3 papers
cs.CV2026
VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation
Tarun Gehlaut, Difan Liu, Charu Bansal +5
Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluated on synthetic benchmarks, wh…
cs.CV2025
Beyond the Pixels: VLM-based Evaluation of Identity Preservation in Reference-Guided Synthesis
Aditi Singhania, Krutik Malani, Riddhi Dhawan +6
Evaluating identity preservation in generative models remains a critical yet unresolved challenge. Existing metrics rely on global embeddings or coarse VLM prompting, failing to ca…
cs.CV2025
Taming Identity Consistency and Prompt Diversity in Diffusion Models via Latent Concatenation and Masked Conditional Flow Matching
Aditi Singhania, Arushi Jain, Krutik Malani +4
Subject-driven image generation aims to synthesize novel depictions of a specific subject across diverse contexts while preserving its core identity features. Achieving both strong…