Tagged articles

RL fine‑tuning

3 articles · Page 1 of 1

Jul 8, 2026 · Artificial Intelligence

One Layer Is Enough: Single‑Layer RL Beats Full‑Parameter Training Across Models, Tasks, and Algorithms

A systematic study of reinforcement‑learning post‑training for large language models shows that most RL gains are concentrated in a few middle Transformer layers, and training just one such layer can match or surpass full‑parameter RL across seven models, three RL algorithms, and multiple task domains, leading to simple yet effective training strategies.

Large Language ModelsModel OptimizationRL fine‑tuning

0 likes · 17 min read

One Layer Is Enough: Single‑Layer RL Beats Full‑Parameter Training Across Models, Tasks, and Algorithms

Machine Heart

May 28, 2026 · Artificial Intelligence

How Orbit Enables Single-Node RL Fine-Tuning of Trillion-Parameter Models like DeepSeek‑V4

Orbit’s adapter‑first design freezes a low‑precision base model and updates only a small adapter, allowing trillion‑parameter MoE models such as DeepSeek‑V4 to be RL‑fine‑tuned on a single 8×B200 node while keeping training and rollout precision aligned and memory usage within budget.

DeepSeekMoEOrbit framework

0 likes · 9 min read

How Orbit Enables Single-Node RL Fine-Tuning of Trillion-Parameter Models like DeepSeek‑V4

Machine Learning Algorithms & Natural Language Processing

Feb 20, 2026 · Artificial Intelligence

Do Interleaved Images Really Help Thinking‑with‑Images Models?

An analysis of recent Vision‑Language models shows that removing interleaved images has minimal impact on benchmark performance, suggesting that better priors from RL fine‑tuning and effective context management are the key drivers of success.

Attention RolloutCropping MethodsInterleaved Images

0 likes · 8 min read

Do Interleaved Images Really Help Thinking‑with‑Images Models?