12 papers
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
Chenxi Zhao, Chen Zhu, Xiaokun Feng +6
Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow prima…
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
Meiqi Wu, Zhixin Cai, Fufangchen Zhao +13
Video--based world models have emerged along two dominant paradigms: video generation and 3D reconstruction. However, existing evaluation benchmarks either focus narrowly on visual…
Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
Chubin Chen, Jiashu Zhu, Xiaokun Feng +7
Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for enhancing sample quality and prompt adherence. However, through an empirical analysis on Ga…
HMVLA: Hyperbolic Multimodal Fusion for Vision-Language-Action Models
Kun Wang, Xiao Feng, Mingcheng Qu +1
Vision Language Action (VLA) models have recently shown great potential in bridging multimodal perception with robotic control. However, existing methods often rely on direct fine-…
Latent Temporal Discrepancy as Motion Prior: A Loss-Weighting Strategy for Dynamic Fidelity in T2V
Meiqi Wu, Bingze Song, Ruimin Lin +5
Video generation models have achieved notable progress in static scenarios, yet their performance in motion video generation remains limited, with quality degrading under drastic d…
Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
Fangyuan Mao, Aiming Hao, Jintao Chen +7
Visual effects (VFX) are essential visual enhancements fundamental to modern cinematic production. Although video generation models offer cost-efficient solutions for VFX productio…