55 papers screened · since 2026-07-08 · updated July 15, 2026
TerraZero uses a configurable C engine and procedural scenario generation to achieve this. One of the past week's strongest signals — worth a skim even if it's adjacent to your stack.
arXiv:2607.13028v1 ↗The novel mechanism is an incentive-compatible auction mechanism for dynamically allocating tasks to expert models and tools. Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.09600v1 ↗The core problem is the lack of control over AI agents' evolution, the novel mechanism is the introduction of the logos pluggable layer for self-evolution and governance, the headline empirical result is the ability to compile heterogene… Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.10878v1 ↗The novel mechanism is the information profile ν(t) that records how much each token reveals about the secret. Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.13003v1 ↗85% accuracy on CIFAR-10 with only 174,000 parameters, this approach enables efficient deep learning models for edge deployment. Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.11826v1 ↗The novel mechanism is MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations. Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.12893v1 ↗Evaluating vision-language models for safety-critical incidents in autonomous driving is challenging, AUTOPILOT-VQA addresses this gap with an incident-centric visual question answering benchmark, the dataset covers diverse safety-releva… Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.08745v1 ↗The novel mechanism is the introduction of the vocabulary gap and the verifier gap, which are addressed through a unified framework of intelligence as cognitive discrepancy reduction. Not a direct fit, but it's a higher-signal entry from the past week in Machine Learning.
arXiv:2607.09560v1 ↗The novel mechanism is a task-specific two-agent architecture utilizing confidence-calibrated answering and domain-specific numeric reasoning. Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.09623v1 ↗The novel mechanism introduced is correctness agreement, a decision-level metric that measures overlap in correct predictions between a base model and its quantized variants. Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.08734v1 ↗The novel mechanism is the introduction of the Complex Social Behavior (CSB) dataset to analyze the progression of scene descriptions. Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.09654v1 ↗The core problem is that current pretraining approaches discard visual cues by converting visually rich sources into plain text, Visual Pretraining is the novel mechanism that directly leverages visual documents without text extraction,… Not a direct fit, but it's a higher-signal entry from the past week in Artificial Intelligence.
arXiv:2607.09657v1 ↗We built Vercel's brief from a public sketch of what they do. Field Watch tunes to your actual roadmap and rivals — daily-fresh, delivered to your whole team.