FirsthandTech
arXiv — cs.AI preprintsInternational16 October 2026

Amplitude-Only FFN Intervention for Tool-Structured LLM Inference: Method, Gated Evaluation Protocol, and Cross-Model Empirical Results

This is an official announcement record

Firsthand records what arXiv — cs.AI preprints announced and links to the original. The wording below is theirs, not ours.

arXiv:2607.11183v4 Announce Type: replace-cross Abstract: We study Amplitude Gating (AG), an inference-time intervention that masks feed-forward network (FFN) activation coordinates while keeping pretrained weights fixed. Six SwiGLU sites separate shared and gate-only inputs, expanded gate/value channels, and the FFN output. Magnitude-ranked entropy masks and a Newton-Schulz windowed ranking variant provide alternative forward paths without retraining. The corrected September collection covers three Qwen checkpoints and eight text/tool endpoints. Under frozen local text scorers, the displayed
— arXiv — cs.AI preprints

More from arXiv — cs.AI preprints

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.