AI Research

Everything That Happened in AI Today (Tuesday, October 27, 2026)

OpenAI published new results on major math and computer-science problems; security researchers penetrated systems used by Anthropic; SpaceX secured $40 billion in GPU financing.

What Makes AI-Written Stories Feel Off?

And how we can turn that feeling into insights The post What Makes AI-Written Stories Feel Off? appeared first on Towards Data Science.

Opening the Box: Can Machine Learning Resolve Schrödinger’s Cat?

Neural networks won’t settle the measurement problem — but they are quietly changing how we see, predict and protect quantum superpositions. The post Opening the Box: Can Machine Learning Resolve Schrödinger’s Cat?…

My Machine Learning Pipeline Cheated, and Cross-Validation Never Noticed

What an ID column, a date string, and a missing value taught me. The post My Machine Learning Pipeline Cheated, and Cross-Validation Never Noticed appeared first on Towards Data Science.

Claude Code vs. Cursor: What a Field Test Shows That the Feature Comparisons Miss

One benchmark says Claude Code used 33,000 tokens where Cursor used 188,000. Another says the exact reverse. Here is the field test that actually settles it for your team. The post Claude Code vs. Cursor: What a Field…

😺 Claude crossed a paywall on its own

From Bug Hunting to Verification: Anthropic’s Next Software Security Experiment

Anthropic and Theorem used Claude to generate mathematical security proofs across 123 open-source libraries. The research shows how AI could automate verification, although the guarantees depend on specified software…

SkillRep: Characterizing and Understanding the Representation Design Space of Agent Skill Retrieval

arXiv:2610.32336v1 Announce Type: new Abstract: Retrieving the right skill from a large library is essential for LLM agents, yet requests and skills are written for different purposes and in different words. Existing…

Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance

arXiv:2610.31863v1 Announce Type: cross Abstract: If agricultural machinery is to support intelligent, offline assistance, then the system must access technical documentation dynamically. In this paper, the Semantic…

MICE to Meet You: From Re-ranking Only to End-to-End Retrieval

arXiv:2610.31932v1 Announce Type: new Abstract: Late-interaction models offer state-of-the-art efficiency-effectiveness trade-offs for neural retrieval by enabling document representations to be pre-computed and…

A Model-Agnostic Correction Framework for Short-Term Building Load Forecasting

arXiv:2610.31959v1 Announce Type: new Abstract: Short-term building load forecasting remains challenging because load patterns can change rapidly with weather and operating conditions. Data-driven forecasting models may…

UAE GovTrust Scope Filtering Gains and Routing Failures in Bilingual Public Service Retrieval

arXiv:2610.32608v1 Announce Type: new Abstract: Public-service queries can mention several locations while only one controls the requested service. We study this distinction in UAE GovTrust, a controlled English-Arabic…

Hierarchical GTV Estimation: Bridging the Gap between Container-Level Ranking and Item-Level Conversion

arXiv:2610.32420v1 Announce Type: new Abstract: Emerging e-commerce platforms, such as live-streaming and Online-to-Offline (O2O) services, inherently operate under a "Container-based" display paradigm. In this setting,…

PersonalQuery-Benchmark:Evaluating Retrieval Robustness to Personalized User Expression Differences

arXiv:2610.32164v1 Announce Type: new Abstract: Existing personalized information retrieval methods mainly model differences in user needs through user preferences and query intent, while paying little attention to the…

Separating Thinking from Spelling for Efficient Generative Recommendation

arXiv:2610.32980v1 Announce Type: new Abstract: Generative recommenders retrieve items by writing their semantic IDs (SIDs) code by code under trie-constrained beam search, an approach now deployed on large web…

Deep learning enables urban change profiling through alignment of historical maps

arXiv:2602.02154v3 Announce Type: replace-cross Abstract: Prior to modern Earth observation technologies, historical maps provide a unique record of long-term urban transformation and offer a lens on the evolving…

From archive to resource: bringing legacy data back to life at scale with large language models

arXiv:2610.32616v1 Announce Type: new Abstract: Pharmaceutical companies maintain vast archives of legacy preclinical study reports that contain study-context details, such as fasting, anesthesia, and laboratory…

Driving Video Retrieval for Complex Queries with Structured Grounding

arXiv:2606.09109v3 Announce Type: replace-cross Abstract: Video retrieval at scale is central to data curation and safety validation in autonomous driving, where users want to find not only scenes but also dynamic…

Knowledge Distillation across Item and Code Spaces for Parallel Generative Recommendation

arXiv:2610.32943v1 Announce Type: new Abstract: Generative recommendation with semantic IDs represents each item as a sequence of discrete codes derived from its semantic representation and predicts these codes to…

Scaling Graph Query Processing: Focused Exploration on Partitions Using Load Balancing

arXiv:2610.32015v1 Announce Type: cross Abstract: The focus of this paper is on query processing and not search (approximate or exact). The goal is to find all or k answers and the expressiveness of a query (as opposed…