conftrace_

vision-language benchmark

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multimodal large language model (3) vision-language model (3) multimodal learning (3) step-wise feedback (1) multimodal adaptor (1) emotional caption (1) multilingual vision (1) unsupervised coefficient optimization (1) background noise (1) output reward model (1)

Papers

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization CVPR 2025 IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities AAAI 2025 PCRI: Measuring Context Robustness in Multimodal Models for Enterprise Applications EMNLP 2025 ViLBench: A Suite for Vision-Language Process Reward Modeling EMNLP 2025 No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages EMNLP 2024