Search: “papers”

arXiv:2605.03620v1 Announce Type: cross Abstract: Syndrome-based neural decoding (SBND) has emerged as a promising deep learning approach for soft-decision decoding of high-rate, short-length codes. H

tutorialsarxiv-cs-lg

Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks

DGX agent

arXiv:2605.01293v1 Announce Type: new Abstract: Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing

agentsarxiv-cs-ai

6 May 2026

LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing

arXiv:2605.03328v1 Announce Type: new Abstract: Additive manufacturing (AM) continues to transform modern manufacturing by enabling flexible, on-demand production of complex geometries across diverse

Agents

LLM-Powered AI Agent Systems and Their Applications in Industry

arXiv:2505.16120v2 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered

agentsarxiv-cs-ai

Logic-Constrained Shortest Paths for Flight Planning

arXiv:2412.13235v4 Announce Type: replace Abstract: The logic-constrained shortest path problem (LCSPP) combines a one-to-one shortest path problem with satisfiability constraints imposed on the routi

Applications

Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments

arXiv:2605.03971v1 Announce Type: new Abstract: Large Language Models (LLMs) are prone to factual hallucinations, risking their reliability in real-world applications. Existing hallucination detectors

applicationsarxiv-cs-cl

MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory

arXiv:2605.03228v1 Announce Type: cross Abstract: As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that

safetyarxiv-cs-cl

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach

arXiv:2511.01680v3 Announce Type: replace-cross Abstract: Social scientists are increasingly turning to unstructured datasets to unlock new empirical insights, e.g., estimating descriptive statistics

MedSR-Vision: Deep Learning Framework for Multi-Domain Medical Image Super-Resolution

arXiv:2605.03343v1 Announce Type: new Abstract: Medical image super-resolution (MedSR) is essential for improving diagnostic precision across diverse imaging modalities such as MRI, CT, X-ray, Ultraso

researcharxiv-cs-cv

Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings

arXiv:2605.02908v1 Announce Type: new Abstract: Understanding how textual embeddings contribute to memorization in text-to-image diffusion models is crucial for both interpretability and safety. This

safetyarxiv-cs-cv

Meta-Inverse Physics-Informed Neural Networks for High-Dimensional Ordinary Differential Equations

arXiv:2605.03511v1 Announce Type: new Abstract: Solving inverse problems in dynamical systems governed by high-dimensional coupled ordinary differential equations (ODEs) is a ubiquitous challenge in s

Metadata, Wavelet, and Time Aware Diffusion Models for Satellite Image Super Resolution

arXiv:2506.23566v2 Announce Type: replace Abstract: The acquisition of high-resolution satellite imagery is often constrained by the spatial and temporal limitations of satellite sensors, as well as t

researcharxiv-cs-cv

Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection

arXiv:2605.02918v1 Announce Type: new Abstract: Variational autoencoders are widely used for unsupervised anomaly detection. Model selection however remains an open-question: to remain fully unsupervi

Model Routing as a Trust Problem: Route Receipts for Adaptive AI Systems

arXiv:2605.01710v1 Announce Type: new Abstract: AI products often route requests through version aliases, service tiers, tool choices, regional endpoints, fallback rules, or safety handling before res

Hardware

MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier

arXiv:2603.03756v3 Announce Type: replace-cross Abstract: While large language models (LLMs) show promise in scientific discovery, existing research focuses on inference or feedback-driven training, l

hardwarearxiv-cs-cl

MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs

model-releasesarxiv-cs-ai

arXiv:2505.20740v3 Announce Type: replace Abstract: The rapid advancement of multimodal large language models (MLLMs) offers new opportunities for complex scientific challenges, yet their application

Multilingual Safety Alignment via Self-Distillation

arXiv:2605.02971v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain hig

safetyarxiv-cs-cl

Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration

model-releasesarxiv-cs-cv

arXiv:2605.03820v1 Announce Type: new Abstract: Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy cor

NORA: A Harness-Engineered Autonomous Research Agent for End-to-End Spatial Data Science

arXiv:2605.02092v1 Announce Type: new Abstract: The automation of scientific research workflows has emerged as a transformative frontier in artificial intelligence, yet existing autonomous research ag

Not that Groove: Zero-Shot Symbolic Music Editing

model-releasesarxiv-cs-cl

arXiv:2505.08203v2 Announce Type: replace-cross Abstract: While recent advancements in AI music generation have predominantly focused on direct audio synthesis, these systems suffer from inherent rigi

Local Ai

On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization

arXiv:2511.11362v2 Announce Type: replace-cross Abstract: On-device fine-tuning is a critical capability for edge AI systems, which must support adaptation to different agentic tasks under stringent m

local-aiarxiv-cs-cl

On the Privacy of LLMs: An Ablation Study

arXiv:2605.02255v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While at

Partial Effective Information Decomposition for Synergistic Causality

arXiv:2605.03267v1 Announce Type: cross Abstract: Causality is a central topic in scientific inquiry, yet for complex systems, the identification and analysis of synergistic causation remain a challen

PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination

model-releasesarxiv-cs-cl

arXiv:2605.03571v1 Announce Type: new Abstract: Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising applicati

Pioneering AI-assisted code migration: How Google achieved 6x faster migration from TensorFlow to JAX

model-releasesgoogle-cloud-ai

AI coding agents are rapidly becoming ubiquitous across the software industry, fundamentally changing how developers write, test, and debug daily code. While these tools excel at localized, self-conta

Poly-EPO: Training Exploratory Reasoning Models

arXiv:2604.17654v3 Announce Type: replace Abstract: Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and sca

Position: How can Graphs Help Large Language Models?

arXiv:2605.02452v1 Announce Type: new Abstract: With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding o

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment

arXiv:2605.01147v1 Announce Type: new Abstract: As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety propertie

(POSTER) From Sensors to Insight: Rapid, Edge-to-Core Application Development for Sensor-Driven Applications

arXiv:2605.02844v1 Announce Type: cross Abstract: Scientists increasingly rely on sensor-based data; however transforming raw streams into insights across the edge-to-cloud continuum remains difficult

Predicting missing values: A good idea?

arXiv:2605.03733v1 Announce Type: cross Abstract: Minimizing the Mean Squared Error (MSE) is a key objective in machine learning and is commonly used for imputing missing values. While this approach p

safetyarxiv-cs-lg

Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning

arXiv:2605.02372v1 Announce Type: cross Abstract: The growing development of artificial intelligence based solutions, together with privacy legislation, has driven the rise of the so-called privacy pr

Applications

Re-Key-Free, Risky-Free: Adaptable Model Usage Control

arXiv:2511.18772v2 Announce Type: replace-cross Abstract: Deep neural networks (DNNs) have become valuable intellectual property of model owners, due to the substantial resources required for their de

applicationsarxiv-cs-ai

Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction

model-releasesarxiv-cs-ai

arXiv:2509.12464v2 Announce Type: replace Abstract: Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale.

Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding

arXiv:2605.03514v1 Announce Type: new Abstract: The remarkable success of large language models (LLMs) has motivated researchers to adapt them as universal predictors for various graph tasks. As a wid

RFPrompt: Prompt-Based Expert Adaptation of the Large Wireless Model for Modulation Classification

arXiv:2605.03279v1 Announce Type: new Abstract: Automatic modulation classification (AMC) in real-world deployments demands robustness to distribution shifts arising from hardware impairments, unseen

Robust Language Identification for Romansh Varieties

model-releasesarxiv-cs-cl

arXiv:2603.15969v2 Announce Type: replace Abstract: The Romansh language has several regional varieties, called idioms, which sometimes have limited mutual intelligibility. Despite this linguistic div

Local Ai

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs

arXiv:2605.02946v1 Announce Type: new Abstract: Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly

local-aiarxiv-cs-lg

Local Ai

RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement

arXiv:2605.03626v1 Announce Type: new Abstract: To address module fragmentation, uninterpretable mappings, and deployment constraints in RAW-domain demosaicing, color correction, and detail enhancemen

local-aiarxiv-cs-cv

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

arXiv:2605.02900v1 Announce Type: cross Abstract: Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, saf

safetyarxiv-cs-cv

Agents

Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Drones

arXiv:2605.03788v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time

agentsarxiv-cs-ro

SCGNN: Semantic Consistency enhanced Graph Neural Network Guided by Granular-ball Computing

model-releasesarxiv-cs-ai

arXiv:2605.02617v2 Announce Type: new Abstract: Capturing semantic consistency among nodes is crucial for effective graph representation learning. Existing approaches typically rely on k-nearest neigh

Scoring Edit Impact in Grammatical Error Correction via Embedded Association Graphs

arXiv:2604.06573v2 Announce Type: replace Abstract: A Grammatical Error Correction (GEC) system produces a sequence of edits to correct an erroneous sentence. The quality of these edits is typically e

Should We Still Pretrain Encoders with Masked Language Modeling?

arXiv:2507.00994v4 Announce Type: replace Abstract: Learning high-quality text representations is fundamental to a wide range of NLP tasks. While encoder pretraining has traditionally relied on Masked

SoDa2: Single-Stage Open-Set Domain Adaptation via Decoupled Alignment for Cross-Scene Hyperspectral Image Classification

arXiv:2605.03371v1 Announce Type: new Abstract: Cross-scene hyperspectral image (HSI) classification stands as a fundamental research topic in remote sensing, with extensive applications spanning vari

safetyarxiv-cs-cv

Soft Tournament Equilibrium

arXiv:2604.04328v3 Announce Type: replace-cross Abstract: The evaluation of general-purpose artificial agents, particularly those based on LLMs, presents a significant challenge due to the non-transit

Spatiotemporal Convolutions on EEG signal -- A Representation Learning Perspective on Efficient and Explainable EEG Classification with Convolutional Neural Nets

arXiv:2605.03874v1 Announce Type: new Abstract: Classification of EEG signals using shallow Convolutional Neural Networks (CNNs) is a prevalent and successful approach across a variety of fields. Most

Static Analysis of Recursive SHACL

arXiv:2605.02787v1 Announce Type: cross Abstract: SHACL (Shapes Constraint Language) expresses constraints on RDF data by means of so-called shapes. Its central service is validation: verifying whethe

Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers

arXiv:2605.03780v1 Announce Type: cross Abstract: Transformers are effective at inferring the latent task from context via two inference modes: recognizing a task seen during training, and adapting to