Adnan Saeed

Adnan Saeed is a deep learning researcher working on medical image analysis, with a focus on multimodal architectures, graph neural networks, and evidential deep learning for clinical imaging tasks. His peer reviewed research has appeared in journals across machine learning and biomedical signal processing. At AI Trend Blend he turns recent papers into clear, practical explainers, with an emphasis on what a method actually does and where it holds up, written for readers who want depth without the hype.

Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference.

Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference

Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference | MedAI Research 3D Generation · Computer Vision, 2026 · 18 min read A breakthrough framework called PSD bridges the gap between 2D aesthetic preferences and 3D generation — without requiring a single 3D training sample, by reformulating RLHF as a classifier-free […]

Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference Read More »

TPMRI Framework Architecture.

TPMRI: How Three-Stage Progressive Fusion Is Solving RGB-T Tracking’s Temporal Blindness

TPMRI: How Three-Stage Progressive Fusion Is Solving RGB-T Tracking’s Temporal Blindness | MedAI Research Computer Vision · Knowledge-Based Systems, 2026 · 14 min read When RGB-T Trackers Lose Track: How TPMRI Learned to Remember Through Time TPMRI introduces a three-stage progressive fusion framework that fixes RGB-T tracking’s most frustrating failures — temporal blindness and modality

TPMRI: How Three-Stage Progressive Fusion Is Solving RGB-T Tracking’s Temporal Blindness Read More »

RCD framework addresses three critical bottlenecks in text-to-image generation.

RCD: How Three Simple Fixes Are Solving Stable Diffusion’s Biggest Problem

RCD: How Three Simple Fixes Are Solving Stable Diffusion’s Biggest Problem | MedAI Research MedAI Research Machine Learning About Deep Learning · TPAMI, 2026 · 16 min read When Stable Diffusion Forgets: How RCD Learned to Remember Every Detail RCD introduces a training-free framework that fixes text-to-image diffusion models’ most frustrating failures — missing objects

RCD: How Three Simple Fixes Are Solving Stable Diffusion’s Biggest Problem Read More »

The WEMoE framework transforms critical MLP modules into dynamic mixture-of-experts structures while statically merging non-critical components. Input-dependent routing weights allow the model to adaptively blend task-specific knowledge, achieving superior multi-task performance over static merging methods.

WEMoE: How a Mixture-of-Experts Approach Is Solving the Multi-Task Model Merging Problem

WEMoE: How a Mixture-of-Experts Approach Is Solving the Multi-Task Model Merging Problem | MedAI Research Deep Learning · TPAMI, 2026 · 18 min read The Static Model Merging Problem — and How WEMoE Learned to Adapt WEMoE introduces a dynamic mixture-of-experts approach to multi-task model merging, transforming how we combine fine-tuned neural networks by routing

WEMoE: How a Mixture-of-Experts Approach Is Solving the Multi-Task Model Merging Problem Read More »

the proposed ESM-AnatTractNet model

ESM-AnatTractNet: Deep Learning for Eloquent White Matter Tractography in Pediatric Epilepsy Surgery

ESM-AnatTractNet: Deep Learning for Eloquent White Matter Tractography in Pediatric Epilepsy Surgery | MedAI Research MedAI Research Machine Learning About Neurosurgical AI · Medical Image Analysis, 2026 · 22 min read The Deep Learning System That Learned to Map Eloquent Brain Circuits from Electrical Stimulation and Anatomy ESM-AnatTractNet integrates electrophysiological validation with anatomical context to

ESM-AnatTractNet: Deep Learning for Eloquent White Matter Tractography in Pediatric Epilepsy Surgery Read More »

TAM: Plug-and-Play Temporal Attention Module for Motion-Guided Cardiac Segmentation

TAM: Plug-and-Play Temporal Attention Module for Motion-Guided Cardiac Segmentation

TAM: Plug-and-Play Temporal Attention Module for Motion-Guided Cardiac Segmentation | MedAI Research MedAI Research machine Learning About Cardiac AI · Medical Image Analysis, 2026 · 17 min read The Plug-and-Play Module That Taught Neural Networks to Watch the Heart Move A compact temporal attention module called TAM quietly outperforms much heavier architectures on cardiac segmentation

TAM: Plug-and-Play Temporal Attention Module for Motion-Guided Cardiac Segmentation Read More »

The MT-Net encoder-decoder architecture with dimension transformation. D-DOWN operations compress depth while preserving lateral structure; D-UP operations restore volumetric resolution during decoding

MT-Net: 3D Retinal Microvascular Segmentation via Multi-Scale Topology Regulation

MT-Net: 3D Retinal Microvascular Segmentation via Multi-Scale Topology Regulation Medical Image Analysis · 2026 Vol. 110 · doi:10.1016/j.media.2026.103988 When the Vessels Disappear in Three Dimensions:MT-Net and the Geometry of Retinal Blood Flow Ophthalmic AI ~2,600 words · 12 min read Luo, Zhang et al. — Ningbo University & Chinese Academy of Sciences Every ophthalmologist interpreting

MT-Net: 3D Retinal Microvascular Segmentation via Multi-Scale Topology Regulation Read More »

MSFT-Net: Multimodal Sparse Fusion Transformer for Breast Tumor Classification Using US, SMI & Elastography

MSFT-Net: Multimodal Sparse Fusion Transformer for Breast Tumor Classification Using US, SMI & Elastography Medical Image Analysis · 2026 Vol. 110 · doi:10.1016/j.media.2026.103966 When Three Ultrasound Windows See What One Cannot:MSFT-Net and the Sparse Fusion of Breast Tumor Intelligence Multimodal Medical AI ~2,400 words · 11 min read Xu, Zhuang et al. — Shantou University

MSFT-Net: Multimodal Sparse Fusion Transformer for Breast Tumor Classification Using US, SMI & Elastography Read More »

Fig. 3. Structure of the semantic latent factor encoding module of CD-CMAN model

CD-CMAN: Causality-Driven Neural Network for EEG Signal Decoding in Brain-Computer Interfaces

CD-CMAN: Causality-Driven Neural Network for EEG Signal Decoding in Brain-Computer Interfaces Neuroscience × Deep Learning · March 2026 How Causality Is Rewiring the Brain-Computer Interface:Inside CD-CMAN, the EEG Decoder That Thinks Causally Deep Learning & Medical AI ~2,100 words · 10 min read IEEE TPAMI · Vol. 48 · No. 3 · 2026 Slug: /cd-cman-eeg-decoding-causality-driven-neural-network

CD-CMAN: Causality-Driven Neural Network for EEG Signal Decoding in Brain-Computer Interfaces Read More »

Overview of proposed Slot-BERT model.

Slot-BERT: Revolutionary AI Breakthrough for Self-Supervised Surgical Video Analysis

Introduction: The Challenge of Understanding Complex Surgical Videos Modern surgical procedures generate vast amounts of video data that hold immense potential for training, quality assessment, and AI-assisted decision-making. Yet, one persistent challenge has plagued computer vision researchers: how can machines automatically identify and track surgical instruments and anatomical structures without human-labeled data? Traditional supervised learning

Slot-BERT: Revolutionary AI Breakthrough for Self-Supervised Surgical Video Analysis Read More »