Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
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…
cs.LG2026
What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations
Kaizhen Tan, Xin Xu, Siru Tao +4
A central premise of latent world models is that predicting the future forces a representation to internalize the physics of its environment. Which physical quantities does a train…
cs.LG2026
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…