Tag
Opus 5.5 demonstrates the ability to generate videos from a single sentence, consuming over 300 million tokens in hours, and the post envisions future advancements where AI and immersive technologies could render imagination in real time.
This tweet thread claims that Brain-Computer Interface (BCI) technology will cause a 'cambrian explosion' in Human-Computer Interaction (HCI), detailing the development of a wearable BCI and the training of a brain foundation model.
Bio-MF is a one-step generative framework for EEG-to-fNIRS cross-modal generation, enabling low-latency and high-fidelity synthesis for hybrid motor-imagery brain-computer interfaces.
Neuralink's brain-computer interface enables an ALS patient to regain speech by decoding neural signals in real-time, demonstrating a significant breakthrough in communication technology.
The tweet promotes Terry, a Neuralink patient with ALS, urging support for him and a charity walk to defeat ALS.
Neuralink's VOICE trial is enabling individuals with disabilities to regain communication abilities through their brain-computer interface technology.
The paper proposes TriDim, a reusable block for EEG decoding that preserves spatial and temporal structures, achieving state-of-the-art performance across multiple datasets and improving existing models.
The post highlights AI's achievements in medicine, such as enabling paralyzed individuals to speak and walk through brain implants and spinal interfaces.
Neuralink shared a trial clip demonstrating thought-to-speech technology, where the interface interprets 'I-I love you' from neural signals.
This paper challenges the assumption that more components improve performance in P300 brain-computer interface spellers, revealing that components can exhibit anti-synergy and their effectiveness depends on the quality of the underlying EEG pipeline.
This paper introduces Brain2Semantics2Text, a non-invasive speech decoding method that maps MEG responses to semantic embeddings to reconstruct sentence-level text without word-level alignment.
AI visionary Ray Kurzweil is joining Silicon Valley startup Subsense to help develop a brain computer system that uses nanoparticles inhaled through the nose to interact with brain neurons.
The article announces the 2026 PNPL Competition focused on word classification and efficient cross-subject generalization in the LibriBrain100 dataset, advancing non-invasive speech decoding for brain-computer interfaces.
BrainCo's brain-computer interface translates EEG signals into control commands for a humanoid robot, enabling its movement and manipulation capabilities.
Neuralink has advanced from a 2021 macaque Pong demo to a human trial, with paralyzed participant Audrey Crews, who received an implant in July 2025, now drawing and signing her name using thought-controlled cursor movement.
The paper introduces LibriBrain100, a large-scale MEG dataset with over 100 hours of data for neural speech decoding, achieving state-of-the-art performance on word classification benchmarks.
This research uses non-invasive EEG and contrastive learning to decode words during silent reading, showing scalable lexical information recovery that scales with data volume.
This paper presents Brain2Qwerty v2, an AI model that accurately decodes natural sentences from non-invasive magnetoencephalography brain recordings with a 39% word error rate, demonstrating that data scaling can help bridge performance gaps with invasive methods.
This paper proposes SW-ProxyCE, a zero-query adversarial attack framework that transfers from public EEG encoders to private downstream models, demonstrating security risks in EEG foundation models.
Silicon Valley companies are pursuing neurotechnology that can track and potentially manipulate brain activity, raising profound privacy concerns about inner thoughts as the next frontier.