Archive - Friendly Paper Review

Reinforcement Learning via Self-Distillation

or, The Student Becomes the Master

16 hrs ago • Tim Dingman

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

or, Learning to Learn From Experience

Jul 22 • Tim Dingman

RLAnything + OpenClaw-RL

Originally presented as a live talk on March 25, 2026

Jul 20 • Tim Dingman

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

or, Diffusion in Production

Jul 17 • Tim Dingman

mHC vs Attention Residuals

Originally presented as a live talk on April 1, 2026

Jul 13 • Tim Dingman

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

or, The Year of CUA

Jul 8 • Tim Dingman

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

or, Necessity Is the Mother of Invention

Jul 6 • Tim Dingman

Qwen-AgentWorld: Language World Models for General Agents

or, A Mirror for Agents

Jul 1 • Tim Dingman

June 2026

ZAYA1-8B Technical Report

or, Swapping Space for Time

Jun 29 • Tim Dingman

Agents’ Last Exam

or, Benchmarks Are Hard

Jun 24 • Tim Dingman

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Jun 22 • Tim Dingman

Nemotron 3 Ultra

or, The American Open-Weights King

Jun 18 • 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