A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Discrete-AIR model identifies objects in images with interpretable latent codes.
Model learns disentangled object location and appearance representations.
DRNets combine deep learning and reasoning for complex tasks.
We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep generative model for videos of moving objects. It can reliably discover and track objects throughout the sequence of frames, and can also generate future frames conditioning on the current frame, thereby simulating expected motion of objects. Th…