7 papers
Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence
Junchao Liao, Zhenghao Zhang, Xiangyu Meng +5
Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible motion-sound relations remains c…
Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning
Xiangyu Meng, Zixian Zhang, Zhenghao Zhang +3
While advanced methods like VACE and Phantom have advanced video generation for specific subjects in diverse scenarios, they struggle with multi-human identity preservation in dyna…
LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing
Zhenghao Zhang, Ziying Zhang, Junchao Liao +6
Recent multimodal models for instruction-based face editing enable semantic manipulation but still struggle with precise attribute control and identity preservation. Structural fac…
Controlling Language Difficulty in Dialogues with Linguistic Features
Shuyao Xu, Wenguang Wang, Handong Gao +3
Large language models (LLMs) have emerged as powerful tools for supporting second language acquisition, particularly in simulating interactive dialogues for speaking practice. Howe…
Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation
Zhenghao Zhang, Junchao Liao, Xiangyu Meng +2
Recent advances in diffusion transformer models for motion-guided video generation, such as Tora, have shown significant progress. In this paper, we present Tora2, an enhanced vers…
Tora: Trajectory-oriented Diffusion Transformer for Video Generation
Zhenghao Zhang, Junchao Liao, Menghao Li +5
Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based…