Tag: multimodal LLMs
Browse our exclusive articles!
EmoTrans Benchmark for Emotion Transitions in Multimodal LLMs
Discover EmoTrans, a new benchmark to evaluate emotion understanding and prediction in multimodal large language models across dynamic social contexts.
Evaluating Small Object Understanding in Multimodal LLMs
Discover how SOUBench benchmarks multimodal large language models' ability to understand small objects and improve performance with SOU-Train.
CNSL-bench: Evaluating MLLMs on Chinese Sign Language
Discover CNSL-bench, a benchmark assessing multimodal LLMs' understanding of Chinese National Sign Language and advancing sign language AI research.
SpikeMLLM: Efficient Spike-Based Multimodal Language Models
Discover SpikeMLLM, a spike-based multimodal large language model offering energy-efficient processing with modality-specific temporal scales and compressi...
Chain-of-Thought Lowers Visual Spatial Reasoning in Multimodal LLMs
Study reveals Chain-of-Thought prompting reduces visual spatial reasoning accuracy in multimodal LLMs, urging new vision-centric AI methods.