Fast Log-Domain Sinkhorn Optimal Transport with Warp-Level GPU Reductions
arXiv:2605.00837v1 Announce Type: new
Abstract: Entropic regularized optimal transport (OT) via the Sinkhorn algorithm has become a fundamental tool in machine learning, yet existing implementations either suffer from numerical instability for small regularization parameters or incur significant ov...
2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing
arXiv:2605.00839v1 Announce Type: new
Abstract: The evolution of artificial intelligence (AI) and machine learning (ML) is reshaping smart manufacturing by providing new capabilities for efficiency, adaptability, and autonomy across industrial value chains. However, the deployment of AI and ML in i...
AI Agents for Sustainable SMEs: A Green ESG Assessment Framework
arXiv:2605.00841v1 Announce Type: new
Abstract: This study presents a novel, AI-driven framework for assessing Environmental, Social, and Governance (ESG) performance in European small and medium-sized enterprises (SMEs). An initial phase established expert-validated ESG baseline scores from a subs...
Understanding Emergent Misalignment via Feature Superposition Geometry
arXiv:2605.00842v1 Announce Type: new
Abstract: Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, its underlying mechanism remains unclear. To uncover the reason behind th...
Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference
arXiv:2605.00005v1 Announce Type: new
Abstract: The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on execution platforms, posing challenges to real-time control deadlines. Traditional ...
What Physics do Data-Driven MoCap-to-Radar Models Learn?
arXiv:2605.00018v1 Announce Type: new
Abstract: Data-driven MoCap-to-radar models generate plausible micro-Doppler spectrograms, but do they actually learn the underlying physics? We introduce a physics-based interpretability framework to answer this question via two proposed complementary metrics:...
AirFM-DDA: Air-Interface Foundation Model in the Delay-Doppler-Angle Domain for AI-Native 6G
arXiv:2605.00020v1 Announce Type: new
Abstract: The success of large foundation models is catalyzing a new paradigm for AI-native 6G network design: wireless foundation models for physical layer design. However, existing models often operate on channel state information (CSI) in the space-time-freq...
TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data
arXiv:2605.00060v1 Announce Type: new
Abstract: We present TADI (Tool-Augmented Drilling Intelligence), an agentic AI system that transforms drilling operational data into evidence-based analytical intelligence. Applied to the Equinor Volve Field dataset, TADI integrates 1,759 daily drilling report...
AgentReputation: A Decentralized Agentic AI Reputation Framework
arXiv:2605.00073v1 Announce Type: new
Abstract: Decentralized, agentic AI marketplaces are rapidly emerging to support software engineering tasks such as debugging, patch generation, and security auditing, often operating without centralized oversight. However, existing reputation mechanisms fail i...
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 are susceptible to jailbreaks, future frontier models operating more autonomously...
Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents
arXiv:2605.00136v1 Announce Type: new
Abstract: Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we demonstrate that this consensus does not always hold: in the presence of semantic distractors, too...
TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
arXiv:2605.00224v1 Announce Type: new
Abstract: Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy Optimization (PPO) or, more simply, via Direct Preference Optimization (DPO). While DPO is stable ...
PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning
Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls to external tools. However, training such agents using outcome-only rewards suffers from credit-assignment ambiguity, obscuring which intermediate steps ...
What's shaping frontier AI in 2026? Find out in London, May 21st
On May 21st, the Innodata GenAI Summit convenes in London for a single day of rigorous, practitioner-led exchange on the challenges defining frontier AI in 2026. Here is what the agenda covers, who is in the room, and why it's a must for AI professionals...
Simple Self-Conditioning Adaptation for Masked Diffusion Models
arXiv:2604.26985v1 Announce Type: new
Abstract: Masked diffusion models (MDMs) generate discrete sequences by iterative denoising under an absorbing masking process. In standard masked diffusion, if a token remains masked after a reverse update, the model discards its clean-state prediction for tha...
arXiv:2604.26991v1 Announce Type: new
Abstract: Recent advances in data-centric medical AI have produced highly accurate diagnostic systems, but the emphasis on data curation and performance metrics has not translated into widespread clinical adoption. We conjecture that this limited uptake stems f...
arXiv:2604.27007v1 Announce Type: new
Abstract: We provide a causal analysis of Binary Spiking Neural Networks (BSNNs) to explain their behavior. We formally define a BSNN and represent its spiking activity as a binary causal model. Thanks to this causal representation, we are able to explain the o...
When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production Systems
arXiv:2604.27082v1 Announce Type: new
Abstract: We present a framework for migrating production Large Language Model (LLM) based systems when the underlying model reaches end-of-life or requires replacement. The key contribution is a Bayesian statistical approach that calibrates automated evaluatio...
End-to-end autonomous scientific discovery on a real optical platform
arXiv:2604.27092v1 Announce Type: new
Abstract: Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods and claims as evidence accumulates. Although large language model (LLM)-based agents are beginning ...
Think it, Run it: Autonomous ML pipeline generation via self-healing multi-agent AI
arXiv:2604.27096v1 Announce Type: new
Abstract: The purpose of our paper is to develop a unified multi-agent architecture that automates end-to-end machine learning (ML) pipeline generation from datasets and natural-language (NL) goals, improving efficiency, robustness and explainability. A five-ag...
Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents
This paper was accepted at the Fifth Workshop on Natural Language Generation, Evaluation, and Metrics at ACL 2026.
Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active e...
Red-teaming a network of agents: Understanding what breaks when AI agents interact at scale
Safe agents don’t guarantee a safe ecosystem of interconnected agents. Microsoft Research examines what breaks when AI agents interact and why network-level risks require new approaches.
The post Red-teaming a network of agents: Understanding what breaks when AI agents interact at scale appeared fir...