Readable implementation of Mamba 3 SSM model

DGX Spark research and tests - containers, benchmarks, and investigation notes for running models on GB10 (SM 12.1)

Deploy Mamba-SSM on NVIDIA Jetson with TensorRT support

End-to-end crypto price direction prediction framework built on the Mamba Selective State Space architecture (Python/PyTorch). Covers the full lifecycle: data preparation, Triple Barrier labeling, training, evaluation & live inference — all from a single config. Linear-time sequence processing as a Transformer alternative.

A production-grade deep learning framework for zero-shot ECG classification that achieves state-of-the-art generalization through morphology-rhythm disentanglement and efficient long-range sequence modeling with Mamba/SSM.

Zero-Shot ECG Generalization using Morphology-Rhythm Disentanglement and Mamba State Space Models. Features a production-ready Clinical Dashboard

MambaQuant - A production-ready stock prediction tool based on Mamba SSM. Features yfinance integration for global markets (US/TW/Crypto), sliding window inference for T+1 prediction, and optimized CUDA pipelines.

A physics-informed Deep Learning framework (Mamba/Swin-UNet) for Sentinel-1 SAR imagery denoising and speckle suppression. Features unsupervised refinement and multi-task learning.

Autonomous AI ecosystem for planetary-scale biodiversity restoration. Agentic swarm intelligence, real-time field robotics, and neurosymbolic governance — built to act, not just predict.

Unified Video Anomaly Detection using SigLIP 2 and Mamba SSM

Listening Between the Lines: An explainable multimodal framework for MCI detection from spontaneous speech. Leverages Selective State Space Models (Mamba) and Gated Fusion to integrate linguistic disfluencies and eGeMAPS biomarkers across multi-corpus benchmarks (Pitt, ADReSS, TAUKADIAL)

Computational phenomenology study of semantic satiation in neural networks. Comparing how GPT-2, BERT, and Mamba handle extreme repetition reveals causal models drift into hallucination while bidirectional models stay stable—suggesting attention directionality preserves semantic identity.

Geometry-first gesture recognition using differential geometry (Ricci curvature, Bézier arcs, joint angles) from hand landmarks. DGN pipeline from the paper "Geometry-First Visual Intelligence".

Comparative analysis of Mamba vs. Transformers trained from scratch. Benchmarking Mamba's linear O(N) scaling and constant-time inference against quadratic attention mechanisms.