19 papers
TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback
Jingyu Liu, Hao Jiang, Yikang Ding +6
Classifier-free guidance (CFG) typically applies a shared scale to all latent tokens, although their velocity predictions evolve differently during sampling. We introduce Trajector…
SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling
Xinyu Wang, Huafeng Shi, Zian Li +4
We present SubjectAnchor, a Subject-Aware Memory-to-Video paradigm for multi-shot storytelling in which the current shot is generated by conditioning on explicit visual memories ex…
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models
Meng Luo, Yicheng Liu, Jiahao Wang +5
Video generation has advanced to produce visually compelling and temporally coherent results. Yet, whether these models can genuinely think with video--executing symbolic rules, re…
Human-Centric Image Captioning with Subject-Centered Spatial Understanding
Bozhou Li, Jiahang Zhang, Yue Ding +11
While multimodal large language models (MLLMs) achieve remarkable performance on generic image captioning, they frequently suffer from structural hallucinations in human-centric sc…
MVWeaver: A Hierarchical Music Video Generation Agent with a Learned Song-to-Visual Bridge
Sifei Li, Minyan Luo, Xu Li +7
Music videos are an important form of audiovisual expression in contemporary culture. They translate and extend the expressive content of songs through deliberate visual design. Ex…
Closing the Verification Loop: Self-Check Captioning for Long-Paragraph Detailed Audio Captioning
Fengji Ma, Yan Rong, Xu Li +3
Long-paragraph detailed audio captioning, which requires dense and transcript-faithful descriptions of fine-grained audio content, remains unsolved for current audio-visual multimo…
EmotionDialogCN: A Spontaneous Multimodal Dataset for Mandarin Emotional Dialogue
Yi Zheng, Yifan Xu, Yan Zhou +8
Face-to-face audiovisual interaction is central to human communication, conveying rich emotional and social cues. However, existing multimodal dialogue datasets remain limited by i…
SonicWeave: Chunk-Routed Mixture-of-Experts for Unified Audio Scene Generation
Yunrui Cai, Xu Li, Yucheng Zhou +8
Text-conditioned general audio generation is moving beyond isolated speech, music, and sound-effect synthesis toward a single model that can compose them into controllable, coheren…
Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations
Zhixue Fang, Zhimin Zhang, Bi'an Du +6
Video motion transfer aims to animate a target object using dynamics from a reference video. Existing formulations largely rely on fixed structural correspondence, which becomes il…
StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation
Zejing Rao, Haoxian Zhang, Xiaoqiang Liu +5
Existing human--object interaction (HOI) video generation methods are largely limited to offline short-video generation with complex driving conditions, making them unsuitable for…
MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations
Hejia Chen, Haoxian Zhang, Xu He +4
Generating lifelike facial animation for dyadic conversations requires reconciling high-level cognitive intent with precise low-level motor reflexes, yet existing methods fall shor…
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
Jiwen Liu, Shujuan Li, Zhixue Fang +8
Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control. Existing methods either directly use parametr…
ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation
Zijie Meng, Jiwen Liu, Yufei Liu +5
Subject-preserving video generation is not solved by frontal-face similarity alone: a generated person must remain recognizable across motion, large viewpoint changes, expression s…
Semantic-Aware Prefix Learning for Token-Efficient Image Generation
Qingfeng Li, Haoxian Zhang, Xu He +4
Visual tokenizers play a central role in latent image generation by bridging high-dimensional images and tractable generative modeling. However, most existing tokenizers are still…
IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation
Zhufeng Xu, Xuan Gao, Feng-Lin Liu +6
Recent progress in video diffusion models has markedly advanced character animation, which synthesizes motioned videos by animating a static identity image according to a driving v…
From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping
Xu He, Haoxian Zhang, Hejia Chen +7
Audio-driven visual dubbing aims to synchronize a video's lip movements with new speech but is fundamentally challenged by the lack of ideal training data: paired videos differing…
VC-Agent: An Interactive Agent for Customized Video Dataset Collection
Yidan Zhang, Mutian Xu, Yiming Hao +6
Facing scaling laws, video data from the internet becomes increasingly important. However, collecting extensive videos that meet specific needs is extremely labor-intensive and tim…
Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis
Yikang Ding, Jiwen Liu, Wenyuan Zhang +11
Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-lev…
MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
Yuan Wang, Di Huang, Yaqi Zhang +5
Generating lifelike human motions from descriptive texts has experienced remarkable research focus in the recent years, propelled by the emerging requirements of digital humans.Des…