Running on Zero MCP 4 Laya Multilingual Demo 🌍 4 System 1 decisions in 100+ languages, one forward pass
Running Agents 36 Typed Decision Leaderboard 🎯 36 JEV & open-Jev answer verifiers, one identical test set
Running Featured 241 Jev Decision Index 🔬 241 Benchmarks and news on various repros of TypeSafe's Jev
Running on Zero Agents Featured 212 Laya Demo 🎯 212 Fast System 1 decisions with calibrated probabilities
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published 10 days ago • 133
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 10 days ago • 181
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published 20 days ago • 374
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation Paper • 2609.11115 • Published 17 days ago • 172
Running Featured 86 A Hitchhiker's Guide to the 3D Ecosystem 💡 86 An interactive guide to 3D representations.
Running on CPU Upgrade Featured 146 H3 Acceleration Arena 🥇 146 Blind A/B ranking of MiniMax-H3 acceleration variants
Agentic Visual Generation: From Generative Models to Agentic Control Paper • 2609.06758 • Published 21 days ago • 34
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation Paper • 2609.08084 • Published 19 days ago • 71
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation Paper • 2608.30935 • Published 27 days ago • 32
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering Paper • 2608.28281 • Published 30 days ago • 99
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling Paper • 2608.30821 • Published 27 days ago • 67
Running on CPU Upgrade Agents Featured 122 Rare Disease, Real Kid: MVA Hackathon 2026 🧬 122 Rare disease hackathon 2026