Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
Paper • 2607.21072 • Published • 34
sfywtdiy
xnxjiu
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text upvoted a paper 18 days ago
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon published a model 3 months ago
xnxjiu/pi05_v2_deepseek_metaworld_stage1Organizations
None yet