research note
Mean Flow Distillation — Robust and Stable Distillation for Flow Matching Models
Flow Matching (FM) models excel at generative tasks but suffer from slow ODE-based iterative sampling, limiting real-time use
Research
Page 35 of 104
Skip to content
research note
Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diagnosis of Asthma and COPD Using CNN- and GRU-Based Networks
This study addresses the challenge of differential diagnosis between asthma and COPD using acoustic analysis of multi-channel pulmonary sounds
research note
Piper — A Programmable Distributed Training System
Piper addresses the complexity and inflexibility in current large-scale distributed training systems that combine multiple parallelism strategies (data, pipeline, expert, tensor parallelism) and me…
research note
Pre-Fault Voltage Discrimination and Time-Domain Protection for Distribution Networks with Inverter-Based Resources
This paper addresses the challenge of fault detection in distribution networks increasingly penetrated by inverter-based resources (IBRs), which produce low short-circuit fault currents that underm…
research note
Spatially heterogeneous power-law attenuation with multiple relaxation mechanisms for ultrasound modeling
This paper addresses the challenge of accurately modeling spatially heterogeneous power-law frequency-dependent attenuation in biological tissues for ultrasound simulations
research note
The Agentic Web Requires New Normative Infrastructure
This paper addresses the emerging reality of the "agentic web," where users interact with online services predominantly through AI agents acting on their behalf
research note
Time-frequency localization of bird calls in dense soundscapes
This work addresses the limitation of most bioacoustic classifiers that only predict species presence in broad time windows without precisely localizing bird vocalizations in time and frequency
research note
UniPET — a universal network for high-quality PET image denoising across varied dose reduction factors
This paper addresses the challenge of PET image denoising across varied dose reduction factors (DRFs), a key practical problem since existing DL methods assume a fixed DRF and degrade when the DRF …
research note
WorldOlympiad — Can Your World Model Survive a Triathlon?
WorldOlympiad introduces a comprehensive benchmark to evaluate video-based world models across three critical dimensions — physical faithfulness, geometric consistency, and interaction fidelity
research note
A Bell-State Extension of Loop-Back Quantum Key Distribution
This work addresses persistent challenges in bidirectional quantum key distribution (QKD) such as classical data leakage, signal-space confinement to predictable subspaces, and limited detectabilit…
research note
Adaptive Derivative Estimation via Stein's Unbiased Risk
This work addresses the classical challenge of causal derivative estimation from noisy discrete-time data, fundamental in control, HCI, and biomedical domains
research note
AetheRock — An Arm-Worn Robot Teaching System for Force-Guided Vision-Tactile Learning
This paper addresses significant challenges in robotic contact-rich manipulation that rely on force and tactile sensing