Attention ISN'T all you need?! New Qwen3 variant Brumby-14B-Base leverages Power Retention technique

Dissecting Transformers: A CLEAR Perspective towards Green AI

IBM Released new Granite 4.0 Models with a Novel Hybrid Mamba-2/Transformer Architecture: Drastically Reducing Memory Use without Sacrificing Performance

Qwen3 von Grund auf: Ein Leitfaden zum führenden Open‑Source‑LLM

Hybrid Models as First-Class Citizens in vLLM

EchoLSTM: Selbstreflektierende RNNs verbessern Langzeitgedächtnis

The beginning of the end of the transformer era? Neuro-symbolic AI startup AUI announces new funding at $750M valuation