Search: “papers”

CuraLight: Debate-Guided Data Curation for LLM-Centered Traffic Signal Control

arXiv:2604.05663v2 Announce Type: replace Abstract: Traffic signal control (TSC) is a core component of intelligent transportation systems (ITS), aiming to reduce congestion, emissions, and travel tim

CUTEv2: Unified and Configurable Matrix Extension for Diverse CPU Architectures with Minimal Design Overhead

DGX agent

arXiv:2604.11615v1 Announce Type: cross Abstract: Matrix extensions have emerged as an essential feature in modern CPUs to address the surging demands of AI workloads. However, existing designs often

researcharxiv-cs-ai

14 Apr 2026

DarwinNet: An Evolutionary Network Architecture for Agent-Driven Protocol Synthesis

arXiv:2604.01236v2 Announce Type: replace-cross Abstract: Traditional network architectures suffer from severe protocol ossification and structural fragility due to their reliance on static, human-def

Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labeling

arXiv:2604.11007v1 Announce Type: new Abstract: Semantic segmentation of 3D point cloud scenes is a crucial task for various applications. In real-world scenarios, training segmentation models often f

Decomposing and Reducing Hidden Measurement Error in LLM Evaluation Pipelines

model-releasesarxiv-cs-cl

arXiv:2604.11581v1 Announce Type: new Abstract: LLM evaluations drive which models get deployed, which safety standards get adopted, and which research conclusions get published. Yet these scores carr

Hardware

Deep Optimizer States: Towards Scalable Training of Transformer Models Using Interleaved Offloading

arXiv:2410.21316v2 Announce Type: replace-cross Abstract: Transformers and large language models~(LLMs) have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of pa

hardwarearxiv-cs-ai

DeepFleet: Multi-Agent Foundation Models for Mobile Robots

arXiv:2508.08574v3 Announce Type: replace Abstract: We introduce DeepFleet, a suite of foundation models designed to support coordination and planning for large-scale mobile robot fleets. These models

safetyarxiv-cs-ro

Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition

arXiv:2604.10715v1 Announce Type: new Abstract: Adversarial examples present significant challenges to the security of Deep Neural Network (DNN) applications. Specifically, there are patch-based and t

local-aiarxiv-cs-cv

Detecting Corporate AI-Washing via Cross-Modal Semantic Inconsistency Learning

arXiv:2604.09644v1 Announce Type: cross Abstract: Corporate AI-washing-the strategic misrepresentation of AI capabilities via exaggerated or fabricated cross-channel disclosures-has emerged as a syste

Diffusion Reinforcement Learning Based Online 3D Bin Packing Spatial Strategy Optimization

arXiv:2604.10953v1 Announce Type: new Abstract: The online 3D bin packing problem is important in logistics, warehousing and intelligent manufacturing, with solutions shifting to deep reinforcement le

applicationsarxiv-cs-ro

DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment

arXiv:2510.24574v2 Announce Type: replace-cross Abstract: Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The

Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models

model-releasesarxiv-cs-cl

arXiv:2601.03926v2 Announce Type: replace Abstract: The deployment of Large Vision-Language Models (LVLMs) for real-world document question answering is often constrained by dynamic, user-defined poli

DocRevive: A Unified Pipeline for Document Text Restoration

arXiv:2604.10077v1 Announce Type: new Abstract: In Document Understanding, the challenge of reconstructing damaged, occluded, or incomplete text remains a critical yet unexplored problem. Subsequent d

DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping

arXiv:2604.03402v2 Announce Type: replace-cross Abstract: Smartphone cameras have gained immense popularity with the adoption of high-resolution and high-dynamic range imaging. As a result, high-perfo

safetyarxiv-cs-cv

Dual-Branch Remote Sensing Infrared Image Super-Resolution

arXiv:2604.10112v1 Announce Type: new Abstract: Remote sensing infrared image super-resolution aims to recover sharper thermal observations from low-resolution inputs while preserving target contours,

local-aiarxiv-cs-cv

Dynamic Adaptive Attention and Supervised Contrastive Learning: A Novel Hybrid Framework for Text Sentiment Classification

arXiv:2604.10459v1 Announce Type: new Abstract: The exponential growth of user-generated movie reviews on digital platforms has made accurate text sentiment classification a cornerstone task in natura

researcharxiv-cs-cl

Dynamic Forecasting and Temporal Feature Evolution of Stock Repurchases in Listed Companies Using Attention-Based Deep Temporal Networks

arXiv:2604.09650v1 Announce Type: cross Abstract: Accurately predicting stock repurchases is crucial for quantitative investment and risk management, yet traditional static models fail to capture the

applicationsarxiv-cs-ai

DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells

arXiv:2604.10661v1 Announce Type: cross Abstract: Mobile apps have become essential of our daily lives, making code quality a critical concern for developers. Behavioural code smells are characteristi

researcharxiv-cs-ai

Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts

arXiv:2604.10200v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric eva

Efficient Training for Cross-lingual Speech Language Models

arXiv:2604.11096v1 Announce Type: cross Abstract: Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emergin

Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction

arXiv:2604.11098v1 Announce Type: new Abstract: Large-scale three-dimensional (3D) scene reconstruction in low-altitude intelligent networks (LAIN) demands highly efficient wireless image transmission

applicationsarxiv-cs-cv

Energy-Efficient Federated Edge Learning For Small-Scale Datasets in Large IoT Networks

arXiv:2604.10662v1 Announce Type: new Abstract: Large-scale Internet of Things (IoT) networks enable intelligent services such as smart cities and autonomous driving, but often face resource constrain

agentsarxiv-cs-lg

Tutorials

Engineering Resource-constrained Software Systems with DNN Components: a Concept-based Pruning Approach

arXiv:2604.09988v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are widely used by engineers to solve difficult problems that require predictive modeling from data. However, these models

tutorialsarxiv-cs-lg

Enhancing Cross-Problem Vehicle Routing via Federated Learning

arXiv:2604.10652v1 Announce Type: new Abstract: Vehicle routing problems (VRPs) constitute a core optimization challenge in modern logistics and supply chain management. The recent neural combinatoria

local-aiarxiv-cs-ai

Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training

arXiv:2604.11248v1 Announce Type: cross Abstract: The generation of sustained, open-ended complexity from local interactions remains a fundamental challenge in artificial life. Differentiable multi-ag

ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation

arXiv:2502.18026v3 Announce Type: replace-cross Abstract: Retrieving targeted pathways in biological knowledge bases, particularly when incorporating wet-lab experimental data, remains a challenging t

researcharxiv-cs-ai

Explainable Human Activity Recognition: A Unified Review of Concepts and Mechanisms

arXiv:2604.09799v1 Announce Type: cross Abstract: Human activity recognition (HAR) has become a key component of intelligent systems for healthcare monitoring, assistive living, smart environments, an

applicationsarxiv-cs-ai

Exploring Cross-Modal Flows for Few-Shot Learning

arXiv:2510.14543v4 Announce Type: replace Abstract: Aligning features from different modalities, is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language m

Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs

arXiv:2602.01064v2 Announce Type: replace Abstract: Knowledge distillation has emerged as a pivotal technique for transferring knowledge from stronger large language models (LLMs) to smaller, more eff

researcharxiv-cs-cl

Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards

arXiv:2604.09868v1 Announce Type: cross Abstract: Industrial standards and normative documents exhibit intricate hierarchical structures, domain-specific lexicons, and extensive cross-referential depe

applicationsarxiv-cs-ai

Exploring the impact of fairness-aware criteria in AutoML

arXiv:2604.10224v1 Announce Type: cross Abstract: Machine Learning (ML) systems are increasingly used to support decision-making processes that affect individuals. However, these systems often rely on

ExpressMM: Expressive Mobile Manipulation Behaviors in Human-Robot Interactions

arXiv:2604.05320v2 Announce Type: replace Abstract: Mobile manipulators are increasingly deployed in human-centered environments to perform tasks. While completing such tasks, they should also be able

safetyarxiv-cs-ro

F2F-AP: Flow-to-Future Asynchronous Policy for Real-time Dynamic Manipulation

arXiv:2604.02408v2 Announce Type: replace Abstract: Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness

safetyarxiv-cs-ro

Factorizing formal contexts from closures of necessity operators

arXiv:2604.09582v1 Announce Type: new Abstract: Factorizing datasets is an interesting process in a multitude of approaches, but many times it is not possible or efficient the computation of a factori

researcharxiv-cs-ai

Fairness is Not Flat: Geometric Phase Transitions Against Shortcut Learning

arXiv:2604.11704v1 Announce Type: cross Abstract: Deep Neural Networks are highly susceptible to shortcut learning, frequently memorizing low-dimensional spurious correlations instead of underlying ca

FastSHADE: Fast Self-augmented Hierarchical Asymmetric Denoising for Efficient inference on mobile devices

arXiv:2604.10275v1 Announce Type: new Abstract: Real-time image denoising is essential for modern mobile photography but remains challenging due to the strict latency and power constraints of edge dev

FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning

arXiv:2604.10499v1 Announce Type: cross Abstract: Federated learning has become a popular paradigm for privacy protection and edge-based machine learning. However, defending against differential attac

applicationsarxiv-cs-lg

FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher

arXiv:2408.07587v4 Announce Type: replace Abstract: Federated Learning (FL) enables the collaborative training of machine learning models without requiring centralized collection of user data. To comp

local-aiarxiv-cs-lg

FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views

arXiv:2604.09862v1 Announce Type: new Abstract: Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches

researcharxiv-cs-cv

FGML-DG: Feynman-Inspired Cognitive Science Paradigm for Cross-Domain Medical Image Segmentation

arXiv:2604.10524v1 Announce Type: new Abstract: In medical image segmentation across multiple modalities (e.g., MRI, CT, etc.) and heterogeneous data sources (e.g., different hospitals and devices), D

safetyarxiv-cs-cv

FlexMS is a flexible framework for benchmarking deep learning-based mass spectrum prediction tools in metabolomics

arXiv:2602.22822v2 Announce Type: replace Abstract: The identification and property prediction of chemical molecules is of central importance in the advancement of drug discovery and material science,

FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning

arXiv:2604.11556v1 Announce Type: cross Abstract: LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to st

FM-SIREN & FM-FINER: Implicit Neural Representation Using Nyquist-based Orthogonality

arXiv:2509.23438v3 Announce Type: replace Abstract: Existing periodic activation-based implicit neural representation (INR) networks, such as SIREN and FINER, suffer from hidden feature redundancy, wh

researcharxiv-cs-cv

Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection

arXiv:2511.15083v2 Announce Type: replace Abstract: Time-series anomaly detection plays a critical role in numerous real-world applications, including industrial monitoring and fault diagnosis. Recent

applicationsarxiv-cs-lg

From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution

arXiv:2604.11378v1 Announce Type: new Abstract: The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by readi

From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning

arXiv:2604.11137v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable reasoning.

From Theory to Protocol: Executable Frameworks for Creative Emergence and Strategic Foresight

arXiv:2604.09597v1 Announce Type: cross Abstract: Creativity and strategic foresight have been extensively studied through descriptive theories -- Koestler's bisociation (1964), de Bono's lateral thin

From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience

arXiv:2604.11041v1 Announce Type: new Abstract: Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) plan