3 papers
cs.CV2026
VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
Haz Sameen Shahgir, Xiaofu Chen, Yu Fu +4
Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perce…
eess.AS2025
QuarkAudio Technical Report
Chengwei Liu, Haoyin Yan, Shaofei Xue +5
Many existing audio processing and generation models rely on task-specific architectures, resulting in fragmented development efforts and limited extensibility. It is therefore pro…
cs.CV2025
SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
Xiaofu Chen, Israfel Salazar, Yova Kementchedjhieva
As interest grows in generating long, detailed image captions, standard evaluation metrics become increasingly unreliable. N-gram-based metrics though efficient, fail to capture se…