VLM Latent Shaping: Can 3D Topology Improve Spatial Reasoning?
Can a vision-language model improve spatial reasoning by changing the geometry of its hidden representations? This episode explains how Haoming Wang and Wei Gao turn object-level spatial structure into a fine-tuning signal, and what their experiments establish. We cover three findings: how cross-scene feature extraction separates appearance from layout; why Dirichlet-energy regularization encourages physical neighbors to remain neighbors in latent space; and where the reported benchmark gains occur. The overall Qwen improvement on VSI-Bench is 6.3 points, while the 12.1-percentage-point…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.