Deng Li

Working Memory Fidelity-Active Manipulation is introduced, a calibrated no-scratchpad probe of cumulative arithmetic state tracking, and three construct-isolation ablations support the interpretation that cumulative state tracking under load, rather than single-step arithmetic or entity tracking alone, is the primary difficulty source.

Mimicking the human visual system's "glance and gaze" strategy lets video transformers capture long-range dependencies and achieve state-of-the-art action recognition.