Update README.md

README.md

@@ -8,7 +8,7 @@ pinned: false
 short_description: Reactive AI - Reactive Neural Networks and Event-Driven AI
 ---
 
-<img src="https://huggingface.co/spaces/ReactiveAI/README/resolve/main/logo-black.png" width="250" />
+<img src="https://huggingface.co/spaces/ReactiveAI/README/resolve/main/logo-black.png" width=300 />
 
 # Reactive AI
 We are working on our own ideas of Reactive Neural Networks (RxNN) and Event-Driven AI, advancing from language models to AGI awareness models.
@@ -27,23 +27,12 @@ have to be stateful and remember the data between the interactions.
 _**Strong Reactive Neural Networks**_ like **Reactor** could emit and listen to its internal events, while the _**Weak Reactive Neural Networks**_ are
 working only on environment events.
 
-## Reactor AGI
-
-<!-- <img src="https://raw.githubusercontent.com/RxAI-dev/RxNN/refs/heads/main/assets/logo/logo_reactor.png" width="350" /> -->
-
-Our primary architecture - **Reactor** - is planned as the first _**awareness AGI model**_, that's modelling awareness as an _Infinite Chain-of-Thoughts_,
-connected to _Short-Term and Long-Term Memory_ (_Attention-based Memory System_) and _Receptors/Effectors_ systems for real-time reactive processing.
-It will be able to constantly and autonomously learn from interactions in _Continouos Live Learning_ process.
-
-> Reactor architecture details and mathematical model were analysed by 30 state-of-the-art LLM/Reasoning models that rated it's potential
-> to reach the AGI as ~4.35/5
-
-## Reactive Language Models (RxLM)
-While the **Reactor** is the main goal, it's extremely hard to achieve, as it's definitely the most advanced neural network ensemble ever.
 
-That's why we designed simplified architectures, for incremental transformation from language/reasoning models to awareness model:
-- **Reactive Transformer** is introducing _Attention-based Memory System_ and adding _Short-Term Memory_ to Transformer language models
-- **Preactor** is adding _Long-Term Memory_ and ability to learn from interactions
+## Stateful Reactive Language Models (RxLM)
+Our **Reactive Transformer** and second, improved generation of RxT, are extending stateless Transformer language models (almost all LLMs), introducing
+_Attention-based Memory System_ (ABMS) with _Short-Term Memory_ (STM) or multi-level _Mixture-of-Memory_ (MoM / with _Long-Term Memory_). It's based on higher-level
+of recurrence and memory - not between tokens like SSMs, Linear Attention (it could be combined with RxLM) or RNNs, but between interactions (query and answer).
+They introduce effective stateful processing with continual learning, infinite memory & context and are natively conversational & agentic
 
 ## RxLM vs LLM advantages
 Processing single interactions in real-time by **Reactive Language Models** leads to **revolutional** improvements in inference speed/cost:
@@ -54,14 +43,9 @@ Processing single interactions in real-time by **Reactive Language Models** lead
 > In example, for a dialog with **DeepSeek R1**, that have overally ~90k tokens, I paid for about 1.5M tokens. With **RxLM** it will cost only that ~90k tokens, so it
 > will be about **15x cheaper**
 
+## Reactor AGI
+Our final goal- **Reactor** - is planned as the first _**awareness AGI model**_, that's modelling consciousness as an _Infinite Chain-of-Thoughts_,
+connected to _Mixture-of-Memory (MoM)_ in _Attention-based Memory System_ and _Receptors/Effectors_ systems for real-time reactive processing.
+It will be able to constantly and autonomously learn from interactions in _Continouos Live Learning_ process.
 
-## RxNN Platform
-
-<img src="https://raw.githubusercontent.com/RxAI-dev/rxlm/refs/heads/main/assets/logo/logo_rxnn_v2.png" width="250" />
-
-
-## Additional Research
-- **Sparse Query Attention (SQA)** - the most cost-effective GQA variant, even 2-3x faster for long sequences!
-- **Flex-SQA** - combination of Flex Attention and (symmetric) Sparse Query Attention, enabling 4-8x longer sliding windows
-- **Flex Memory Attention/Memory Cross-Attention** - connecting spatially sparse attention with memory layers to enable very long single interactions - smaller sliding window for input sequences attends to full memory, or the opposite
-- **Mixture-of-Experts for Grouped Attention** - MoE Router dynamically selects GQA/SQA groups, instead of static selection. Abandoned, because results were worse than for GQA/SQA
+[Visit our website!](https://rxai.dev) \[Work in progress\]