Spatial instruction following has become a crucial requirement for text-to-image (T2I) generation. A common challenge arises when directional expressions are interpreted under different frames of reference.
Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.
arXiv:2607. 00491v1 Announce Type: cross Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input.
arXiv:2509. 12046v2 Announce Type: replace-cross Abstract: Although autoregressive (AR) models have demonstrated remarkable success in image generation, extending these models to layout-conditioned generation remains challenging due to the sparse nature of layout conditions and the risk of feature entanglement.
arXiv:2607. 25537v1 Announce Type: cross Abstract: In the age of foundation models, a model is only as good as its prompt.
arXiv:2603. 08652v2 Announce Type: replace Abstract: Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning.
arXiv:2511. 16107v3 Announce Type: replace-cross Abstract: Visual in-context learning (VICL) solves visual tasks by conditioning on a few input-output demonstrations without any model training.
arXiv:2606. 08492v1 Announce Type: cross Abstract: Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user prompts.