Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical Reasoning
Kaizhen Tan, Yang Feng, Heqing Du +3
Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Yet we find that current model…
cs.CV2026
When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMs
Kaizhen Tan, Yang Feng, Heqing Du +3
Visual token pruning is widely used to reduce the inference cost of multimodal large language models (MLLMs), but it is usually evaluated only by accuracy. We study how pruning aff…
cs.CV2026
CREG: Compass Relational Evidence Graph for Characterizing Directional Structure in VLM Spatial-Reasoning Attribution
Kaizhen Tan, Yang Feng, Heqing Du
Standard attribution heatmaps show where a vision-language model (VLM) focuses, but they do not reveal whether the recovered evidence is organized by the queried spatial relation o…