5 papers
Canonical Color as a Lens into Concept Decodability in Vision Encoders and VLMs
Xiaofu Chen, Stella Frank, Yova Kementchedjhieva
Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, information does this representati…
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Yaxin Luo, Haobin Jiang, Jialv Zou +11
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system…
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…
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…
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…