Search: “research”

A Functorial Formulation of Neighborhood Aggregating Deep Learning

arXiv:2604.24672v1 Announce Type: new Abstract: We provide a mathematical interpretation of convolutional (or message passing) neural networks by using presheaves and copresheaves of the set of contin

A Heterogeneous Two-Stream Framework for Video Action Recognition with Comparative Fusion Analysis

DGX agent

arXiv:2604.23415v1 Announce Type: new Abstract: Most two-stream action recognition networks apply the same convolutional backbone to both RGB and optical flow streams, ignoring the fact that the two m

researcharxiv-cs-cv

28 Apr 2026

A Layer Separation Optimization Framework for Cross-Entropy Training in Deep Learning

arXiv:2604.23225v1 Announce Type: new Abstract: This paper investigates the deep learning optimization problem with softmax cross-entropy loss. We propose a layer separation strategy to alleviate the

A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks

arXiv:2507.16079v2 Announce Type: replace-cross Abstract: With the advancement of deep learning, reducing computational complexity and memory consumption has become a critical challenge, and ternary n

A Milestone in Formalization: The Sphere Packing Problem in Dimension 8

arXiv:2604.23468v1 Announce Type: cross Abstract: In 2016, Viazovska famously solved the sphere packing problem in dimension 8, using modular forms to construct a 'magic' function satisfying optimalit

A Reconfigured Wheel-Legged Robot for Enhanced Steering and Adaptability

arXiv:2507.22345v2 Announce Type: replace Abstract: Wheel-legged robots integrate leg agility on rough terrain with wheel efficiency on flat ground. However, most existing designs do not fully capital

researcharxiv-cs-ro

A Specialized Importance-Aware Quantum Convolutional Neural Network with Ring-Topology (IA-QCNN) for MGMT Promoter Methylation Prediction in Glioblastoma

arXiv:2604.22877v1 Announce Type: cross Abstract: GBM is a highly aggressive primary malignancy in adults, necessitating personalized therapeutic strategies due to its inherent molecular heterogeneity

A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations

arXiv:2604.24468v1 Announce Type: cross Abstract: Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource

A Synergistic CNN-Transformer Network with Pooling Attention Fusion for Hyperspectral Image Classification

arXiv:2604.23622v1 Announce Type: new Abstract: In the hyperspectral image (HSI) classification task, each pixel is categorized into a specific land-cover category or material. Convolutional neural ne

A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning

arXiv:2604.23114v1 Announce Type: new Abstract: In limited-data settings, a single endpoint mean of an evaluation metric such as the Continuous Ranked Probability Score (CRPS) is itself a random varia

A Topology fixated Shape Gradient Framework for Non Simple Boundary Extraction for CIE Lab color images with Repulsive Energy

arXiv:2604.23167v1 Announce Type: new Abstract: A levelset free but a hybrid image segmentation approach based on a modified version of the piece wise constant shape gradient of an Mumford Shah shape

A Unified Fractional Regularization Framework for Sparse Recovery

arXiv:2604.23184v1 Announce Type: cross Abstract: We propose a unified fractional regularization framework for sparse signal recovery based on the ell_1/ell_p^q model. Our main theoretical contributio

A2DEPT: Large Language Model-Driven Automated Algorithm Design via Evolutionary Program Trees

arXiv:2604.24043v1 Announce Type: new Abstract: Designing heuristics for combinatorial optimization problems (COPs) is a fundamental yet challenging task that traditionally requires extensive domain e

Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace Filter

arXiv:2510.23215v2 Announce Type: replace-cross Abstract: Eigenvalue problems are among the most important topics in many scientific disciplines. With the recent surge and development of machine learn

Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching

arXiv:2604.22901v1 Announce Type: new Abstract: Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E^2-CRF (Er

Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis

arXiv:2604.22850v1 Announce Type: new Abstract: Industrial visual inspection systems often suffer from a severe scarcity of labeled defect data, particularly during the early stages of New Product Int

AD-Relight: Training-Free Banner Relighting via Illumination Translation with Diffusion Priors

arXiv:2604.24407v1 Announce Type: new Abstract: The recent surge in content consumption through streaming services has driven a growing demand for personalized content. Personalized advertisements (ad

AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models

arXiv:2409.01579v2 Announce Type: replace-cross Abstract: Retrieved documents containing noise will hinder RAG from detecting answer clues and make the inference process slow and expensive. Therefore,

AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models

arXiv:2604.24175v1 Announce Type: cross Abstract: Large language models have demonstrated strong reasoning capabilities in general knowledge question answering. However, their ability to handle tempor

Advancing Ligand-based Virtual Screening and Molecular Generation with Pretrained Molecular Embedding Distance

arXiv:2604.24474v1 Announce Type: new Abstract: Molecular similarity plays a central role in ligand-based drug discovery, such as virtual screening, analog searching, and goal-directed molecular gener

Advancing Remote Medical Palpation through Cognition and Emotion

arXiv:2407.05595v3 Announce Type: replace Abstract: Medical palpation is more than force transmission. It is a bidirectional cognitive and emotional exchange between doctor and patient. We model two c

researcharxiv-cs-ro

AlphaFold's Bayesian Roots in Probability Kinematics

arXiv:2505.19763v3 Announce Type: replace Abstract: The seminal breakthrough of AlphaFold in protein structure prediction relied on a learned potential energy function parameterized by deep models, in

Always Tell Me The Odds: Fine-grained Conditional Probability Estimation

arXiv:2505.01595v2 Announce Type: replace-cross Abstract: We present a state-of-the-art model for fine-grained probability estimation of propositions conditioned on context. Recent advances in large l

An AI-Based Supervisory Measurement Integrity Validation Layer for Cyber-Resilient AC/DC Protection in Inverter-Based Microgrids

arXiv:2604.23666v1 Announce Type: cross Abstract: Line current differential relays (LCDRs) are measurement-driven relays that rely on time-synchronized multi-phase current waveforms to infer internal

Model Releases

An Analysis of Active Learning Algorithms using Real-World Crowd-sourced Text Annotations

model-releasesarxiv-cs-ai

arXiv:2604.23290v1 Announce Type: cross Abstract: Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data and tremendously reduce human anno

An Intelligent Fault Diagnosis Method for General Aviation Aircraft Based on Multi-Fidelity Digital Twin and FMEA Knowledge Enhancement

arXiv:2604.22777v1 Announce Type: new Abstract: Fault diagnosis of general aviation aircraft faces challenges including scarce real fault data, diverse fault types, and weak fault signatures. This pap

Applied AI-Enhanced RF Interference Rejection

arXiv:2604.22816v1 Announce Type: cross Abstract: AI-enhanced interference rejection in radio frequency (RF) transmissions has recently attracted interest because deep learning approaches trained on b

Approximating Uniform Random Rotations by Two-Block Structured Hadamard Rotations in High Dimensions

arXiv:2604.23418v1 Announce Type: new Abstract: Uniform random rotations are a useful primitive in applications such as fast Johnson-Lindenstrauss embeddings, kernel approximation, communication-effic

ARC Prize 2026: ARC-AGI-3 now has H100s Thank you to our partners at @kaggle for powering the ARC-AGI-3 competition with H100s Participants …

researchfrancois-chollet--x

ARC Prize 2026: ARC-AGI-3 now has H100s Thank you to our partners at @kaggle for powering the ARC-AGI-3 competition with H100s Participants now have a pool of accelerators (subject to submission limit

B-FIRE: Binning-Free Diffusion Implicit Neural Representation for Hyper-Accelerated Motion-Resolved MRI

arXiv:2601.06166v2 Announce Type: replace Abstract: Accelerated dynamic volumetric magnetic resonance imaging (4DMRI) is essential for applications relying on motion resolution. Existing 4DMRI produce

Bayesian Optimization for Function-Valued Responses under Min-Max Criteria

arXiv:2512.07868v2 Announce Type: replace-cross Abstract: Bayesian optimization is widely used for optimizing expensive black box functions, but most existing approaches focus on scalar responses. In

BERT-APC: A Reference-free Framework for Automatic Pitch Correction via Musical Context Inference

arXiv:2511.20006v2 Announce Type: replace-cross Abstract: Automatic Pitch Correction (APC) enhances vocal recordings by aligning pitch deviations with intended musical notes. However, existing APC sys

Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks

arXiv:2506.22429v2 Announce Type: replace-cross Abstract: In recent years, the neural tangent kernel (NTK) and neural network Gaussian process kernel (NNGP) have given theoreticians tractable limiting

BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning

arXiv:2604.24089v1 Announce Type: new Abstract: Bridging molecular structures and natural language is essential for controllable design. Autoregressive models struggle with long-range dependencies, wh

BIMStruct3D: A Fully Automated Hybrid Learning Scan-to-BIM Pipeline with Integrated Topology Refinement

arXiv:2604.24311v1 Announce Type: new Abstract: Automatic generation of Building Information Models (BIM) from building scans is a key challenge in architecture and construction. We present a modular

Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions

arXiv:2511.09465v3 Announce Type: replace-cross Abstract: Diffusion and flow matching approaches to generative modeling have shown promise in domains where the state space is continuous, such as image

Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Cameras

arXiv:2604.24024v1 Announce Type: new Abstract: Conventional multi-projector calibration requires projecting and capturing structured light patterns for each projector sequentially, causing calibratio

BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning

arXiv:2510.13799v2 Announce Type: replace Abstract: As retrieval-augmented generation (RAG) tackles complex tasks, increasingly expanded contexts offer richer information, but at the cost of higher la

Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction

arXiv:2604.23803v1 Announce Type: new Abstract: Egocentric video provides a unique view into human perception and interaction, with growing relevance for augmented reality, robotics, and assistive tec

BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning

arXiv:2604.23165v1 Announce Type: new Abstract: Spiking Vision Transformers (S-ViTs) offer a promising framework for energy-efficient visual learning. However, existing designs remain limited by two f

BurstGP: Enhancing Raw Burst Image Super Resolution with Generative Priors

arXiv:2604.23508v1 Announce Type: new Abstract: Burst image super resolution (BISR) aims to construct a single high-resolution (HR) image by aggregating information from multiple low-resolution (LR) f

Can an MLP Absorb Its Own Skip Connection?

arXiv:2604.23705v1 Announce Type: new Abstract: We study when a skip connection around a single-hidden-layer MLP can be absorbed into a residual-free MLP of the same width. We first show that for any

Can Humans Detect AI? Mining Textual Signals of AI-Assisted Writing Under Varying Scrutiny Conditions

arXiv:2604.23471v1 Announce Type: cross Abstract: This study asks whether the threat of AI detection changes how people write with AI, and whether other people can tell the difference. In a two-phase

Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style

arXiv:2604.24444v1 Announce Type: new Abstract: Despite the growing use of large language models (LLMs) for writing tasks, users may hesitate to rely on LLMs when personal style is important. Post-edi

CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation

arXiv:2601.06352v2 Announce Type: replace Abstract: Adapting large language models to individual users remains challenging due to the tension between fine-grained personalization and scalable deployme

Cardiac Stability Theory: An Axiomatically Grounded Framework for Continuous Cardiac Health Monitoring via Smartphone Photoplethysmography

arXiv:2604.23876v1 Announce Type: new Abstract: We present Cardiac Stability Theory (CST), an axiomatically grounded framework formally defining cardiovascular health as a stability margin around a ca

Caries DETR: Tooth Structure-aware Prior and Lesion-aware Dynamic Loss Refinement for DETR Based Caries Detection

arXiv:2604.23718v1 Announce Type: new Abstract: As dental caries appear as subtle, low-contrast lesions in intraoral imaging, existing deep learning models face significant challenges in the early det

Characterizations of Admissible Objective Functions for Hierarchical Clustering

arXiv:2604.23628v1 Announce Type: cross Abstract: Hierarchical clustering is a fundamental task in data analysis, yet for a long time it lacked a principled objective function. Dasgupta [STOC 2016] in