Fourier
PulseAugur coverage of Fourier — every cluster mentioning Fourier across labs, papers, and developer communities, ranked by signal.
- 2026-05-13 partnership Fourier Intelligence signed strategic cooperation agreements with NHG Health and Nagoya University to advance embodied healthcare. source
12 day(s) with sentiment data
-
DeepSeek raises $15.8B, Meta partners on robot, Alibaba integrates AI into Apple
DeepSeek has secured a significant 105.5 billion RMB (approximately $15.8 billion) in its second round of funding, attracting nearly 30 investors including Tencent Holdings and CATL, with state-backed entities now compr…
-
Meta reportedly builds household humanoid robot prototype, Max
Meta has reportedly developed a prototype humanoid robot, codenamed Max, designed for household chores. The robot, built in collaboration with Chinese robotics company Fourier, stands approximately 1.5 meters tall and w…
-
New framework O2D-MedNet enhances medical image segmentation
Researchers have developed O2D-MedNet, a novel framework designed to improve medical image segmentation. This dual-domain approach integrates features from both Fourier and Wavelet domains to better handle image degrada…
-
WaFIR introduces subband-adaptive routing for blind image restoration
Researchers have introduced WaFIR, a novel decoder module designed for blind all-in-one image restoration. This system decomposes image features into subbands, uses Fourier descriptors to summarize each subband, and rou…
-
FoundPDE: New foundation model for symbolic discovery of PDEs
Researchers have developed FoundPDE, a generative foundation model designed for the symbolic discovery of partial differential equations (PDEs) from data. This transformer-based model utilizes Fourier and spatial-deriva…
-
New AQUA-Net model enhances underwater images using frequency and illumination fusion
Researchers have developed AQUA-Net, a novel deep learning model designed to enhance underwater images. This network addresses challenges like color distortion and low contrast by integrating spatial, frequency, and ill…
-
New method learns optimal phases for quantum state preparation
Researchers have developed a new method to optimize the preparation of quantum states in bosonic qudits using SNAP-Displacement sequences. This technique learns which phases are necessary and their values, employing a d…
-
Study reveals grokking in MLPs sharpens pre-existing algorithms
A new study published on arXiv investigates the phenomenon of 'grokking' in neural networks, specifically focusing on ReLU MLPs trained on modular arithmetic. Researchers found that instead of sinusoidal weight distribu…
-
New FA-PI Method Enhances Defect Detection in Concrete Structures
Researchers have developed a new method called Frequency-Amplitude Persistence Image (FA-PI) to improve the detection of defects in concrete structures using impact-echo testing. This technique constructs a two-dimensio…
-
New method explains how neural networks learn modular addition
Researchers have developed a new method using probability signatures to understand how neural networks learn modular addition tasks. This approach reveals that these networks develop specific Fourier-structured represen…
-
Study reveals random testing underestimates neural operator error
A new study published on arXiv investigates the accuracy of neural operators, specifically those utilizing wave-based processors for Fourier layers. The research highlights that random-device testing significantly under…
-
New S2-PINN method advances uncertainty quantification for random PDEs
Researchers have developed S$^{2}$-PINN, a novel approach to uncertainty quantification for random partial differential equations. This method utilizes a learnable Gaussian spatial dictionary, Fourier temporal features,…
-
New AI method enhances medical image generalization using Fourier phase
Researchers have developed PhaseAT, a novel adversarial training framework designed to improve the generalization capabilities of deep learning models in medical imaging. This method focuses on manipulating the Fourier …
-
Goal representation quality has minimal impact on GCRL performance, study finds
A new research paper investigates the impact of goal representations on goal-conditioned reinforcement learning (GCRL). The study found that the quality of the goal representation has minimal effect on downstream perfor…
-
New R$^2$NO framework adapts simulated neural operators to real-world data
Researchers have developed a new framework called the Retain-and-Repair Neural Operator (R$^2$NO) to better adapt neural operators pretrained on simulations to real-world data. This method involves finetuning the pretra…
-
AI model predicts coronary blood flow from angiography
Researchers have developed a novel physics-informed deep learning framework to analyze coronary blood flow from dual-view angiography, addressing limitations of existing methods. The system uses an attention-enhanced CN…
-
New paper proposes storing knowledge as periodic latent dynamics
A new research paper titled "Knowledge as Orbit: Finite Collections as Phases of an Exactly Periodic Latent Generator" proposes a novel method for storing finite knowledge intensionally rather than extensionally. The ap…
-
Deep learning framework enables cross-physics mapping between distinct physical domains
Researchers have introduced Cross-Physics Mapping (CPM), a novel framework for operator learning that enables deep learning models to translate between physical domains governed by different equations. The study propose…
-
New framework analyzes encoder-decoder operator learning via limiting kernels
This paper introduces a novel framework for analyzing operator learning within encoder-decoder architectures. It formulates operator learning on function spaces, addressing the challenge of finite-dimensional training d…
-
Structured Features Overfit in ML Models, New Research Shows
Researchers have demonstrated that structured feature maps in over-parameterized ridge regression can lead to overfitting, contrasting with unstructured random feature maps that generalize. Specifically, a band-limited …