Search papers, labs, and topics across Lattice.
University of Modena and Reggio Emilia, Modena, Italy
5
0
8
32
DocAttriBench (DAB) is introduced, a large-scale benchmark for fine-grained, element-level source attribution in Document VQA, grounding answers to specific layout elements such as text blocks, tables, and images.
Aligning the least aligned attention heads in MLLMs can yield the most significant performance gains, challenging conventional alignment strategies.
DLMs reveal surprising trade-offs between performance and computational efficiency that challenge conventional wisdom about language model design.
Ditching text-based conditioning for visual features in diffusion-based super-resolution unlocks significantly improved structural fidelity and texture realism.
Forget training wheels: RaTA-Tool lets MLLMs pick the right tool for the job in the wild, even if they've never seen it before.
