List your company

Video Understanding on Ego-in-Exo, NeXTQA, Video MME, ADL-X

71.89Ego-in-Exo (Exo RGB) ScoreVISCOP
60.533263.481666.4369.3784Oct 15, 2025

Evaluation results

MethodLinks
VISCOPVision Language Connector=trainable2025.1071.8983.9164.376.5976.4774.631.84
Finetuning (Frozen VE, Frozen LLM)Vision Encoder=frozen, LLM=frozen, Vision Language Connector=trainable2025.1071.3683.1562.4170.969.0571.37-1.42
Base VLMVision Encoder=frozen, LLM=frozen2025.1066.2784.3265.3777.3670.6572.79—
Finetuning (Trainable VE, Frozen LLM)Vision Encoder=trainable, LLM=frozen, Vision Language Connector=trainable2025.1060.9782.896271.4867.2668.92-3.87
Finetuning (Frozen VE, LoRA LLM)Vision Encoder=frozen, LLM=LoRA updates, Vision Language Connector=trainable2025.1060.9783.7364.1972.1972.4970.71-2.08