Detection-Guided Attention Steering for Vision Language Models

ConvCue: Complementary Visual Inductive Biases for Vision-Language Models

Modern vision-language models (VLMs) achieve strong performance across a broad range of multimodal tasks, yet still struggle with visual questions that require fine-grained discrimination and spatial understanding. These limitations motivate investigating whether supplementary visual representations can improve existin...

Toward Multimodal Understanding in Low-Level Vision: The Rise of Vision-Language Models

Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs

Generative vision-language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining distribution, yet fail on specialized domains where the required discriminative features were never learned, a regime we term distant out-of-distribution (OOD). Standard ad...

Gaze-Driven Efficient Inference for Vision-Language Models

UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models

UC-VLM is a unified multi-stage binary-supervised framework that consistently reuses the same authenticity labels for visual adaptation and label-conditioned text generation, while leveraging automatically optimized instructions to reduce prompt sensitivity without requiring human-written rationales or hand-crafted pro...

Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis

It is found that post-pretraining QK-RMSNorm injection fails to reproduce the protection of native QK-RMSNorm, while several off-the-shelf weight-merging settings fail to recover the lost capability after VL training, highlighting the value of screening backbones with Sink Strength before VL training and narrow the int...