3 citations · 3 across the 22 of their papers we have counts for
19 papers · 1 filter
ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs
Zizhong Ding, Junxian Li, Kai Liu +4
Visual token pruning reduces the inference cost of multimodal large language models, but a fixed token ratio is poorly matched to text-rich inputs. In OCR-centric tasks, decisive e…
FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring
Jiatong Li, Leo Liang, Linghe Kong +1
Autoregressive video diffusion models enable real-time streaming video generation. However, errors introduced during self-rollout accumulate over long horizons, manifesting as colo…
LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution
Tianxing Wu, Zheng Chen, Cirou Xu +5
One-Step Diffusion Models have demonstrated promising capability and fast inference in video super-resolution (VSR) for real-world. Nevertheless, the substantial model size and hig…
BinaryDemoire: Moiré-Aware Binarization for Image Demoiréing
Zheng Chen, Zhi Yang, Xiaoyang Liu +5
Image demoiréing aims to remove structured moiré artifacts in recaptured imagery, where degradations are highly frequency-dependent and vary across scales and directions. While rec…
PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks
Junxian Li, Kai Liu, Leyang Chen +7
Unified multimodal models (UMMs) have shown impressive capabilities in generating natural images and supporting multimodal reasoning. However, their potential in supporting compute…
VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models
Guangshuo Qin, Zhiteng Li, Zheng Chen +3
Mixture-of-Experts(MoE) Vision-Language Models (VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training…