8 papers
Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?
Ta Duc Huy, Trang Nguyen, Townim Chowdhury +5
Vision-language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions. Common entropy-based methods, such as Semantic Entropy (SE), rel…
STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
Ankit Yadav, Arpit Garg, Ta Duc Huy +1
Distilled one-step (T=1) or few-step (T4) diffusion models enable real-time image generation but often exhibit reduced sample diversity compared to their multi-step counterpa…
Overthinking Causes Hallucination: Tracing Confounder Propagation in Vision Language Models
Abin Shoby, Ta Duc Huy, Tuan Dung Nguyen +6
Vision Language models (VLMs) often hallucinate non-existent objects. Detecting hallucination is analogous to detecting deception: a single final statement is insufficient, one mus…
Hierarchical Text-Guided Brain Tumor Segmentation via Sub-Region-Aware Prompts
Bahram Mohammadi, Ta Duc Huy, Afrouz Sheikholeslami +8
Brain tumor segmentation remains challenging because the three standard sub-regions, i.e., whole tumor (WT), tumor core (TC), and enhancing tumor (ET), often exhibit ambiguous visu…
AR&D: A Framework for Retrieving and Describing Concepts for Interpreting AudioLLMs
Townim Faisal Chowdhury, Ta Duc Huy, Siqi Pan +2
Despite strong performance in audio perception tasks, large audio-language models (AudioLLMs) remain opaque to interpretation. A major factor behind this lack of interpretability i…
Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
Ta Duc Huy, Duy Anh Huynh, Yutong Xie +10
Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability…