Search: “research”

Evolving Knowledge Distillation for Lightweight Neural Machine Translation

arXiv:2605.09924v1 Announce Type: new Abstract: Recent advancements in Neural Machine Translation (NMT) have significantly improved translation quality. However, the increasing size and complexity of

researcharxiv-cs-cl

Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents

DGX agent

arXiv:2605.10663v1 Announce Type: new Abstract: Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactio

researcharxiv-cs-ai

12 May 2026

Exact Fixed-Point Constraints in Neural-ODEs with Provable Universality

arXiv:2605.10613v1 Announce Type: cross Abstract: We introduce a technique that enables Neural-ODEs to approximate arbitrary velocity fields with a priori planted fixed-points. Specifically, a recipe

Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning

arXiv:2605.10680v1 Announce Type: new Abstract: This paper proposes a paradigm shift linking machine unlearning directly to the structure of the data distributions rather than a mere update of the neu

Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning

arXiv:2605.09369v1 Announce Type: new Abstract: Knowledge Tracing (KT) models students' knowledge states based on learning interactions to predict performance. While deep learning-based KT models have

Explaining Graph Neural Networks for Node Similarity on Graphs

arXiv:2407.07639v2 Announce Type: replace-cross Abstract: Similarity search is a fundamental task for exploiting information in various applications dealing with graph data, such as citation networks

Explicit and Effectively Symmetric Schemes for Neural SDEs on Lie Groups

arXiv:2509.20599v2 Announce Type: replace Abstract: Backpropagation through (neural) SDE solvers is traditionally approached in two ways: discretise-then-optimise, which offers accurate gradients but

Explicit Bounds on the Hausdorff Distance for Truncated mRPI Sets via Norm-Dependent Contraction Rates

arXiv:2511.18374v2 Announce Type: replace Abstract: We derive a computable closed-form upper bound on the Hausdorff distance between a truncated minimal robust positively invariant (mRPI) set and its

researcharxiv-cs-ro

Exploring 6D Object Pose Estimation with Deformation

arXiv:2604.06720v2 Announce Type: replace Abstract: We present DeSOPE, a large-scale dataset for 6DoF deformed objects. Most 6D object pose methods assume rigid or articulated objects, an assumption t

Exploring and Exploiting Stability in Latent Flow Matching

arXiv:2605.08398v1 Announce Type: cross Abstract: In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capaci

Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering

arXiv:2605.10318v1 Announce Type: new Abstract: Large language models (LLMs) allow users to query databases using natural language by translating questions into executable queries. Despite strong prog

researcharxiv-cs-cl

ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models

arXiv:2605.10045v1 Announce Type: new Abstract: Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents d

Factual recall in linear associative memories: sharp asymptotics and mechanistic insights

arXiv:2605.10795v1 Announce Type: cross Abstract: Large language models demonstrate remarkable ability in factual recall, yet the fundamental limits of storing and retrieving input--output association

Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration

arXiv:2605.10330v1 Announce Type: cross Abstract: We propose a novel adaptive Mixture-of-Experts (MoE) framework for time series forecasting that enhances expert specialization by incorporating expert

FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation

arXiv:2601.22204v2 Announce Type: replace Abstract: Federated learning (FL) encounters substantial challenges due to heterogeneity, leading to gradient noise, client drift, and partial client particip

FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-level Anomaly Detection

arXiv:2605.09428v1 Announce Type: new Abstract: Graph-level anomaly detection (GLAD) is crucial for ensuring the reliability of graph-driven applications by identifying abnormal graphs that deviate fr

Federated Concept-Based Models: Interpretable models with distributed supervision

arXiv:2602.04093v2 Announce Type: replace Abstract: Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept ann

FERA: Uncertainty-Aware Federated Reasoning for Large Language Models

arXiv:2605.10082v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong reasoning capabilities when guided by high-quality demonstrations, yet such data is often distributed across

researcharxiv-cs-cl

Fetal Brain Imaging: A Composite Neural Network Approach for Keyframe Detection in Ultrasound Videos

arXiv:2605.09750v1 Announce Type: new Abstract: This article presents a novel approach to keyframe detection in ultrasound videos, with a particular focus on fetal brain imaging. The proposed model is

Field-Localized Forgery Detection for Digital Identity Documents

arXiv:2605.09089v1 Announce Type: cross Abstract: Digital identity verification systems used in remote onboarding rely on document images to authenticate users, making them vulnerable to localized man

Finer is Better (with the Right Scaling)

arXiv:2605.08565v1 Announce Type: new Abstract: Microscaling is a critical technique for preserving the quality of Large Language Models (LLMs) quantized to ultra-low precision formats. Intuitively, f

Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs

arXiv:2605.08894v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance but incur high deployment costs, motivating extremely low-bit but lossy quantization. Existing

Fixed-Point Neural Optimal Transport without Implicit Differentiation

arXiv:2605.10792v1 Announce Type: cross Abstract: We propose an implicit neural formulation of optimal transport that eliminates adversarial min--max optimization and multi-network architectures commo

FlowADMM: Plug-and-play ADMM with Flow-based Renoise-Denoise Priors

arXiv:2605.08640v1 Announce Type: new Abstract: Plug-and-play (PnP) methods for solving inverse problems have recently achieved strong performance by leveraging denoising priors based on powerful gene

Foundations of Reliable Inference: Reliability-Efficiency Co-Design

arXiv:2605.10351v1 Announce Type: new Abstract: Reliable inference requires that artificial intelligence (AI) models provide trustworthy uncertainty estimates, not merely accurate predictions. Recent

Fourier Feature Methods for Nonlinear Causal Discovery: FFML Scoring, TRFF Scoring, and FFCI Testing in Mixed Data

arXiv:2605.05743v2 Announce Type: replace-cross Abstract: Gaussian process (GP) marginal likelihood scores and kernel conditional independence tests are theoretically appealing for nonlinear causal di

FQPDR: Federated Quantum Neural Network for Privacy-preserving Early Detection of Diabetic Retinopathy

arXiv:2605.08324v1 Announce Type: cross Abstract: Diabetic Retinopathy (DR) is a common complication of diabetes that can lead to blindness of people. Detecting DR at the earliest stage is essential t

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness

arXiv:2605.08896v1 Announce Type: cross Abstract: Robust adaptation of LLMs and VLMs is often evaluated by average accuracy or average consistency under perturbations. However, these averages can hide

Free Energy Manifold: Score-Based Inference for Hybrid Bayesian Networks

arXiv:2605.09839v1 Announce Type: cross Abstract: We introduce the Free Energy Manifold (FEM), a score-trained conditional energy model specialized for inference in hybrid Bayesian networks with discr

Applications

FrequencyCT: Frequency domain pseudo-label generation for self-supervised low-dose CT denoising

arXiv:2605.10583v1 Announce Type: new Abstract: Despite extensive research on computed tomography (CT) denoising, few studies exploit projection-domain data characteristics to mitigate noise correlati

applicationsarxiv-cs-cv

From Mechanistic to Compositional Interpretability

arXiv:2605.08934v1 Announce Type: new Abstract: Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable com

From Ontology Conformance to Admissible Reconfiguration: A RoSO/SMGI Adequacy Argument for Robotic Service Governance

arXiv:2605.08185v1 Announce Type: cross Abstract: The Robotic Service Ontology (RoSO) gives service robotics a typed semantic vocabulary for services, functions, interactions, and deployment-sensitive

FugSeg: Fast Uncertainty-aware Ground Segmentation for 3D Point Cloud

arXiv:2605.08952v1 Announce Type: new Abstract: In LiDAR-based environment perception systems, ground segmentation is a key preprocessing step supporting various applications such as mapping and navig

Fully First-Order Algorithms for Online Bilevel Optimization

arXiv:2602.11665v2 Announce Type: replace Abstract: In this work, we study nonconvex-strongly convex online bilevel optimization (OBO) using only first-order oracle. Existing OBO algorithms are mainly

Functional Stable Model Semantics and Answer Set Programming Modulo Theories

arXiv:2605.09524v1 Announce Type: new Abstract: Recently there has been an increasing interest in incorporating ``intensional'' functions in answer set programming. Intensional functions are those who

Functional Subspace, where language models can use vector algebra to solve problems

arXiv:2602.01687v2 Announce Type: replace-cross Abstract: Large language models (LLMs) were invented for natural language tasks such as translation, but they have proved that they can perform highly c

Gate-and-Merge: Zero-shot Compositional Personalization of Vision Language Models

arXiv:2605.08702v1 Announce Type: cross Abstract: This paper tackles compositional personalization of vision-language models (VLMs). In this problem, multiple user-defined concepts must be recognized

Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once

arXiv:2605.08424v1 Announce Type: new Abstract: Flow matching has recently emerged as a flexible and efficient framework for generative modelling by learning deterministic transport dynamics between p

Generative Giants, Retrieval Weaklings: Why do Multimodal Large Language Models Fail at Multimodal Retrieval?

arXiv:2512.19115v2 Announce Type: replace Abstract: Despite the remarkable success of multimodal large language models (MLLMs) in generative tasks, we observe that they exhibit a counterintuitive defi

Geometric Flood Depth Estimation: Fusing Transformer-Based Segmentation with Digital Elevation Models

arXiv:2605.08521v1 Announce Type: new Abstract: Post-disaster situational awareness relies heavily on understanding both the extent and the volume of floodwaters. While 2D semantic segmentation provid

Geometry-aware Prototype Learning for Cross-domain Few-shot Medical Image Segmentation

arXiv:2605.10885v1 Announce Type: new Abstract: Cross-domain few-shot medical image segmentation (CD-FSMIS) requires a model to generalise simultaneously to novel anatomical categories and unseen imag

Geometry Guided Self-Consistency for Physical AI

arXiv:2605.08638v1 Announce Type: cross Abstract: State-of-the-art physical AI models generate a chunk of actions per inference through diffusion or flow matching, iteratively refining an initial nois

GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling

arXiv:2510.00883v2 Announce Type: replace-cross Abstract: In this work we introduce GreenLightningAI (GLAI), a new architectural block designed as an alternative to conventional MLPs. The central idea

GLEAM: A Multimodal Imaging Dataset and HAMM for Glaucoma Classification

arXiv:2603.12800v2 Announce Type: replace-cross Abstract: We propose glaucoma lesion evaluation and analysis with multimodal imaging (GLEAM), the first publicly available tri-modal glaucoma dataset co

Graph Computation Meets Circuit Algebra: A Task-Aligned Analysis of Graph Neural Networks for Electronic Design Automation

arXiv:2605.08291v1 Announce Type: cross Abstract: EDA problems are graph-structured, but not all graph-structured problems call for the same GNN computation. We argue that successful GNN-for-EDA metho

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs

arXiv:2605.10762v1 Announce Type: cross Abstract: Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mi

GRIT: Teaching MLLMs to Think with Images

arXiv:2505.15879v2 Announce Type: replace-cross Abstract: Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thou

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

arXiv:2605.10582v1 Announce Type: cross Abstract: This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from t