5 papers
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Zanyi Wang, Xin Lin, Haodong Li +2
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing g…
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen +17
Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining.…
ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
Duy M. H. Nguyen, Nghiem T. Diep, Trung Q. Nguyen +10
State-of-the-art medical multi-modal LLMs (med-MLLMs), such as LLaVA-Med and BioMedGPT, primarily depend on scaling model size and data volume, with training driven largely by auto…
S-Chain: Structured Visual Chain-of-Thought For Medicine
Khai Le-Duc, Duy M. H. Nguyen, Phuong T. H. Trinh +21
Faithful reasoning in medical vision-language models (VLMs) requires not only accurate predictions but also transparent alignment between textual rationales and visual evidence. Wh…
Accelerating Transformers with Spectrum-Preserving Token Merging
Hoai-Chau Tran, Duy M. H. Nguyen, Duy M. Nguyen +7
Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an…