Yu Zhou

bryanzhou008

·

https://yu-bryan-zhou.github.io/

AI & ML interests

Multimodality, NLP, Computer Vision, Embodied AI

Recent Activity

upvoted a paper about 5 hours ago

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

upvoted a paper 1 day ago

OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

upvoted a paper 3 days ago

Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning

View all activity

Organizations

New activity in uclanlp/OpenVLHarness-Evaluation-Datasets about 1 month ago

Add general-VQA and spatial benchmarks (RealWorldQA, HallusionBench, V*, FREAK, MMSI, ERQA, SPAR, MindCube, EmbSpatial, OmniSpatial)

#3 opened about 1 month ago by

Add FVQA, InfoSeek and EncyclopedicVQA evaluation splits (full + _mini)

#2 opened about 1 month ago by

New activity in bryanzhou008/vit-base-patch16-224-in21k-finetuned-inaturalist 10 months ago

dataset used to train this model

#1 opened about 1 year ago by

New activity in bryanzhou008/vit-base-patch16-224-in21k-finetuned-inaturalist about 1 year ago

dataset used to train this model

#1 opened about 1 year ago by