6 papers · 1 filter
Ground, Cover, and Refine: Evidence-Centric Frame Selection for Long-Video Question Answering
Fan Wei, Siru Zhong, Runmin Dong +3
Long-video question answering requires identifying sparse yet critical evidence from videos containing thousands of frames under a constrained visual-token budget. Existing methods…
Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference
Zhaoyang Luo, Runmin Dong, Miao Yang +4
Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation. Existing acceleration methods usually remov…
RS-Prune: Training-Free Data Pruning at High Ratios for Efficient Remote Sensing Diffusion Foundation Models
Fan Wei, Runmin Dong, Yushan Lai +8
Diffusion-based remote sensing (RS) generative foundation models are cruial for downstream tasks. However, these models rely on large amounts of globally representative data, which…
Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
Kaixin Ding, Yang Zhou, Xi Chen +5
Recent advances in Text-to-Image (T2I) generative models, such as Imagen, Stable Diffusion, and FLUX, have led to remarkable improvements in visual quality. However, their performa…
FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
Xiangyang Luo, Qingyu Li, Xiaokun Liu +7
Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consis…
OpusAnimation: Code-Based Dynamic Chart Generation
Bozheng Li, Miao Yang, Zhenhan Chen +9
Dynamic Chart Generation (DCG) involves producing code-rendered animated visualizations as charts. While recent advances in multi-modal large language models (MLLMs) have significa…