Search: “research”

FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation

arXiv:2605.04651v1 Announce Type: cross Abstract: Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memor

Research

FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation

DGX agent

arXiv:2605.04702v1 Announce Type: new Abstract: Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Des

researcharxiv-cs-cv

7 May 2026

Feature importance analysis for patient management decisions

arXiv:2605.04666v1 Announce Type: new Abstract: The objective of this paper is to understand what characteristics and features of clinical data influence physician's decision about ordering laboratory

Federated Learning for Early Prediction of EV Charging Demand

arXiv:2605.04993v1 Announce Type: new Abstract: Accurate forecasting of electric vehicle (EV) charging demand is critical for grid stability, infrastructure planning, and real-time charging optimizati

FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals

arXiv:2605.04157v1 Announce Type: new Abstract: SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios, asking participating

Agents

From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

arXiv:2605.03205v1 Announce Type: cross Abstract: Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowled

agentsarxiv-cs-ai

From Passive Feeds to Guided Discovery: AI-Initiated Interaction for Vague Intent in Content Exploration

arXiv:2605.02902v1 Announce Type: cross Abstract: Recommendation feeds work well when people are simply browsing, and search works well when they can formulate a query. Between these two cases is a co

researcharxiv-cs-ai

From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models

arXiv:2605.04678v1 Announce Type: cross Abstract: Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous da

From Priors to Perception: Grounding Video-LLMs in Physical Reality

arXiv:2605.04515v1 Announce Type: new Abstract: While Video Large Language Models (Video-LLMs) excel in general understanding, they exhibit systematic deficits in fine-grained physical reasoning. Exis

From Video-to-PDE: Data-Driven Discovery of Nonlinear Dye Plume Dynamics

arXiv:2605.04535v1 Announce Type: new Abstract: Inferring continuum models directly from video is hampered by two facts: the recorded field is uncalibrated image intensity rather than a physical state

Full-chip CMP modelling based on Fully Convolutional Network leveraging White Light Interferometry

arXiv:2605.05062v1 Announce Type: new Abstract: As time-to-market is crucial in the Integrated Circuit (IC) industry, speeding up layout manufacturability verifi-cation is essential. Chemical-Mechanic

Fully Guided Neural Schrodinger bridge for Brain MR image synthesis

arXiv:2501.14171v3 Announce Type: replace-cross Abstract: Multi-modal brain MRI provides essential complementary information for clinical diagnosis. However, acquiring all modalities in practice is of

Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory

arXiv:2604.07401v2 Announce Type: replace-cross Abstract: We study the thermodynamic memory capacity of modern Hopfield networks (Dense Associative Memory models) with continuous states under geometri

Geometry-Aware Neural Optimizer for Shape Optimization and Inversion

arXiv:2605.04474v1 Announce Type: new Abstract: Geometry is central to PDE-governed systems, motivating shape optimization and inversion. Classical pipelines conduct costly forward simulation with geo

GTF: Omnidirectional EPI Transformer for Light Field Super-Resolution

arXiv:2605.04581v1 Announce Type: new Abstract: Light field (LF) image super-resolution benefits from Epipolar Plane Images (EPIs), whose line slopes explicitly encode disparity. However, existing Tra

Gyan: An Explainable Neuro-Symbolic Language Model

arXiv:2605.04759v1 Announce Type: new Abstract: Transformer based pre-trained large language models have become ubiquitous. There is increasing evidence to suggest that even with large scale pre-train

How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences

arXiv:2605.05113v1 Announce Type: new Abstract: We study signal propagation in linear recurrent models at finite width. While existing signal propagation theory relies predominantly on the infinite-wi

Applications

Human-AI Co-Mentorship in Project-Based Learning: A Case Study in Financial Forecasting

arXiv:2605.05144v1 Announce Type: new Abstract: This paper reflects on a AI research project carried out by a team of high-school and early-undergraduate students under the mentorship of graduate rese

applicationsarxiv-cs-lg

Hybrid Iterative Neural Low-Regularity Integrator for Nonlinear Dispersive Equations

arXiv:2605.04853v1 Announce Type: new Abstract: We propose HIN-LRI, a hybrid framework that augments a classical numerical solver with a neural operator trained to correct the solver's structured trun

Ilov3Splat: Instance-Level Open-Vocabulary 3D Scene Understanding in Gaussian Splatting

arXiv:2605.04506v1 Announce Type: new Abstract: We introduce Ilov3Splat, a novel framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS). Most prior

Implicit Representations of Grammaticality in Language Models

arXiv:2605.05197v1 Announce Type: new Abstract: Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitte

Inconsistent Databases and Argumentation Frameworks with Collective Attacks

arXiv:2605.03954v1 Announce Type: cross Abstract: The connection between subset-maximal repairs for inconsistent databases involving various integrity constraints and acceptable sets of arguments with

researcharxiv-cs-ai

InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model

arXiv:2603.11911v3 Announce Type: replace Abstract: We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential

InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery

arXiv:2605.04554v1 Announce Type: new Abstract: Humans constantly interact with their surroundings. Existing end-to-end multi-person human mesh recovery methods, typically based on the DETR framework,

ipc_shared_ptr: A Publish/Subscribe-Aware Smart Pointer for Cross-Process Object Lifetime Management

arXiv:2605.04226v1 Announce Type: cross Abstract: True zero-copy Inter-Process Communication (IPC) in publish/subscribe (pub/sub) middleware such as Robot Operating System 2 (ROS 2) requires subscribe

researcharxiv-cs-ro

ITBoost: Information-Theoretic Trust for Robust Boosting

arXiv:2605.04671v1 Announce Type: new Abstract: Gradient boosting remains a strong and widely used method for tabular data learning, but its performance often degrades when training labels are noisy.

Koopman Identification of Nonlinear Systems via Reservoir Liftings

arXiv:2605.04917v1 Announce Type: new Abstract: Learning tractable linear representations of nonlinear dynamical systems via Koopman operator theory is often hindered by dictionary selection, temporal

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

arXiv:2510.08431v3 Announce Type: replace Abstract: Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diff

Layerwise LQR for Geometry-Aware Optimization of Deep Networks

arXiv:2605.04230v1 Announce Type: new Abstract: Geometry-aware optimizers such as Newton and natural gradient can improve conditioning in deep learning, but scalable variants such as K-FAC, Shampoo, a

Learning-based Statistical Refinement for Denoising

arXiv:2605.04332v1 Announce Type: cross Abstract: This work proposes a learning-based statistical refinement method for improving the denoising results of a given denoiser without knowing the precise

Learning reveals invisible structure in low-rank RNNs

arXiv:2605.04115v1 Announce Type: new Abstract: Learning in neural systems arises from synaptic changes that reshape the representations underlying behavior. While low-rank recurrent neural networks (

Learning Time-Varying Graphs from Incomplete Graph Signals

arXiv:2510.17903v3 Announce Type: replace-cross Abstract: This paper tackles the challenging problem of jointly inferring time-varying network topologies and imputing missing data from partially obser

Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion

arXiv:2605.04291v1 Announce Type: new Abstract: We present a discrete diffusion-based language model using Glauber dynamics from statistical physics. Our main insight is that instead of trying to trai

Library learning with e-graphs on jazz harmony

arXiv:2605.04622v1 Announce Type: new Abstract: Humans can acquire a highly structured intuitive understanding of musical patterns, yet these patterns often require multiple iterations of reflection a

Lightning Unified Video Editing via In-Context Sparse Attention

arXiv:2605.04569v1 Announce Type: new Abstract: Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottle

Lookahead Drifting Model

arXiv:2605.04060v1 Announce Type: cross Abstract: Recently, a new paradigm named drifting model has been proposed for mapping distributions, which achieves the SOTA image generation performance over I

Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction

arXiv:2605.05134v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection method

Malliavin Calculus for Counterfactual Gradient Estimation in Adaptive Inverse Reinforcement Learning

arXiv:2604.01345v2 Announce Type: replace Abstract: Inverse reinforcement learning (IRL) recovers the loss function of a forward learner from its observed responses. Adaptive IRL aims to reconstruct t

MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks

arXiv:2312.06423v3 Announce Type: replace-cross Abstract: Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid prolif

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

arXiv:2605.05115v1 Announce Type: new Abstract: Neural representations carry rich geometric structure; but does that structure causally shape behavior? To address this question, we intervene along pat

Measuring Psychological States Through Semantic Projection: A Theory-Driven Approach to Language-Based Assessment

arXiv:2605.04873v1 Announce Type: new Abstract: Recent advances in natural language processing have enabled increasingly accurate estimation of psychological traits from language. However, most existi

Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answering

arXiv:2605.04116v1 Announce Type: cross Abstract: We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be

Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment

arXiv:2605.04363v1 Announce Type: new Abstract: TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synth

Model synthesis and identifiability analysis of stiff chemical reaction systems with inVAErt networks

arXiv:2605.04134v1 Announce Type: new Abstract: We consider the problem of learning data-driven replicas for stiff systems of ordinary differential equations arising in chemical kinetics that can be e

MoLF: Mixture-of-Latent-Flow for Pan-Cancer Spatial Gene Expression Prediction from Histology

arXiv:2602.02282v2 Announce Type: replace Abstract: Inferring spatial transcriptomics (ST) from histology enables scalable histogenomic profiling, yet current methods are largely restricted to single-

Morphology-Guided Cross-Task Coupling for Joint Building Height and Footprint Estimation

arXiv:2605.04731v1 Announce Type: new Abstract: Building height (BH) and building footprint (BF) jointly describe the vertical and horizontal extent of the built environment and are required inputs fo

MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation

arXiv:2605.04108v1 Announce Type: new Abstract: Federated Learning enables decentralized training by aggregating model updates across clients without sharing raw data, while Split Federated Learning f

Multi-site modelling and reconstruction of past extreme skew surges along the French Atlantic coast

arXiv:2505.00835v2 Announce Type: replace-cross Abstract: Appropriate modelling of extreme skew surges is crucial, particularly for coastal risk management. Our study focuses on modelling extreme skew