Planetary prediction engine: Automating global models via Earth AI
Earth AI
Topic - Edition
AI Research
True Positive Weekly #175
The most important artificial intelligence and machine learning news and articles
The Sigmoid Function: From 'e' to Neural Networks
We use the equation all the time. But where did it actually come from? The post The Sigmoid Function: From 'e' to Neural Networks appeared first on Towards Data Science.
I Trained Six Models for Fraud Detection, and the Best One Isn't in Production
What a final-year project taught me about the gap between evaluation metrics and production decisions The post I Trained Six Models for Fraud Detection, and the Best One Isn't in Production appeared first on Towards…
Agentic AI Is Rewriting The Analytics Stack But There's One Skill It Still Can't Touch
As AI handles more of the execution, what work should belong to agents vs humans and why does that distinction matter? The post Agentic AI Is Rewriting The Analytics Stack But There's One Skill It Still Can't Touch…
How to Work with AI Coding Agents
A practical guide to getting better code, not just more code The post How to Work with AI Coding Agents appeared first on Towards Data Science.
Stop Giving Your AI Agent a Search Box and Start Giving It Typed Tools, Hard Bounds, and a Gate It Cannot Talk Past
What happens when you stop feeding a model context and let it go find its own, walking a knowledge graph within strict limits, and what four models and one wrong prediction revealed about whether that is worth doing.…
Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
arXiv:2608.24338v1 Announce Type: new Abstract: Inference-time decoding methods improve LLM reasoning by exploring multiple candidate trajectories, yet treat each trajectory as atomic: either retaining it whole or…
STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning
arXiv:2608.23952v1 Announce Type: cross Abstract: Federated video anomaly detection trains model collaboratively without sharing raw surveillance footage, but limited server-side visibility lets compromised clients to…
Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy
arXiv:2608.24771v1 Announce Type: cross Abstract: Brain stroke, known for its high mortality and incidence rates, poses significant health risks and requires rapid intervention for survival. Early diagnosis and…
Identifying Latent Declarative Representations of Code for Assisting Repository Migration
arXiv:2608.23619v1 Announce Type: cross Abstract: Legacy software repositories embed decades of domain knowledge in undocumented code, making understanding and modernization difficult. We treat a program as the…
ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams
arXiv:2604.15994v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reasoning over simple linear diagrams. However, when faced with complex…
Do Joint Language-Audio Embeddings Encode Perceptual Timbre Semantics?
arXiv:2510.14249v2 Announce Type: replace-cross Abstract: Understanding and modeling the relationship between language and sound are essential for applications such as music information retrieval, text-guided music…
ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models
arXiv:2603.10068v2 Announce Type: replace-cross Abstract: Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to capture how safety…
EMRB: A Multi-Level Benchmark for Evaluating LLM Reasoning over Raw Electromagnetic Signals
arXiv:2608.24086v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as code agents for scientific and engineering analysis, but their ability to analyze raw physical-layer measurements…
Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
arXiv:2507.11482v5 Announce Type: replace Abstract: Artificial learning systems are graduating from passive learners to increasingly autonomous agents, lending pragmatic urgency to the question of what constitutes…
MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation
arXiv:2608.15299v2 Announce Type: replace-cross Abstract: Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of routed experts across all layers, a convention that ignores the…
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
arXiv:2605.10426v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mechanisms still struggle…
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
arXiv:2601.17027v2 Announce Type: replace-cross Abstract: While synthetic data has proven effective for improving scientific reasoning in the text domain, multimodal reasoning remains constrained by the difficulty of…
ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents
arXiv:2608.23635v1 Announce Type: cross Abstract: Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them to invoke external systems and complete tasks beyond text generation.…
Loading more...
792 items available