



Neeraj Kumar
1.2K posts

@Neeraj_Kumar222
Chief Data Scientist @PNNLab - Exploring intelligence stack: data, memory, chips, compute, agents, autonomous lab. Optimistic 4 AGI, space infra. Views mine!













































Humans count the boxes in this image, hidden ones included, with 82.1% accuracy. The best off-the-shelf multimodal model manages 17.7%. Spatial-IQ is a diagnostic benchmark from NVIDIA Research that breaks 3D object counting into nine perceptual and cognitive sub-tasks, from counting columns to inferring the blocks that must be underneath to hold the structure up, and scores each one separately. Training on those sub-tasks lifted Qwen2.5-VL-32B object-counting accuracy from 2.9% to 62.6%. For researchers developing multimodal reasoning systems, this creates a practical loop: identify where spatial reasoning fails, target the missing capability, and verify that improvement reflects composition, not just a better final score.











