From the 1 of 5 linked papers with an AI index.
5 papers
Beyond Multimodal Alignment: Certifying Physical Language through Response Substitution and Ordered Execution
Kaizhen Tan, Xin Xu, Siru Tao +4
World models increasingly treat compact multimodal representations as interfaces between perception and physical interaction, yet existing probes do not establish whether different…
What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations
Kaizhen Tan, Xin Xu, Siru Tao +4
The paper investigates which physical properties (mass, drag, stiffness) are encoded in latent world models by using controlled interventions in a simulated multimodal environment…
How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning
Kaizhen Tan, Heqing Du, Yang Feng
A LoRA adapter is a few megabytes that almost everyone treats as a skill rather than a record of the data behind it. We put that assumption on a scale. Extending compression-based…
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…
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…