IEEE

Visual Imagery-Based Brain-Computer Interaction Paradigms and Neural Encoding and Decoding

Abstract: Imagination is a significant mental activity of human beings that can serve as a brain-computer interaction (BCI) paradigm, and visual imagery (VI) has become a relatively new BCI paradigm.
WRAL

Agentic AI Explained: Duke researcher's AI model could accelerate drug development

Inquisite is agentic AI. It doesn't just give you answers, it performs tasks. It can scour research and medical journals faster than a human being, looking for breakthroughs humans can apply.
GitHub

[Feature]: Add speculative decoding with draft model pruning

at the logits processor level, using AllowedTokenIdsLogitsProcessor. This implementation does not prune the draft model itself but allows evaluating acceptance rates under different draft pruning ...
Frontiers

Convolutional neural networks decode finger movements in motor sequence learning from MEG data

1 Institute of Cognitive Neuroscience, National Research University Higher School of Economics, Moscow, Russia 2 Department of Learning, Data Analytics and Technology, Section Cognition, Data and ...
GitHub

[Paper Note] Set Block Decoding is a Language Model Inference Accelerator, Itai Gat+, arXiv'25

Autoregressive next token prediction language models offer powerful capabilities but face significant challenges in practical deployment due to the high computational and memory costs of inference, ...
IEEE

Dual-TSST: A Dual-Branch Temporal-Spectral-Spatial Transformer Model for EEG Decoding

Abstract: The decoding of electroencephalography (EEG) signals allows access to user intentions conveniently, which plays an important role in the fields of human-machine interaction. To effectively ...