Search: “papers”

Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text

arXiv:2606.27215v1 Announce Type: new Abstract: Deep learning models have achieved impressive performance across various fields but remain vulnerable to adversarial inputs, particularly in NLP, where

26 Jun 2026

Safety

When Agents Meet Electric Bus Fleet Operations: Pricing Behavior, Trade-offs, and Policy Implications in an Aggregator Framework

DGX agent

arXiv:2606.26400v1 Announce Type: new Abstract: Agentic systems are changing how complex operational tasks are coordinated, introducing a new paradigm for connecting heterogeneous data sources and aut

safetyarxiv-cs-ai

26 Jun 2026

When are likely answers right? On Sequence Probability and Correctness in LLMs

arXiv:2606.27359v1 Announce Type: cross Abstract: Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, ei

26 Jun 2026

XMSE-Aware Adaptive Empirical Bayes Estimation

arXiv:2606.26975v1 Announce Type: cross Abstract: Empirical Bayes (EB) estimators can match the first-order asymptotic risk of maximum likelihood (ML) while behaving very differently at second order:

26 Jun 2026

A Bregman Perspective on Classification and Regression Trees

arXiv:2606.13984v2 Announce Type: replace-cross Abstract: Classification and Regression Trees (CART) constitute one of the most influential paradigms in statistical learning. Although a variety of imp

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation

arXiv:2606.25476v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes appl

A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks

arXiv:2606.26059v1 Announce Type: new Abstract: The laser welding full-penetration is of critical importance, as it constitutes one of the fundamental factors in achieving defect-free welded joints. A

Adaptive-Horizon Conflict-Based Search for Closed-Loop Multi-Agent Path Finding

arXiv:2602.12024v3 Announce Type: replace Abstract: Multi-Agent Path Finding (MAPF) is a core coordination problem for large robot fleets in automated warehouses and logistics. Existing approaches are

Adaptive Joint Compression and Synchronisation in Federated Split Learning for IoT Rainfall Prediction

arXiv:2606.25003v1 Announce Type: new Abstract: Federated split learning (FSL) enables collaborative training across bandwidth-constrained IoT devices, but repeated activation and gradient exchange cr

safetyarxiv-cs-lg

Adaptive Oscillatory Inductive Bias for Modeling Sharp Prosodic Dynamics in Diffusion-Based TTS

arXiv:2606.25424v1 Announce Type: cross Abstract: Diffusion-based text-to-speech (TTS) models have achieved significant improvements in speech quality. However, modeling sharp prosodic transitions and

safetyarxiv-cs-cl

Agents

AeroCast: Probabilistic 3D Trajectory Prediction for Non-Cooperative Aerial Obstacles via Transformer-MDN Architecture

arXiv:2606.25122v1 Announce Type: cross Abstract: Autonomous aerial vehicles operating in shared airspace must predict the future positions of non-cooperative obstacles to plan evasive maneuvers befor

agentsarxiv-cs-lg

Agents

AI Coaching for Accelerating Human Skill Development with Reinforcement Learning

arXiv:2606.25337v1 Announce Type: new Abstract: AI copilots can substantially boost human performance through shared control, but excessive assistance can induce over-reliance and skill atrophy. This

agentsarxiv-cs-ro

An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages

arXiv:2604.02596v3 Announce Type: replace Abstract: In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks from a few examples, making it promising for languages underrepr

An Improved Variational Method for Image Denoising

arXiv:2410.02587v2 Announce Type: replace Abstract: The total variation (TV) method is an image denoising technique that aims to reduce noise by minimizing the total variation of the image, which meas

Applications

Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints

arXiv:2603.11606v2 Announce Type: replace Abstract: Building high-fidelity digital twins of articulated objects from visual data remains a central challenge. Existing approaches depend on multi-view c

applicationsarxiv-cs-cv

ARTOO-DARTU: Studying AR-HRC With AR Obstruction Mitigation During a Warehouse Task

arXiv:2606.25202v1 Announce Type: cross Abstract: Human-robot collaboration (HRC) often requires robot intentions and internal states to be conveyed to users for task efficiency and safety. Recently,

Attractive and Repulsive Pattern Control in Sequence Generation

arXiv:2606.24911v1 Announce Type: cross Abstract: Variable-order Markov models preserve local symbolic syntax by adapting context length, but long continuations can enter recurring high-order 'tunnels

researcharxiv-cs-ai

BitNet Text Embeddings

arXiv:2606.25674v1 Announce Type: new Abstract: LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone

Causality-Based Parametric Control Barrier Function for Safe Multi-Vehicle Interaction

arXiv:2606.25134v1 Announce Type: new Abstract: Safe control has been widely studied in various safety-critical applications, for instance, autonomous driving. In order to ensure the autonomous vehicl

CKM-Driven Communication-Aware UAV Intelligent Trajectory Optimization for Urban Inspection

arXiv:2606.24979v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) are increasingly employed in urban inspection tasks, where reliable communication is critical but challenging due to the

CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks

arXiv:2604.03314v2 Announce Type: replace-cross Abstract: Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures compos

Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks

arXiv:2606.25858v1 Announce Type: cross Abstract: Federated learning is vulnerable to backdoor attacks in which malicious clients inject poisoned updates while preserving benign-task performance. In t

Tutorials

Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning

arXiv:2606.25357v1 Announce Type: new Abstract: State abstraction plays a key role in scaling reinforcement learning to complex but structured systems. In studying such systems, a wide range of behavi

tutorialsarxiv-cs-lg

Constituency Structure over Eojeol in Korean Treebanks

arXiv:2512.22487v2 Announce Type: replace Abstract: The design of Korean constituency treebanks raises a central representational question concerning the choice of terminal units. Although Korean word

safetyarxiv-cs-cl

Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints

arXiv:2606.25605v1 Announce Type: new Abstract: Tool Calling and Structured Output are two core capabilities of modern Agent systems, yet their interaction under joint deployment conditions remains in

CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations

arXiv:2606.25403v1 Announce Type: cross Abstract: Accent conversion and controllability remain fundamental challenges in cross-lingual text-to-speech (TTS), particularly for low-resource and phonetica

researcharxiv-cs-ai

Data-Driven Evolution of Library and Information Science Research Methods (1990-2022): A Perspective Based on Fine-grained Method Entities

arXiv:2606.25320v1 Announce Type: cross Abstract: Since the 1990s, advancements in big data and information technology have increasingly driven data-centric research in the field of Library and Inform

Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning

model-releasesarxiv-cs-lg

arXiv:2510.04773v2 Announce Type: replace Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiv

Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation

arXiv:2606.25782v1 Announce Type: new Abstract: With the widespread adoption of large language models (LLMs) in chatbots and everyday applications, companies increasingly need guardrails that are effe

Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect

arXiv:2606.26003v1 Announce Type: new Abstract: Automatic speech and language technologies are still heavily biased toward high-resource languages, limiting their applicability to dialectal and low-re

Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models

model-releasesarxiv-cs-cv

arXiv:2606.25324v1 Announce Type: new Abstract: The computational complexity of Transformers scales quadratically with the number of tokens, which significantly constrains the efficiency of vision mod

Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns

arXiv:2606.25010v1 Announce Type: cross Abstract: Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabil

End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users

arXiv:2606.24910v1 Announce Type: cross Abstract: Voice control offers an intuitive alternative to manual drone piloting, yet most existing systems rely on rigid command vocabularies that fail to hand

researcharxiv-cs-ai

Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval

arXiv:2512.00804v3 Announce Type: replace-cross Abstract: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. The

Local Ai

Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface

arXiv:2606.25941v1 Announce Type: cross Abstract: Increasing demand for precise and reliable control in complex scenarios has led to the development of increasingly sophisticated controllers, includin

local-aiarxiv-cs-ai

Extreme Meta-Classification for Large-Scale Zero-Shot Retrieval

arXiv:2606.25237v1 Announce Type: cross Abstract: We develop accurate and efficient solutions for large-scale retrieval tasks where novel (zero-shot) items can arrive continuously at a rapid pace. Con

Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation

arXiv:2606.24902v1 Announce Type: cross Abstract: The 'First Proof' benchmark [1] posed ten research-level mathematics questions to the strongest publicly available LLMs and found them consistently wr

FAR-LIO: Enabling High-Speed Autonomy through Fast, Accurate, and Robust LiDAR-Inertial Odometry

model-releasesarxiv-cs-ro

arXiv:2606.26010v1 Announce Type: new Abstract: Robust and accurate odometry estimation is essential in modern robotics. In environments characterized by highly dynamic motion and sensor noise, odomet

Local Ai

FedReLa: Imbalanced Federated Learning via Re-Labeling

arXiv:2606.26037v1 Announce Type: cross Abstract: Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation. The global class imbalance and cro

local-aiarxiv-cs-cv

ForceBand: Learning Forceful Manipulation with sEMG

arXiv:2606.26093v1 Announce Type: new Abstract: Human demonstrations are a scalable data source for learning robot manipulation policies. However, common sources of human demonstration data, such as m

Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential

arXiv:2502.18959v4 Announce Type: replace Abstract: The architecture of a neural network and the choice of its activation function are both fundamental to its performance. Equally important is ensurin

safetyarxiv-cs-lg

From Rubble Simulation to Active Magnetic Mapping: Quantum Sensing for Disaster Response

arXiv:2606.25957v1 Announce Type: new Abstract: Locating survivors of building collapses within the first 72 hours is a critical challenge in disaster response, and existing sensing modalities provide

researcharxiv-cs-ro

Gastroendoscopy View Synthesis: A New Real Dataset and Evaluation

arXiv:2606.25427v1 Announce Type: new Abstract: Novel view synthesis (NVS) is an active research topic in computer vision, owing to the success of neural radiance field (NeRF) and 3D Gaussian splattin

Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning

arXiv:2606.25347v1 Announce Type: cross Abstract: Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space. While maintaining class-conditio

safetyarxiv-cs-cv

GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization

arXiv:2505.13731v4 Announce Type: replace Abstract: Worldwide image geolocalization-the task of predicting GPS coordinates from images taken anywhere on Earth-poses a fundamental challenge due to the

GUI agent: Guided Exploration of User-Sensitive Screens

arXiv:2606.25705v1 Announce Type: new Abstract: LLM agents are increasingly being used to automate tasks for users within an open GUI environment. They inevitably encounter screens containing user-sen

safetyarxiv-cs-ai

HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment

model-releasesarxiv-cs-cv

arXiv:2606.25491v1 Announce Type: new Abstract: Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate r

Applications

HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors

arXiv:2606.25300v1 Announce Type: new Abstract: Existing 3D vehicle generation methods often suffer from low geometric fidelity and blurry textures, hindering their downstream applications. While rece

applicationsarxiv-cs-cv