GUESS: GradUally Enriching SyntheSis for Text-Driven Human Motion Generation.

In this article, we propose a novel cascaded diffusion-based generative framework for text-driven human motion synthesis, which exploits a strategy named GradUally Enriching SyntheSis (GUESS as its abbreviation). The strategy sets up generation objectives by grouping body joints of detailed skeletons in close semantic proximity together and then replacing each of such joint group with a single body-part node. Such an operation recursively abstracts a human pose to coarser and coarser skeletons at multiple granularity levels.

Bubble Manipulation Driven by Alternating Current Electrowetting: Oscillation Modes and Surface Detachment.

In this paper, a millimeter-sized bubble in water pending on a substrate is manipulated by applying an alternating current (AC) electric field, known as electrowetting on dielectric. In this setup, standing waves on the bubble surface are observed. The amplitude of these waves varies with frequency, and three resonance peaks (21, 76, and 134 Hz) can be identified.

Field-Induced Wettability Gradients for No-Loss Transport of Oil Droplets on Slippery Surfaces.

Transporting oil droplets is crucial for a wide range of industrial and biomedical applications but remains highly challenging due to the large contact angle hysteresis on most solid surfaces. A liquid-infused slippery surface has a low hysteresis contact angle and is a highly promising platform if sufficient wettability gradient can be created. Current strategies used to create wettability gradient typically rely on the engineering of the chemical composition or geometrical structure.