collaborators

8 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.SD2026

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…

cs.CV2025

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…