Ziyi Wang
PulseAugur coverage of Ziyi Wang — every cluster mentioning Ziyi Wang across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Vision-Language Models Struggle to Infer Player Engagement in Games
Researchers have investigated whether vision-language models (VLMs) can accurately infer human engagement during gameplay. Using the GameVibe Few-Shot dataset across nine first-person shooter games, they tested three VL…
-
UniMotion framework unifies motion, text, and vision understanding
Researchers have introduced UniMotion, a novel framework designed for the integrated understanding and generation of human motion, text, and visual data. Unlike previous models that handle limited modality combinations …
-
StableMotion uses diffusion models for image motion estimation
Researchers have introduced StableMotion, a new framework that utilizes image diffusion models for motion estimation in image rectification tasks. The system repurposes a Stable Diffusion model to estimate motion, emplo…
-
SkeletonLLM enables LLMs to process human skeleton data
Researchers have developed SkeletonLLM, a novel approach to enable multimodal large language models (MLLMs) to understand structured, non-visual data like human skeletons. The system uses DrAction, a differentiable rend…
-
New hardware method physically obscures camera lenses for privacy
Researchers have developed Lens Privacy Sealing (LPS), a novel hardware solution to protect privacy in RGB camera surveillance systems. LPS uses adjustable laminating film to physically obscure camera lenses, offering p…