Announcement_25
VLMs are Biased has been used by ByteDance to evaluate Seed 2.0, Alibaba Qwen to evaluate Qwen3.8, and Moonshot AI as a source benchmark for PerceptionBench!
VLMs are Biased has been used by ByteDance to evaluate Seed 2.0, Alibaba Qwen to evaluate Qwen3.8, and Moonshot AI as a source benchmark for PerceptionBench!