3 papers
cs.LG2026
When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws
Fabien Polly
Compact networks built from Clifford algebra Cl(3,0) primitives are exactly SO(3)-equivariant and learn synthetic 3D vector laws from few samples. We ask whether the geometric alge…
cs.LG2026
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning
Fabien Polly
Parameter-efficient fine-tuning still leaves a broad space of behavior-changing updates reachable, so a poisoned objective can be represented and optimized. We study an alternative…
cs.LG2026
FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models
Fabien Polly
World models learn to predict future states of an environment, enabling planning and mental simulation. Current approaches default to Transformer-based predictors operating in lear…