GRAFT: New Transformer Model Improves Neural Population Activity Modeling and Cross-Day Adaptation
Researchers introduced GRAFT, a Transformer-based model that separates reusable temporal dynamics from a recalibratable neuron interface for neural population activity modeling. The model achieves state-of-the-art performance on the NLB'21 MC Maze benchmark and can efficiently adapt across days by updating only 9.21% of parameters. This advancement addresses a key limitation in brain-computer interfaces where recorded neuron identities and counts change over time.
GRAFT is a new neural population activity model designed to overcome a significant challenge in long-term brain-computer interfaces: the instability of recorded neuron sets across different recording sessions. Traditional models couple their input and output layers to specific recorded neurons, making them difficult to reuse when neuron identities, counts, or response statistics change. GRAFT solves this by separating the model into two components—a reusable temporal dynamics backbone and a recalibratable neuron interface—allowing the same core model to adapt to different neuron configurations. On the standard NLB'21 MC Maze benchmark, GRAFT achieves 0.3866 co-bps as an ensemble, setting a new state-of-the-art result. In cross-day adaptation experiments, the model successfully recalibrates to different dataset scales by updating only 9.21% of its parameters, demonstrating data-efficient transfer learning for neural interfaces.
Limitations & open questions
The study does not discuss potential limitations of the approach, such as performance degradation under extreme changes in neuron counts, computational overhead compared to simpler baselines, or applicability to other neural recording modalities beyond the tested MC Maze dataset.
What different sources said
- arXiv cs.LGCenter
GRAFT: Gain-Recalibrated Adapters for Transformer-Based Neural Population Activity Modeling
Related
Researchers Identify D-Retro-Inverso Peptide Candidates for Treating Cardiac Amyloidosis
Researchers have designed and computationally evaluated four peptide candidates made from D-amino acids that may inhibit the formation of Serum Amyloid A (SAA) fibrils associated with cardiac complications following heart attacks. The study builds on mouse model evidence suggesting SAA aggregates contribute to long-term myocardial infarction complications and may operate similarly in humans. Two candidates, DRI-R5S and DRI-H6A, were identified as particularly promising for potential drug development.
Study Identifies D-Retro-Inverso Peptides as Potential Treatments for Cardiac Amyloidosis
Researchers designed four peptide candidates using D-amino acids to inhibit Serum Amyloid A (SAA) fibril formation, which may contribute to complications following heart attacks. The study, conducted using molecular dynamics simulations in a mouse model, identified two peptides—DRI-R5S and DRI-H6A—as promising drug candidates. This work could lead to new therapeutic approaches for cardiac amyloidosis, a serious post-infarction complication.
Scientists Discover Previously Unknown Branch of Tryptophan Metabolism in Humans
Researchers identified a new enzymatic step in human tryptophan catabolism, showing that the protein ASPDH acts as a 2-aminomuconate reductase to produce a previously unknown amino acid. This discovery fills a gap in the kynurenine pathway, one of the body's major metabolic routes for processing the amino acid tryptophan. The finding expands understanding of human metabolism and may have implications for understanding NAD cofactor production and related metabolic diseases.