This work proposes PosterText, a unified model trained with a four-stage curriculum, including text rendering pretraining, instruction-following training, reinforcement learning for preference alignment, and spatial guidance self-distillation for execution refinement that achieves competitive performance against existi...
Xiao-An Liu, Li-Chen Ma, Zipeng Guo et al.· 1 citation
Vision-language models offer a promising approach for zero-shot anomaly detection (ZSAD). However, due to object-centric bias, normal and anomalous text prototypes exhibit a high semantic overlap. While enforcing strict orthogonality between them improves discriminability, mapping highly contiguous visual inputs onto d...
Man-Wen Yang, Le-Qian Ding, Yu Guo et al.· 0 citations
A VLM-native framework that detects cross-frame object correspondence and explicitly models object presence states, thereby enabling accurate and consistent visual grounding under streaming inputs, and introduces Streaming Grounding Reinforcement (SGR), which optimizes TempoGround with verifiable Grounding, Identity, a...
Le-Qian Ding, Jun-Ning Qiu, Man-Wen Yang et al.· 0 citations
TransAnyText, a structured visual code framework that reformulates image text translation as generating renderable HTML patches from source images and target languages, is introduced, providing an effective, controllable, and editable solution for cross-border e-commerce image translation.
Xiao-An Liu, Li-Chen Ma, Zipeng Guo et al.· 0 citations
Observation Operator Diffusion is proposed, a unified framework that aligns both the supervision trajectory and feature refinement with the intrinsic recovery order of image structures and introduces GL-CoDA, a decoder that injects scale-specific Gaussian-Lanczos observations across decoding stages for coarse-to-fine f...
Shaojie Guo, Li-Chen Ma, Haoyang Tong et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
