srm.git/models/srm/__init__.py, branch main Unnamed repository; edit this file 'description' to name the repository. Add SRM-Joint-AOL v1 model 2026-05-23T09:37:43+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-05-23T09:37:43+00:00 27b69c2b75a251ec39ece318c26ccb1a25d9fd79 Forked from HRM ACT framework. Replaces dual H_level/L_level transformer stacks with a single joint operator T(h, l) that is provably contractive under weighted P-norm with Lip_P(T) ≤ (1-α) + α·κ < 1. Per-step Lyapunov bound: λ_1 ≤ log((1-α) + α·κ). With κ=0.86 → λ_1 ≤ -0.15 ≈ HRM success regime (no CF needed). Components: - AOLLinear: 1-Lipschitz via Prach & Lampert rescaling (float32 normalization) - AOLBlock: stack with ReLU (1-Lipschitz activation) - CayleyOrthogonal: exact orthogonal cross-coupling - BlockGain: softmax row-sum bound under P-norm - AOLTokenMixer: 1-Lipschitz token + channel mixing Smoke test passes: params=939k (hidden=256 test config), forward OK, empirical Lip=0.17 < theoretical bound 0.90. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> 
Forked from HRM ACT framework. Replaces dual H_level/L_level transformer
stacks with a single joint operator T(h, l) that is provably contractive
under weighted P-norm with Lip_P(T) ≤ (1-α) + α·κ < 1.

Per-step Lyapunov bound: λ_1 ≤ log((1-α) + α·κ).
With κ=0.86 → λ_1 ≤ -0.15 ≈ HRM success regime (no CF needed).

Components:
- AOLLinear: 1-Lipschitz via Prach & Lampert rescaling (float32 normalization)
- AOLBlock: stack with ReLU (1-Lipschitz activation)
- CayleyOrthogonal: exact orthogonal cross-coupling
- BlockGain: softmax row-sum bound under P-norm
- AOLTokenMixer: 1-Lipschitz token + channel mixing

Smoke test passes: params=939k (hidden=256 test config),
forward OK, empirical Lip=0.17 < theoretical bound 0.90.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>