5 papers · 1 filter
TGV-KV: Text-Grounded KV Eviction for Vision-Language Models
Jizhihui Liu, Ruizi Han, Miao Zhang +4
Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate inference, resulting in memory…
A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis
Xianchao Guan, Zhiyuan Fan, Yifeng Wang +11
The development of clinical-grade artificial intelligence in pathology is limited by the scarcity of diverse, high-quality annotated datasets. Generative models offer a potential s…
VideoVista-CulturalLingo: 360 Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension
Xinyu Chen, Yunxin Li, Haoyuan Shi +4
Assessing the video comprehension capabilities of multimodal AI systems can effectively measure their understanding and reasoning abilities. Most video evaluation benchmarks are li…
CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion
Yanyu Li, Pencheng Wan, Liang Han +3
Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost an…
A Unified Agentic Framework for Evaluating Conditional Image Generation
Jifang Wang, Xue Yang, Longyue Wang +7
Conditional image generation has gained significant attention for its ability to personalize content. However, the field faces challenges in developing task-agnostic, reliable, and…