Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training
Matin Mahmood, Antonio Rueda-Toicen, Mohamed ElBassat +3
CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embeddings and global pooling fail t…
cs.CV2026
Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models
Weixing Wang, Liudvikas Zekas, Anton Hackl +5
Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evaluation protocols assess these…
cs.CV2025
Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
Weixing Wang, Zifeng Ding, Jindong Gu +4
Large Vision-Language Models (LVLMs) with discrete image tokenizers unify multimodal representations by encoding visual inputs into a finite set of tokens. Despite their effectiven…