The Indispensable Role of User Simulation in the Pursuit of AGI
arXiv:2509.19456v1 Announce Type: new Abstract: Progress toward Artificial General Intelligence (AGI) faces significant bottlenecks, particularly in rigorously evaluating complex interactive…
MOIS-SAM2: Exemplar-based Segment Anything Model 2 for multilesion interactive segmentation of neurofibromas in whole-body MRI
arXiv:2509.19277v2 Announce Type: replace-cross Abstract: Background and Objectives: Neurofibromatosis type 1 is a genetic disorder characterized by the development of…
One Filters All: A Generalist Filter for State Estimation
arXiv:2509.20051v1 Announce Type: cross Abstract: Estimating hidden states in dynamical systems, also known as optimal filtering, is a long-standing problem…
Projective Kolmogorov Arnold Neural Networks (P-KANs): Entropy-Driven Functional Space Discovery for Interpretable Machine Learning
arXiv:2509.20049v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) relocate learnable nonlinearities from nodes to edges, demonstrating remarkable capabilities in scientific…
Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning
arXiv:2509.19090v2 Announce Type: replace-cross Abstract: Medical imaging provides critical evidence for clinical diagnosis, treatment planning, and surgical decisions, yet most…
Identifying Critical Pathways in Coronary Heart Disease via Fuzzy Subgraph Connectivity
arXiv:2509.16288v1 Announce Type: new Abstract: Coronary heart disease (CHD) arises from complex interactions among uncontrollable factors, controllable lifestyle factors, and…
Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement
arXiv:2509.15952v2 Announce Type: replace-cross Abstract: Diffusion and flow matching (FM) models have achieved remarkable progress in speech enhancement (SE), yet…
Confidence-gated training for efficient early-exit neural networks
arXiv:2509.17885v1 Announce Type: cross Abstract: Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint…