10 papers
Learning an Image Editing Model without Image Editing Pairs
Nupur Kumari, Sheng-Yu Wang, Nanxuan Zhao +7
Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine-tuning with large datasets of i…
Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA
Xin Lu, Rui Li, Xun Huang +6
Embodied Question Answering (EQA) has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. However, in dynamic, human-p…
MotionStream: Real-Time Video Generation with Interactive Motion Controls
Joonghyuk Shin, Zhengqi Li, Richard Zhang +4
Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present Mo…
MonarchRT: Efficient Attention for Real-Time Video Generation
Krish Agarwal, Zhuoming Chen, Cheng Luo +5
Real-time video generation with Diffusion Transformers is bottlenecked by the quadratic cost of 3D self-attention, especially in real-time regimes that are both few-step and autore…
Causality in Video Diffusers is Separable from Denoising
Xingjian Bai, Guande He, Zhengqi Li +3
Causality -- referring to temporal, uni-directional cause-effect relationships between components -- underlies many complex generative processes, including videos, language, and ro…
MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
Haotian Xue, Qi Chen, Zhonghao Wang +4
Video diffusion models achieve strong frame-level fidelity but still struggle with motion coherence, dynamics and realism, often producing jitter, ghosting, or implausible dynamics…