Section

Industry

AI applied to specific industries — finance, healthcare, legal, security, and more.

134 stories

Industry
Agentic Retrieval-Augmented Generation for Financial Document Question Answering
arXiv:2605.05409v1 Announce Type: new Abstract: Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence--structured tables, textual narratives, and…
cs.AI updates on arXiv.orgMay 9Score 7.0
May 9
Score 7.0
Industry
Intelligent CCTV for Urban Design: AI-Based Analysis of Soft Infrastructure at Intersections
arXiv:2605.05402v1 Announce Type: new Abstract: Artificial intelligence (AI) and computer vision are transforming transportation data collection. This study introduces an AI-enabled analytics framework leveraging…
cs.AI updates on arXiv.orgMay 9Score 7.0
May 9
Score 7.0
Industry
Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning
arXiv:2605.05217v1 Announce Type: new Abstract: We propose a self-supervised physics-informed neural network (PINN) framework that adaptively balances physics-based and data-driven supervision for scientific machine…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Are Flat Minima an Illusion?
arXiv:2605.05209v1 Announce Type: new Abstract: Neural networks that land in flat regions of the loss landscape tend to generalise better than those in sharp regions. Sharpness-Aware Minimisation exploits this to…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Expert Routing for Communication-Efficient MoE via Finite Expert Banks
arXiv:2605.05278v1 Announce Type: new Abstract: Resource-efficient machine learning increasingly uses sparse Mixture-of-Experts (MoE) architectures, where the gate acts as both a learning component and a routing…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Nationwide EHR-Based Chronic Rhinosinusitis Prediction Using Demographic-Stratified Models
arXiv:2605.05213v1 Announce Type: new Abstract: Chronic rhinosinusitis (CRS) is a common heterogeneous inflammatory disorder that causes substantial morbidity and healthcare costs. CRS is difficult to identify early…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning
arXiv:2605.05226v1 Announce Type: new Abstract: The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees
arXiv:2605.05216v1 Announce Type: new Abstract: Large language models (LLMs) with a large number of parameters achieve strong performance but are often prohibitively expensive to deploy. Recent work explores using teams…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Sparse Prefix Caching for Hybrid and Recurrent LLM Serving
arXiv:2605.05219v1 Announce Type: new Abstract: Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
arXiv:2605.05224v1 Announce Type: new Abstract: The unauthorized use of personal data in model training has emerged as a growing privacy threat. Unlearnable examples (UEs) address this issue by embedding imperceptible…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Horizon-Constrained Rashomon Sets for Chaotic Forecasting
arXiv:2605.05218v1 Announce Type: new Abstract: Predictive multiplicity and chaotic dynamics represent two fundamental challenges in machine learning that have evolved independently despite their conceptual connections.…
cs.LG updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
SLAM: Structural Linguistic Activation Marking for Language Models
arXiv:2605.05443v1 Announce Type: new Abstract: LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for detection with measurable…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models
arXiv:2605.05758v1 Announce Type: new Abstract: Despite the success of large language models (LLMs) on general-purpose tasks, their performance in highly specialized domains such as biomedicine remains unsatisfactory. A…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Evaluation Awareness in Language Models Has Limited Effect on Behaviour
arXiv:2605.05835v1 Announce Type: new Abstract: Large reasoning models (LRMs) sometimes note in their chain of thought (CoT) that they may be under evaluation. Researchers worry that this verbalised evaluation awareness…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
A Few Good Clauses: Comparing LLMs vs Domain-Trained Small Language Models on Structured Contract Extraction
arXiv:2605.05532v1 Announce Type: new Abstract: This paper evaluates whether a domain trained Small Language Model (SLM) can outperform frontier Large Language Models on structured contract extraction at radically lower…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis
arXiv:2605.05485v1 Announce Type: new Abstract: LLMs can solve program synthesis tasks but remain inefficient and unreliable on hard instances requiring large combinatorial search. Given a small set of reasoning traces,…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language Models
arXiv:2605.05626v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at generating contextually appropriate responses but remain poorly calibrated for multi-party conversations, where deciding when to…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
arXiv:2605.05676v1 Announce Type: new Abstract: Recently, the prominent performance of large language models (LLMs) has been largely driven by multi-task instruct-tuning. Unfortunately, this training paradigm suffers…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation
arXiv:2605.05245v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) remains brittle on multi-hop questions in realistic deployment settings, where retrieved evidence may be noisy or redundant and only…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Generating Query-Focused Summarization Datasets from Query-Free Summarization Datasets
arXiv:2605.05392v1 Announce Type: new Abstract: Large-scale datasets are widely used to perform summarization tasks, but they may not include queries alongside documents and summaries. In the search for suitable…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
arXiv:2605.05892v1 Announce Type: new Abstract: Activation steering has emerged as a promising alternative for controlling language-model behavior at inference time by modifying intermediate representations while…
cs.CL updates on arXiv.orgMay 8Score 7.0
May 8
Score 7.0
Industry
ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations
This paper proposes a clinical chatbot that grounds answers in official guidelines using prioritized evidence retrieval and verifiable citations. It is relevant for builders working on high-stakes RAG systems where…
cs.AI updates on arXiv.orgMay 6Score 9.6
May 6
Score 9.6
Industry
Algebraic Semantics of Governed Execution: Monoidal Categories, Effect Algebras, and Coterminous Boundaries
This paper gives a formal algebraic semantics for governed execution, backed by a substantial Rocq mechanization. It is technically rigorous, but the abstraction is far from the day-to-day concerns of most AI builders.
cs.AI updates on arXiv.orgMay 6Score 8.2
May 6
Score 8.2
Industry
Accelerating battery research with an AI interface between FINALES and Kadi4Mat
This paper connects an AI interface to battery experimentation infrastructure to speed up formation-protocol optimization for sodium-ion cells. It is most relevant as an example of closed-loop materials discovery, where…
cs.AI updates on arXiv.orgMay 6Score 8.4
May 6
Score 8.4
Industry
MAEPose: Self-Supervised Spatiotemporal Learning for Human Pose Estimation on mmWave Video
arXiv:2605.00242v1 Announce Type: cross Abstract: Millimetre-wave (mmWave) radar offers a more privacy-preserving alternative to RGB-based human pose estimation. However, existing methods typically rely on pre-extracted…
cs.AI updates on arXiv.orgMay 5
May 5
Safety
Attention Is Where You Attack
arXiv:2605.00236v1 Announce Type: cross Abstract: Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
AIDA-ReID: Adaptive Intermediate Domain Adaptation for Generalizable and Source-Free Person Re-Identification
arXiv:2605.00111v1 Announce Type: cross Abstract: Person re-identification (Re-ID) aims to match images of the same individual across non-overlapping camera views and remains challenging due to domain shifts caused by…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
DeGenTWeb: A First Look at LLM-dominant Websites
arXiv:2605.00087v1 Announce Type: cross Abstract: Many recent news reports have claimed that content generated by large language models (LLMs) is taking over the web. However, these claims are typically not based on a…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Smart Profit-Aware Crop Advisory System: Kisan AI
arXiv:2605.00133v1 Announce Type: cross Abstract: Modern crop advisory systems exhibit a critical limitation termed \textit{economic blindness}. These systems primarily optimize for biological yield, often overlooking…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
CRC-Screen: Certified DNA-Synthesis Hazard Screening Under Taxonomic Shift
arXiv:2605.00074v1 Announce Type: cross Abstract: DNA-synthesis providers screen incoming orders by searching the requested sequence against curated hazard lists. We show that this baseline collapses to a 100%…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications
arXiv:2605.00068v1 Announce Type: cross Abstract: Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively high costs and…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Hyperspherical Forward-Forward with Prototypical Representations
arXiv:2605.00082v1 Announce Type: cross Abstract: The Forward-Forward (FF) algorithm presents a compelling, bio-inspired alternative to backpropagation. However, while efficient in training, it has a computationally…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
The Cookbook: Design Space of LLM-based Social Simulations
arXiv:2605.00197v1 Announce Type: cross Abstract: Studies attempting to simulate human behavior with grow in numbers while LLM-only social networks have started appearing outside of controlled settings. However, the…
cs.AI updates on arXiv.orgMay 5
May 5
Agentic
Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure
arXiv:2605.00055v1 Announce Type: cross Abstract: We report a safety incident in a deployed multi-agent research system in which a primary AI agent installed 107 unauthorized software components, overwrote a system…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning
arXiv:2605.00015v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TSFMs remain lacking…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Smart Ensemble Learning Framework for Predicting Groundwater Heavy Metal Pollution
arXiv:2605.00056v1 Announce Type: cross Abstract: Groundwater in the Densu Basin is increasingly threatened by heavy metal contamination, but conventional methods fail to capture the statistical complexity and spatial…
cs.AI updates on arXiv.orgMay 5
May 5
Agentic
To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
arXiv:2605.00737v1 Announce Type: new Abstract: Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities. However, tool use is not always beneficial; some calls may be redundant or even…
cs.AI updates on arXiv.orgMay 5
May 5
Physical
Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling
arXiv:2605.00412v1 Announce Type: new Abstract: World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However,…
cs.AI updates on arXiv.orgMay 5
May 5
Agentic
AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?
arXiv:2605.00334v1 Announce Type: new Abstract: Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical routing question…
cs.AI updates on arXiv.orgMay 5
May 5
Physical
Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
arXiv:2605.00438v1 Announce Type: new Abstract: Long-horizon robotic manipulation requires plans that are both logically coherent and geometrically grounded. Existing Vision-Language-Action policies usually hide…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
On the Role of Artificial Intelligence in Human-Machine Symbiosis
arXiv:2605.00440v1 Announce Type: new Abstract: The evolution of artificial intelligence (AI) has rendered the boundary between humanity and computational machinery increasingly ambiguous. In the presence of more…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Instance-Aware Parameter Configuration in Bilevel Late Acceptance Hill Climbing for the Electric Capacitated Vehicle Routing Problem
arXiv:2605.00572v1 Announce Type: new Abstract: Algorithm performance in combinatorial optimization is highly sensitive to parameter settings, while a single globally tuned configuration often fails to exploit the…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference
arXiv:2605.00005v1 Announce Type: cross Abstract: The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources
arXiv:2605.00011v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative intelligence across decentralized data source devices in a privacy-preserving way. While substantial research attention has…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Sure About That Line? Approaching Confidence-Based, Real-Time Line Assignment in Reading Gaze Data
arXiv:2605.00033v1 Announce Type: cross Abstract: Remote and webcam-based eye tracking in multi-line reading suffers from various noise factors and layout ambiguity, precisely where real-time reading support needs…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms
arXiv:2605.00043v1 Announce Type: cross Abstract: Big data platforms are widely used in modern enterprises, and an in-production intelligent assistant is increasingly important to help users quickly find actionable…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Position: agentic AI orchestration should be Bayes-consistent
arXiv:2605.00742v1 Announce Type: new Abstract: LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction
arXiv:2605.00059v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) finds extensive application in autonomous drone navigation within complex, high-risk environments. However, its practical deployment…
cs.AI updates on arXiv.orgMay 5
May 5
Industry
Compliance-Aware Agentic Payments on Stablecoin Rails
arXiv:2605.00071v1 Announce Type: cross Abstract: Agentic payment systems extend delegated action to financial transfers, but scaling them on stablecoin rails in regulated settings requires safeguards that remain…
cs.AI updates on arXiv.orgMay 5
May 5
Safety
Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models
arXiv:2605.00123v1 Announce Type: new Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understanding of why LLMs…
cs.AI updates on arXiv.orgMay 5
May 5