Adam Filipek's picture

In a Training Loop 🔄

Adam Filipek PRO

AdamF92

·

https://rxai.dev

AI & ML interests

Research: AGI, Awareness Models, Memory Systems, Transformers, Reactive Neural Networks & Event-driven AI

Recent Activity

updated a dataset about 19 hours ago

ReactiveAI/WildChat-long-SMAT

published a dataset 1 day ago

ReactiveAI/WildChat-long-SMAT

updated a Space 1 day ago

AdamF92/RxQwen-Nano-0.8B-Chat-Demo

View all activity

Organizations

upvoted 4 collections 8 months ago

Reactive Transformer PoC Supervised Models by Reactive AI

Experimental Proof-of-Concept Reactive Transformer models trained on simple synthetic datasets • 5 items • Updated Oct 9, 2025 • 1

Reactive Transformer PoC - RxT-Alpha Supervised Models

Experimental stateful real-time Reactive Transformer (RxT) models after supervised training stages • 5 items • Updated Oct 8, 2025 • 2

Research Papers

26 items • Updated 6 days ago • 1

Paper

6 items • Updated Oct 14, 2025 • 1

upvoted an article 8 months ago

Article

Reactive Transformer (RxT): Fixing the Memory Problem in Conversational AI

AdamF92

•

Oct 8, 2025

• 6

upvoted 3 papers 8 months ago

TensorBLEU: Vectorized GPU-based BLEU Score Implementation for Per-Sentence In-Training Evaluation

Paper • 2510.05485 • Published Oct 7, 2025 • 8

Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models

Paper • 2510.03561 • Published Oct 3, 2025 • 25

Sparse Query Attention (SQA): A Computationally Efficient Attention Mechanism with Query Heads Reduction

Paper • 2510.01817 • Published Oct 2, 2025 • 16

upvoted a collection about 1 year ago

Sparse Query Attention (SQA) Research

Experimental models with Sparse Query Attention layers. Reducing training time/cost by ~3-10% compared to GQA & MQA, with the same level performance • 10 items • Updated Oct 3, 2025 • 1