2 papers
cs.CV2026
Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
Shizhan Liu, Xinran Deng, Zhuoyi Yang +3
Latent diffusion models pair VAEs with diffusion backbones, and the structure of VAE latents strongly influences the difficulty of diffusion training. However, existing video VAEs…
cs.CV2025
OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding
Jiali Yao, Xinran Deng, Xin Gu +6
In this paper, we propose spatio-temporal omni-object video grounding, dubbed OmniSTVG, a new STVG task that aims at localizing spatially and temporally all targets mentioned in th…