5 papers
AcoustiTrace: When Plausible Sound Violates Physics
Shiyang Li, Yuewen Cao, Yihao Liu +4
Recent audio-video generators can produce semantically plausible and apparently synchronized sound, yet may still violate the acoustic processes implied by visible events and envir…
GenTrack: Physical Alignment for Robot-Native Motion Generation and Zero-Shot Humanoid Tracking
Zeyu Ling, Xinyao Yu, Renye Yan +4
General-purpose humanoid trackers can execute diverse references, but their zero-shot coverage depends on large embodied corpora that are costly to extend. Text-to-motion generator…
PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition
Zeyu Ling, Qing Shuai, Teng Zhang +3
Text-to-motion generation has advanced with larger corpora and stronger generators, yet many models still rely on holistic frame- or clip-level latents that entangle trajectory, or…
SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation
Zeyu Ling, Xiaodong Gu, Jiangnan Tang +1
We introduce SyncLipMAE, a self-supervised pretraining framework for talking-face video that learns synchronization-aware and transferable facial dynamics from unlabeled audio-visu…
VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension
Zeyu Ling, Bo Han, Shiyang Li +3
Large language models (LLMs) are, by design, inherently capable of multi-task learning: through a unified next-token prediction paradigm, they can naturally address a wide variety…