Search: “research”

EvtGraph: Event-Adaptive Compression for Sparse Temporal Graph Learning in Multimodal Time Series

arXiv:2608.04368v1 Announce Type: new Abstract: Multimodal temporal data are inherently irregular and uneven in information density, yet most models rely on uniform discretization, leading to ineffici

Research

Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting

DGX agent

arXiv:2607.15890v2 Announce Type: replace Abstract: Perceiving multimodal cues and forecasting fine-grained actions from an egocentric (Ego) perspective is vital for applications like robot manipulati

researcharxiv-cs-cv

6 Aug 2026

Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models

arXiv:2608.04765v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control. However,

FBID: Adaptive Personalized Federated Learning for Robust Out-of-Distribution Attack Detection in IoT Networks

arXiv:2608.04073v1 Announce Type: cross Abstract: Personalized Federated Learning (PFL) has emerged as a promising solution for intrusion detection in heterogeneous IoT environments, as it can improve

Feasibility of Embedded Photoplethysmography Sensing in Short-Duration Tactile Interactions With Pocket-Sized Robots Using IMU- and Confidence-Based Filtering

arXiv:2608.04242v1 Announce Type: new Abstract: Ubiquitous companion robots offer a promising avenue for immediate anxiety relief in children, yet their effectiveness relies on the ability to monitor

researcharxiv-cs-ro

FM4WiFi: Flow Matching for Multi-AP Coordination in Dense Deployments of Beyond Wi-Fi 8 Networks

arXiv:2608.04050v1 Announce Type: cross Abstract: Wi-Fi networks are moving beyond random channel access toward tightly coordinated operation across access points (APs), a shift reflected in Wi-Fi 8's

For a very long time most high-performing AI models were end-to-end neural models; vector input -> vector output, with only ultra-thin symbo…

researchfrancois-chollet--x

For a very long time most high-performing AI models were end-to-end neural models; vector input -> vector output, with only ultra-thin symbolic preprocessing and postprocessing layers (e.g. label deco

Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection

arXiv:2608.04394v1 Announce Type: new Abstract: Cross-Domain Few-Shot Object Detection (CDFSOD) aims to transfer knowledge from data-rich upstream generic domains to downstream expert domains using sc

From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs

arXiv:2608.04206v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) often require high-accuracy quasi-Newton refinement to obtain reliable partial differential equation solutions,

Fundamentals of quantum Boltzmann machine learning with visible and hidden units

arXiv:2512.19819v2 Announce Type: replace-cross Abstract: One of the primary applications of classical Boltzmann machines is generative modeling, wherein the goal is to tune the parameters of a model

GenAI-Powered Inference

arXiv:2507.03897v3 Announce Type: replace Abstract: We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text

Generative neural physics enables quantitative volumetric ultrasound of tissue mechanics

arXiv:2508.12226v3 Announce Type: replace Abstract: Ultrasound Tomography (UT) is a radiation-free, high-resolution modality, but remains limited for musculoskeletal imaging due to the high computatio

German parties shifted towards intuition-based rhetoric after the far right's parliamentary breakthrough

arXiv:2608.05075v1 Announce Type: new Abstract: The spread of misinformation is widely perceived as a threat to democratic deliberation, yet how political elites' rhetorical commitments to truth shift

Global Attention-Fused Image Cropping with Attention-Guided and Global-Aligned Crop Evaluator

arXiv:2608.04821v1 Announce Type: new Abstract: Image cropping aims to improve image aesthetics by preserving important content within an appropriately composed region. However, most existing methods

Group-Equivariant Diffusion Models for Lattice Field Theory

arXiv:2510.26081v2 Announce Type: replace-cross Abstract: Near the critical point, Markov Chain Monte Carlo (MCMC) simulations of lattice quantum field theories (LQFT) become increasingly inefficient

HexMIL: Hierarchical Attention MIL for Ante-Hoc Explainable Detection of AI-Manipulated CT Volumes

arXiv:2608.05101v1 Announce Type: new Abstract: The emergence of medical deepfakes, i.e., medical images manipulated by deep generative models, poses a significant threat to clinical workflows. Howeve

Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite

arXiv:2608.05095v1 Announce Type: new Abstract: Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new facts and external feedback continue t

HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding

arXiv:2608.04610v1 Announce Type: new Abstract: 3D vision-language models (3D VLMs) enable spatial reasoning over multi-view scenes but suffer from substantial token redundancy due to duplicated obser

I would have assumed it was fairly obvious, but in case it's not: a million-line codebase (also known as a 'harness'), running at inference …

researchfrancois-chollet--x

I would have assumed it was fairly obvious, but in case it's not: a million-line codebase (also known as a 'harness'), running at inference time, orchestrating thousands of calls to a neural network f

Image Classification Using CNN-QNN Hybrid Model with Optimized Correlated Features

arXiv:2608.04379v1 Announce Type: cross Abstract: We propose a method to optimize the correlation among convolutional neural network (CNN) features that are used as inputs to quantum neural network (Q

IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution

arXiv:2608.04777v1 Announce Type: cross Abstract: Oscillatory signals, such as vibration, carry class-discriminative information in specific frequency bands; perturbing them in raw feature space for c

Imitation Learning from Human Motion Alone Does Not Guarantee Biomechanically Plausible Gait Kinetics

arXiv:2603.12408v3 Announce Type: replace-cross Abstract: Motion imitation learning (IL) is increasingly used in robotics and human gait modeling, yet its ability to recover biomechanically consistent

InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Flow Matching Inversion

arXiv:2608.04142v1 Announce Type: cross Abstract: Existing reference-free methods for evaluating music perceptual quality alleviate the need for paired noisy-clean data, but they still rely on a backg

iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data

arXiv:2608.04348v1 Announce Type: cross Abstract: Multimodal learning of images and tabular data is often impaired by ineffective representations, resulting in redundancy, dispersion, and generalizati

Koopman-Based Nonlinear Identification and Model Predictive Control of a Turbofan Engine

arXiv:2604.01730v2 Announce Type: replace Abstract: This paper investigates Koopman operator-based approaches for multivariable control of a two-spool turbofan engine. A physics-based component-level

Learning Neural Networks by Neuron Pursuit

arXiv:2509.12154v2 Announce Type: replace Abstract: The first part of this paper studies the evolution of gradient flow for homogeneous neural networks near a class of saddle points exhibiting a spars

Leveraging Machine Learning to Gain Insights on Quantum Thermodynamic Entropy

arXiv:2305.06177v1 Announce Type: cross Abstract: We present a thermodynamic analysis of a quantum engine that uses a single quantum particle as its working fluid, inspired by Szilard's classical sing

LLM-based Vulnerability Discovery in Business Process Documentation

arXiv:2608.04271v1 Announce Type: cross Abstract: Just like software and hardware, business processes are susceptible to vulnerabilities that can lead to product quality issues, delays, and increased

MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning

arXiv:2608.05088v1 Announce Type: new Abstract: Muon has recently emerged as a promising alternative to AdamW for language model pretraining by orthogonalizing momentum matrices using Newton-Schulz it

Mamba with Hierarchical Memory: Solving Representation Bottleneck in Long Sequence Modeling

arXiv:2608.02347v2 Announce Type: replace Abstract: Recurrent linear attention models (RLAs) such as Mamba offer efficient linear-time sequence modeling as an alternative to Transformers, yet their fi

MarsCast: Transfer Learning of AI Weather Foundation Models to Planetary Atmospheres

arXiv:2608.05054v1 Announce Type: cross Abstract: We investigate the transferability of Earth weather foundation models to planetary atmospheres by adapting the GraphCast graph neural weather forecast

Masked diffusion enables coherent beat tracking

arXiv:2608.04624v1 Announce Type: cross Abstract: Current neural networks for beat tracking generate invalid outputs, such as consecutive downbeats and erratic tempo changes, even when these are not p

MemFly: On-the-Fly Memory Optimization via Information Bottleneck

arXiv:2602.07885v2 Announce Type: replace Abstract: Long-term memory enables large language model agents to tackle complex tasks through historical interactions. However, existing frameworks encounter

MINT: Tensor Decomposition on Stacked Recurrence Matrices for Time Series Data Mining

arXiv:2608.04157v1 Announce Type: new Abstract: Recurrence plots are a time series data mining primitive applied to a variety of domains (e.g. star light curves, sound waveforms, CCT telemetry). This

MME: Mixture of Mesh Experts with Random Walk Transformer Gating

arXiv:2603.00828v2 Announce Type: replace Abstract: In recent years, various methods have been proposed for mesh analysis, each offering distinct advantages and often excelling on different object cla

MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs

arXiv:2608.04680v1 Announce Type: cross Abstract: To adopt the Vision Transformers (ViTs) in resource-constrained environment, token pruning is widely used to reduce computational cost without impacti

Multi-View Face and Gesture Animation with Dynamic Gaussians

arXiv:2608.04722v1 Announce Type: new Abstract: Creating photorealistic 3D human avatars with realistic upper-body motion remains challenging. Existing approaches either focus on the head and overlook

Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Flow-matching

arXiv:2608.05103v1 Announce Type: new Abstract: Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data. In this study, we propose a fundame

MVTOP: Multi-View Transformer-based Object Pose-Estimation

arXiv:2508.03243v2 Announce Type: replace Abstract: We present MVTOP, a novel transformer-based method for multi-view rigid object pose estimation. Through an early fusion of the view-specific feature

Neighborhood-Aware Dual Biomedical Entity Linking

arXiv:2608.04144v1 Announce Type: cross Abstract: Biomedical entity linking grounds mentions in clinical and scientific text to entities in a curated knowledge base (KB) with ontological structure, wh

NeuroPB: Scaling Neural Decoding with Pretrained Behavioral Representations

arXiv:2608.04389v1 Announce Type: new Abstract: Decoding continuous motor trajectories from neural activity is essential for developing practical brain-computer interfaces (BCIs). However, current neu

Nonparametric Goodness-of-fit Testing under Covariate Shift

arXiv:2608.04860v1 Announce Type: cross Abstract: This paper develops procedures for nonparametric goodness-of-fit testing under covariate shift, where labelled data are drawn from a source population

On Hamming-Lipschitz Type Stability of the Subdominant (Minmax) Ultrametric: Theory and Simple Proofs

arXiv:2608.04014v1 Announce Type: cross Abstract: The subdominant (minmax) ultrametric is a canonical tree-structured summary of a dissimilarity matrix, arising equivalently as the ultrametric induced

On MUON optimization: From non-convergence to an error analysis with Polar Express and the Newton-Schulz polynomial from implementations

arXiv:2608.04607v1 Announce Type: cross Abstract: Stochastic gradient descent (SGD) optimization methods are the standard instruments for the training of deep neural networks (DNNs). In many relevant

On The Suitability of Differential Dataflow For Datalog Interpretation In Highly Dynamic Settings

arXiv:2308.04214v2 Announce Type: replace-cross Abstract: In the domain of knowledge representation and reasoning within AI, datalog engines play an ever-increasingly crucial role. The crux of their o

Optimal Training-Time Scaling in Gradual Adaptation

arXiv:2608.04927v1 Announce Type: new Abstract: In gradual adaptation, how should the training time on each task change as the number of intermediate tasks increases? We study this question for overpa

Optimizing the Preconditioner: A Black-box Online-to-Nonconvex Conversion with Static Regret Minimization Oracles

arXiv:2607.17607v2 Announce Type: replace Abstract: We study whether stochastic nonconvex optimization can be reduced to ordinary static regret minimization in online convex optimization in a black-bo

ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration

arXiv:2608.04999v1 Announce Type: cross Abstract: Analog circuit design automation using reinforcement learning (RL) has emerged as a promising approach for reducing manual effort. However, many exist