bound to their targets, and properly realized according to the instruction.
A Retrieval-Augmented Generation framework for scientific image quality assessment, designed to simultaneously address both the understanding track (SIQA-U) and the scoring track (SIQA-S) of the SIQA challenge, is proposed.
This paper proposes and analyzes Comparison-based Preference Optimization (ComPO), a zeroth-order alignment method based on comparison oracles, and establishes a convergence guarantee for its basic offline scheme under smoothness, gradient sparsity, and compatibility between the oracle and a latent objective.
