8 papers · 1 filter
Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models
Yijie Qian, Juncheng Wang, Chao Xu +6
As audio-visual generative models evolve into world simulators, cross-modal synchronization stands as a critical proxy for assessing the consistency of world dynamics and causality…
Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies
Yuxiang Feng, Juncheng Wang, Chao Xu +7
Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design, but it remains challe…
DenseControl: Instance-Level Controllable Synthesis of Dense Crowd Image
Juncheng Wang, Lei Shang, Wang Lu +2
In this paper, we introduce DenseControl, a novel pipeline for generating dense crowd images. Specifically, DenseControl meticulously positions and sizes each generated instance to…
NEWTON: Agentic Planning for Physically Grounded Video Generation
Yuxiang Feng, Juncheng Wang, Chao Xu +7
Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We…
OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction
Zeyu Cai, Yuliang Xiu, Renke Wang +8
Fitting an underlying body model to 3D clothed human assets has been extensively studied, yet most approaches focus on either single-modal inputs such as point clouds or multi-view…
AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
Chengxuan Lu, Shukuan Wang, Yanjie Li +10
Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models is severely bottlenecked by synchronization barriers and the high cost of environment data acquisiti…
GIPO: Gaussian Importance Sampling Policy Optimization
Chengxuan Lu, Zhenquan Zhang, Shukuan Wang +3
Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation. However, RL remains limited by poor da…
Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding
Juncheng Wang, Zhe Hu, Chao Xu +5
Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts, es…