Claims Browser

A Swin V2 encoder pretrained on 10,444 public 3D CT volumes using a DINOv2-style objective can be successfully adapted to T2-weighted MRI for rectal cancer segmentation

"A Swin V2 encoder pretrained on 10,444 public 3D CT volumes using a DINOv2-style objective was adapted to T2-weighted MRI through four cumulative configurations"

SWIFTe reduced total parameters by 70.1% compared to SWIFT while increasing tumor detection rate from 89.9% to 93.9%

"SWIFTe reduced total parameters by 70.1% (from 72.8M to 21.8M) and increased tumor detection rate from 89.9% to 93.9%"

There is a trade-off between tumor detection and boundary agreement in rectal cancer segmentation: removing tumor-aware augmentation reduced detection from 93.9% to 89.9% but increased surface DSC from 0.61 to 0.64

"removing tumor-aware augmentation reduced detection from 93.9% to 89.9% but increased surface DSC from 0.61 to 0.64, demonstrating a detection-boundary-agreement trade-off"

SWIFTe-LoRA achieved similar segmentation performance while using only 14.6% of SWIFTe's trainable parameters

"SWIFTe-LoRA used 14.6% of SWIFTe's trainable parameters while retaining similar segmentation performance"

Knowledge distillation combined with generative models can enable robust and green robotic vehicle communications in NOMA frameworks

"we propose a knowledge distillation-driven and generative models-enhanced NOMA framework for robust and green RV communications, named KDG-SemNOMA."

The SWIFTe-LDE4 ensemble achieved the best calibration after temperature scaling but still exhibited residual miscalibration with an expected calibration error of 0.217

"SWIFTe-LDE4 achieved the lowest calibration errors among the four configurations after temperature scaling (expected calibration error, 0.217; Brier score, 0.222), although the absolute expected calibration error indicates residual miscalibration"

The efficiency-calibration patterns observed are robust across different pretrained initializations but do not demonstrate external clinical generalizability

"Similar efficiency-calibration patterns were observed using the public VoCo checkpoint, supporting robustness across pretrained initializations rather than external clinical generalizability"

LLM agents are increasingly being applied to anomaly detection and root-cause analysis in time-series observations from real-world systems

"LLM agents are increasingly applied to anomaly detection and root-cause analysis in time-series observations collected from real-world systems"

LLM agent performance on anomaly detection and root-cause analysis tasks has not been systematically evaluated under controlled conditions

"their performance on these tasks has not been systematically evaluated under controlled conditions"

LLM agents benefit substantially from domain context when analyzing time-series observations from dynamical systems

"Our results show that agents benefit substantially from domain context"

LLM agents explore time-series data primarily through numerical console output rather than visualizations

"explore data primarily through numerical console output rather than visualizations"

LLM agents generally perform worse when required to produce a Python script for root-cause prediction than when submitting predictions directly

"agents generally perform worse when required to produce a Python script that maps each time-series sample to a predicted root-cause label than when they submit predictions directly"

Large language models enable direct translation from design intent to hardware implementations in electronic design automation

"Large language models (LLMs) extend this trajectory by enabling direct translation from design intent to hardware implementations."

LLM capability in EDA accumulates through three hierarchical roles: Generator, Agent, and Orchestrator

"we instead define three hierarchical roles that reveal how capability accumulates: a Generator that produces design artifacts in a single pass, an Agent that refines outputs through iterative tool feedback, and an Orchestrator that coordinates decisions across EDA-stages."

A latest personal agent is already valued at $2.5 billion and attracting significant investor interest

"The latest personal agent making investors go crazy (already valued at $2.5B)."

Active diffusion-based methods can discover correct parameter regions even when initial training bounds exclude true parameters by iteratively detecting and correcting model misspecification through posterior uncertainty

"By iteratively detecting and correcting model misspecification through posterior uncertainty, the method discovers and learns the correct region of parameter space, even when initial training bounds exclude the true parameters."

Adaptive domain augmentation for inverse problems can be given a principled Bayesian justification that ensures robust inference under incomplete prior knowledge

"This provides a principled, Bayesian justification for adaptive domain augmentation and ensures robust inference for inverse problems under incomplete prior knowledge."

The proposed diffusion-based inverse solver is effective for quantum chromodynamics analysis of nucleon structure, specifically parameterizing quantum correlation functions to event observables

"We demonstrate the effectiveness of our inverse solver for a toy inverse problem with infinite solutions, and for the parameterization of the quantum correlation functions to event observables in a Quantum Chromodynamics analysis of nucleon structure."