Skip to content

Category

explainable ai

2,123 papers

#explainable ai Open access Oct 2026

Yes, ChatGPT (and other models) need a psychiatrist: parallels between experimental neuropsychiatry and AI alignment science

AI chatbots (such as ChatGPT or Claude) sometimes state false information with confidence, a behavior popularly termed “hallucination.” In their recent perspective, de Boer et al. [1] compared these errors to confabulation in patients with memory disorders, and asked whether ChatGPT needs a psychiatrist. I argue that i...

Karthik V. Sarma · 0 citations
#explainable ai Open access Oct 2026

Can We Teach AI to See the World the Way Animals Do?

Tweet For decades, ecology has been very good at explaining the past. We can look at a collapsed fishery, a vanished pollinator population, or a coral reef bleaching event and piece together, after the fact, what went wrong. What ecology has struggled to do, and what it needs to get better at, is predicting these chang...

Pensoft Editorial Team · 0 citations
#explainable ai Book Oct 2026

AI Technical Challenges and Their Strategic Implications

This chapter establishes that healthcare AI must not be treated as a solved technology. Persistent technical limitations – generalisability gaps, explainability deficits, and actionability limitations – are structural properties of current ML systems with direct strategic and patient safety consequences. The chapter in...

Muthu Ramachandran · 0 citations
#explainable ai Open access Oct 2026

A deep learning-based plant disease classification using image recognition techniques

Abstract Plant diseases significantly threaten global food security, necessitating accurate and automated diagnostic systems. This work presents a modular deep learning framework for systematic benchmarking and comparative analysis of multiple architectures using the PlantVillage dataset. The framework integrates pretr...

B. N. Anoop, K. S. Sujesh, Ramyashree Ramyashree et al. · 0 citations
#explainable ai Open access Oct 2026

ISO 55001 and AI agents: how far can we hand over control?

Artificial intelligence agents are no longer limited to producing analyses or answering questions. In some industrial facilities, they examine alarms, search for the causes of a failure, prepare interventions, create work orders and can even act directly on the process. This development promises faster decisions, bette...

Nizar Younes Mqam · 0 citations
#explainable ai Open access Oct 2026

Scripts for publication "Beyond Bulk Grade: Mineral–Flow Accessibility Controls Pore-Scale Copper Recovery"

Beyond Bulk Grade: Mineral–Flow Accessibility at the Pore Scale This release provides the code, analysis products, and reproducibility materials supporting the manuscript: Chakrawal et al., Beyond Bulk Grade: Mineral–Flow Accessibility Controls Pore-Scale Copper Recovery. Critical-mineral recovery is commonly interpret...

Arjun Chakrawal, Maruti Kumar Mudunuru, Satish Karra · 0 citations
#explainable ai Open access Oct 2026

Data Physics and Anticipatory Entropic Coupling - Part II: From High-Density AI Architectures to Fundamental Theoretical Physics: Axiomatic Foundations and Extended Domain Extrapolations.

Abstract This paper establishes the grand unified framework of Data Physics and the paradigm of Anticipatory Entropic Coupling. Originating from applied thermal engineering in sub-3nm Direct-to-Chip (D2C) liquid-cooled AI clusters, the model resolves systemic thermal runaway by proving that in extreme-density processin...

Rajmund Olszewski · 0 citations
#federated learning Book Oct 2026

Federated Learning for Medical Image Analysis Using Convolutional Neural Networks

Medical image segmentation is an important part of healthcare since it lets doctors clearly see anatomical features and diseased areas for diagnosis, therapy planning, and monitoring. CNN works fine with different types of medical images like MRI, CT and ultrasound for segmentizing it precisely. In this chapter all ava...

Pankaj Prusty, Jhilirani Nayak, Arabinda Sahoo et al. · 0 citations

Artificial intelligence in wastewater treatment: critical review of predictive performance, explainability and deployment readiness

ABSTRACT Artificial intelligence (AI) has been increasingly adopted in wastewater treatment to support soft sensing, effluent prediction, nutrient removal assessment, membrane monitoring, anomaly detection, greenhouse-gas emission modeling, and anaerobic digestion optimization. This critical review synthesizes approxim...

Wael S. Al-Rashed · 0 citations
#generative ai Open access Oct 2026

PREreview of "Memory Control Signals Emerge Before Action in Long Horizon Agents"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23197372. ## Summary This paper asks whether a language model already represents its memory needs — when to compress history, when to recall earlier evidence — in its hidden state b...

Karmendra Pandey · 0 citations
#generative ai Book Oct 2026

Transmedia Storytelling in a Fragmented Age

Narrative gravity is a system-level diagnostic heuristic for explaining why some transmedia storyworlds remain coherent under platform fragmentation while others lose interpretive stability. The problem is not simply how stories circulate or whether a world possesses a stable core. It is what coherence looks like after...

Jean Pierre Magro · 0 citations

From tech blogs

See all →
Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

Microsoft Research Blog Oct 6, 2026

What AI gets wrong and what failure teaches us

Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity.  The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.