google's planetary prediction engine automates geospatial modeling
google research introduces an autonomous ai system that builds geospatial prediction models from natural language queries, cutting weeks of manual work to minutes.
researchtag research
summaries filed under research
glucofm: dual-stream model for glucose monitoring
google research introduces glucofm, a self-supervised foundation model that separates slow glucose trends from short-term deviations to improve metabolic predictions.
researchgoogle launches gemini 3.5 transcribe for real-time speech-to-text
google deepmind introduces gemini 3.5 transcribe, a speech-to-text model with smart formatting, custom vocabulary, and low word error rates for developers.
research4-bit model beats its full-precision source after quantization-aware healing
a new healing method lets a compressed, 4-bit model outperform its bfloat16 original on most benchmarks.
machine learninggranite 4.2: how ibm built its reasoning llms
ibm released granite 4.2, a family of dense reasoning llms in 3b, 8b, and 30b sizes, trained from scratch on 15t tokens with a multi-stage rl pipeline.
machine learningkvboost reuses kv cache chunks anywhere in prompts
kvboost cuts llm prefill latency by reusing key-value cache chunks at arbitrary prompt positions, not just shared prefixes.
researchmemory-primed agent spawning for personal ai infrastructure
a system that spawns coding agents with pre-loaded memories from personal databases to avoid empty context windows.
researchspec-driven agentic development reshapes software delivery
a new report formalizes spec-driven agentic development, where machine-readable specs fuel autonomous coding agents across the software lifecycle.
researchdeepmind partners with eve online studio for ai research
google deepmind and fenris creations are collaborating to build ai agents that can learn, remember, and plan in the persistent world of eve online.
researchinherent's faraday agent beats larger models at replicating research
london startup inherent says its small ai agent faraday outperformed anthropic and openai models at reproducing scientific paper findings.
industryBenchmark optimization found in top speech recognition models
New probes show leading ASR models reproduce benchmark transcripts even when audio contradicts them, inflating scores.
machine learningGoogle adds mobility data to language models for better place understanding
Google Research introduces ME-POIs, a framework that blends text and mobility data to improve predictions about places like opening hours and busyness.
researchGoogle's Biomarker Discovery Framework prioritizes wearable sensor candidates
Google Research introduces a multi-agent AI system that structures biomarker discovery from wearable data through iterative hypothesis generation, statistical analysis, and literature-grounded reasoning.
researchModel Cards Fall Short for Open-Weight Model Governance
An analysis of 500 Hugging Face model cards finds current transparency artifacts insufficient for downstream safety governance of open-weight foundation models.
researchGoogle's PhotoScan estimates body composition from smartphone photos
Google Research demonstrates a deep learning method that predicts insulin resistance from smartphone imagery with accuracy close to DXA scans.
researchRubricForge induces reward-free judging rubrics for agent evaluation
RubricForge evolves a human-readable rubric from labeled trajectories to reduce over-crediting in language-model agent evaluation.
researchA Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
A one-year production trace from Chutes reveals how LLM serving workloads evolve, with implications for caching and load-balancing.
researchReasoning Is a Learnable Rule-Based Process
A position paper argues that AI reasoning lacks clear definitions and proposes treating it as a learnable rule-based process with a best-practices checklist.
researchBenchmark Reveals LLMs Fail One in Three Research Integrity Decisions
IntegrityBench evaluates how large language models handle research integrity under pressure, finding significant failure rates and inconsistent behavior across 18 frontier models.
researchOpen models shift toward China, small models, and agents
Hugging Face data from early 2026 shows Chinese labs dominating frontier open models, small models driving downloads, and coding agents becoming a major user base.
machine learning