Yuandong Tian(@tydsh):🚨A novel way to do RL in LLM post-training! Inspired by our previous path-not-taken work (https://t.co/hKe4qkgiXL), we dig deep into the learning trajectory of RL and find that optimizing singular vectors (i.e., rotation) of weight matrices suffices for good performance in RL. The resulting “isospectral optimization” reaches matched scores with substantially fewer training steps. Great work from @zhu

2026.07.25 05:04

🚨A novel way to do RL in LLM post-training! Inspired by our previous path-not-taken work ( we dig deep into the learning trajectory of RL and find that optimizing singular vectors (i.e., rotation) of weight matrices suffices for good performance in RL. The resulting “isospectral optimization” reaches matched scores with substantially fewer training steps. Great work from @zhu_hanqing666 and the co-authors!

Hanqing Zhu@zhu_hanqing666

2026.07.22 20:02

People keep asking me: what's different about optimization in RL? Seemingly nothing — the pre-training stack just works (Adam, even SGD 👀 @saagnikkk). Bringing some answers from my last work (sorry for the delay — been cooking 🚀). We introduce ISO: Isospectral Optimization: an RLVR-native optimization stack. Built on one simple observation, spectral inheritance: RLVR can reuse the base model's spectrum and acquire new behavior purely through the singular frames. 🧩 Offline: ISO-Merger — consolidates RL experts into one model with no data, no rollouts, no OPD. Checkpoints only. ⚙️ Online: ISO-Optimizer — a drop-in wrapper on AdamW / Muon that matches AdamW's accuracy with ~2.7× fewer steps on Qwen3-8B-Base. 📄 🌐 🧵👇