4 papers · 1 filter
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation
Bo Yin, Xiaobin Hu, Jiaqi Zhao +1
Long-horizon video generation requires models to effectively leverage an increasingly long generation history. As the generated history grows, retaining all previous content become…
QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models
Jiaqi Zhao, Xiaobin Hu, Bo Yin +3
Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment bottleneck, which m…
Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning
Hao Guo, Fei Wang, Junjie Chen +4
While Vision-Language Models (VLMs) have achieved state-of-the-art performance in general visual tasks, their perceptual robustness remains remarkably brittle when confronted with…
3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models
Xinye Zheng, Fei Wang, Yiqi Nie +5
Reconstructing 3D scenes from smoke-degraded multi-view images is particularly difficult because smoke introduces strong scattering effects, view-dependent appearance changes, and…