MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
arXiv preprint arXiv:2311.13165 , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
baseline 1polarities
baseline 1representative citing papers
VisMMoE exploits visual-expert affinity via token pruning to achieve up to 2.68x faster VL-MoE inference on memory-constrained hardware while keeping accuracy competitive.
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.
citing papers explorer
-
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
-
VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading
VisMMoE exploits visual-expert affinity via token pruning to achieve up to 2.68x faster VL-MoE inference on memory-constrained hardware while keeping accuracy competitive.
-
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.