01

DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer

02

Integrating Locality-Aware Attention with Transformers for General Geometry PDEs

03

ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models

04

Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation

05

ProPose: Probabilistic 3D Human Pose Estimation with Instance-Level Distribution and Normalizing Flow

06

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

07

PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling

08

Mono-Modalizing Extremely Heterogeneous Multi-Modal Medical Image Registration

9

Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis

10

PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning