Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection
Modern video transformers typically ignore principles from primate vision and are rarely evaluated against neural data, limiting their biological interpretability. We introduce a sparse winner-takes-all token selection module that replaces dense self-attention to improve efficiency and approximate competitive routing observed in biological visual circuits. We further propose a neuro-inspired split-and-fuse video transformer which uses two complementary pathways: a high-resolution, low-frame-rate
Record details
Published: 20 July 2026
Source: arXiv cs.LG
Category: Research
Topics: Safety & alignment · Biotech
Retrieved: 21 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
arXiv red teaming query · 20 July 2026
SoK: Adversarial Robustness of the Variational Quantum Eigensolver via Red-Teaming
arXiv red teaming query · 21 July 2026
Harmonizing AI Safety Thresholds
arXiv · 17 July 2026
Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants
arXiv cs.CY · 16 July 2026
OMNIS: a spatially informed multi-omics deep-learning framework for tumor recurrence prediction and primary–metastatic tumor differentiation title page
Frontiers in Artificial Intelligence · 15 July 2026
From Cellular Responses to Pharmacological Domains: Multimodal Zero-Shot Drug Representation Learning
arXiv · 28 July 2026
How to cite this record
ethics.ai (20 July 2026), “Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection,” evidence record 12267, https://ethics.ai/record/12267 (originally published by arXiv cs.LG).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.