4 papers
LongCat-Video-Avatar 1.5 Technical Report
Meituan LongCat Team, Xunliang Cai, Meng Cheng +10
Despite advances in audio-driven video generation, achieving commercial-grade stability remains challenging. We present LongCat-Video-Avatar 1.5, an upgraded open-source framework…
MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation
Bizhu Wu, Jinheng Xie, Wenting Chen +5
Recent motion-language models unify tasks like comprehension and generation but operate at a coarse granularity, lacking fine-grained understanding and nuanced control over body pa…
FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing
Bizhu Wu, Jinheng Xie, Meidan Ding +5
Generating realistic human motions from textual descriptions has undergone significant advancements. However, existing methods often overlook specific body part movements and their…
MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities
Bizhu Wu, Jinheng Xie, Keming Shen +5
Recent motion-aware large language models have demonstrated promising potential in unifying motion comprehension and generation. However, existing approaches primarily focus on coa…