Archive - Friendly Paper Review

September 2026

SteerDuplex: Steerable Duplex Speech Dialogue Models

or, A Small Step Towards JARVIS

Sep 30 • Tim Dingman

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

or, What Ilya Didn’t See

Sep 28 • Tim Dingman

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

or, Some Engineering Ain’t Pretty

Sep 24 • Tim Dingman

π*0.6: a VLA that Learns from Experience

or, RL for Robots

Sep 21 • Tim Dingman

Kimi K3: Open Frontier Intelligence

or, The Open-Weights King (For Now)

Sep 16 • Tim Dingman

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts