Tag
NeurDuo-EEG is a causal EEG foundation model with channel-resolved persistent state and explicit multi-timescale memory, pre-trained on 3,955 hours of EEG via autoregressive prediction of discrete spectral codes. It achieves top results on four of five benchmarks (including a large seizure-detection AUC-PR jump from 0.285 to 0.471) with a 4.7M-parameter variant supporting efficient streaming inference.
The user tested the Step 5 Preview model and found it performs well on long-sequence tasks in frontend coding, comparing it favorably with models like Fable and GPT5-Sol.
AsySplat proposes an asymmetric architecture that decouples geometry and appearance modeling in 3D Gaussian Splatting, achieving high efficiency for long-sequence scene modeling with nearly 800x speedup over optimization-based methods.
OpenAI introduces the Sparse Transformer, a deep neural network that improves the attention mechanism from O(N²) to O(N√N) complexity, enabling modeling of sequences 30x longer than previously possible across text, images, and audio. The model uses sparse attention patterns and checkpoint-based memory optimization to train networks up to 128 layers deep, achieving state-of-the-art performance across multiple domains.