Institution profile

University of Texas Health Science Center at Houston

Academic institutionnorthamerica · us
Official website
Research library89linked papers
Opportunities0open roles
Selected work

Representative Papers

ReCo-KD: Region- and Context-Aware Knowledge Distillation for Efficient 3D Medical Image Segmentation

Jan 13, 2026

This work addresses the challenge of deploying accurate yet efficient 3D medical image segmentation models in resource-constrained clinical settings, where existing lightweight architectures often suffer significant performance degradation. To this end, we propose ReCo-KD, a training-stage knowledge distillation framework that effectively transfers fine-grained anatomical structures and long-range contextual information from a teacher network to a compact student model. Our approach leverages multi-scale structure-aware region distillation (MS-SARD) and multi-scale context alignment (MS-CA), incorporating class-aware masks, scale-normalized weighting, and cross-level feature affinity alignment. Notably, ReCo-KD operates independently of the student backbone and integrates seamlessly with nnU-Net. Extensive experiments demonstrate that our method substantially reduces model parameters and inference latency across multiple public and complex aggregated 3D medical datasets while preserving segmentation accuracy close to that of the teacher model, highlighting its strong potential for clinical deployment.

1 citationsRead paper

Benchmark for Antibody Binding Affinity Maturation and Design

May 23, 2025arXiv.org

Current antibody affinity evaluation methods typically analyze antibody sequences or structures in isolation, lacking a unified benchmark that treats the antibody–antigen (Ab–Ag) complex as the functional unit and reflects true binding capability. To address this, we propose AbBiBench—the first function-oriented evaluation framework grounded in complex likelihood estimation, breaking from conventional single-antibody assessment paradigms. AbBiBench integrates masked language modeling, autoregressive generation, inverse folding, diffusion-based structure generation, and geometric graph neural networks, jointly scoring candidates across experimental affinity, structural integrity, and biophysical properties. We systematically evaluate 14 state-of-the-art models on a benchmark comprising 9 antigens and 156,000 antibody variants. Results show that structure-conditioned inverse folding models achieve top performance. In an H1N1 antibody design case study, AbBiBench demonstrates strong predictive validity: model-derived complex likelihood correlates significantly with experimental dissociation constants (K<sub>D</sub>; Pearson *r* = 0.72).

1 citationsRead paper
Recent publications

Latest Papers

A cross-modal generative model for incomplete and degraded prostate MRI with multicentre clinical validation

Aug 17, 2026

This study addresses the challenges of missing and degraded sequences in multiparametric prostate MRI by proposing MSCNet, a cross-modal generation framework. Leveraging sequence-conditioned generation, this method achieves high-quality image reconstruction and was validated through a ten-center blinded reader study. Results demonstrate that reconstructed images attained a structural similarity index (SSIM) of 0.818 and a cancer diagnosis area under the curve (AUC) of 0.841. Notably, diagnostic performance was non-inferior to that of original images and exhibited robust cross-center transferability. These findings confirm the clinical utility of MSCNet as an effective auxiliary diagnostic tool, providing a reliable solution for managing incomplete mp-MRI data in clinical practice.

0 citationsRead paper

Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL

Aug 14, 2026

This study addresses the misalignment between teacher trustworthiness and policy objectives in agent self-distillation by proposing Influence-Calibrated Self-Distillation. Leveraging first-order influence functions to measure token-level gradient responses to reinforcement learning objectives, this method adaptively assigns supervision weights, shifting teacher guidance from trust-oriented to utility-oriented without additional inference overhead. Experiments demonstrate that the approach achieves a 96.1% success rate on ALFWorld and a score of 93.1 on WebShop, while reducing ineffective supervision by 37.8% and improving gradient compatibility by 0.192. These results indicate significant enhancements in both decision-making performance and training stability for language agents.

0 citationsRead paper