Tag
LISA is a compact, interpretable MEG decoder that retrieves perceived speech from non-invasive brain recordings with 39.75% Top-1 accuracy among 1,005 candidates using ~20x fewer parameters, while revealing cortical sources and speech features.
A tweet highlights that top young talent in SF is shifting from AGI/alignment to brain-computer interfaces, noting Naomi Bashkansky's resignation from OpenAI to join Conduit as a founding researcher working on non-invasive mind-reading models.
NeuroPB is a framework that scales neural decoding by pretraining a motor encoder on large-scale behavioral data (including robotic trajectories) and aligning neural activity to that representation space, improving trajectory decoding and generalization with limited neural data.
BrainBench is a new unified benchmark for evaluating large language models on comprehensive, instruction-conditioned EEG understanding, covering 17 datasets, 172 tasks, and over 4K real-data instances. The paper evaluates 13 LLMs across two execution paradigms, showing that EEG competence varies by model and operationalization.
Naomi Bashkansky announces her resignation from OpenAI to join Conduit as a founding researcher, building thought-to-text models trained on non-invasive neural data, and shares her vision for telepathic AI interaction.
This paper investigates the effects of phonetic versus character targets and selective state-space models (Mamba) for intracortical brain-to-text decoding, finding that a GRU-based recurrent decoder remains the strongest performer on the Brain-to-Text '25 benchmark.
Tweet about neural control technology, referencing IntEngineering.
Neuralink demonstrates its brain-computer interface allowing trial participants to control wheelchairs using only their thoughts, marking a significant milestone in neural prosthesis technology.
Neuralink is exploring how clinical trial participants can control a powered wheelchair using their mind, detailing the process in a thread.
Chinese company BrainCo demonstrates advanced bionic prosthetics with near-real-time response, requiring no surgical implants, and reduces costs by 85% compared to traditional prosthetics.
BrainCo has launched what it claims is the world's first integrated AI platform for brain-to-robot control, enabling direct neural control of robotic systems.
This paper improves the Huth encoding pipeline for fMRI decoding and introduces fMRIFlamingo, a direct fMRI-to-text framework using Llama 3.2, but finds that decoding success is driven by the language prior rather than neural input.
This paper introduces a multi-feature fusion framework for semantic reconstruction from non-invasive brain recordings, combining static lexical (Word2Vec) and dynamic contextual (GPT) representations via cross-attention, achieving state-of-the-art performance in brain-to-text decoding.
Article contrasts Elon Musk's Neuralink with China's BrainCo, which focuses on non-invasive wearable brain-computer interface devices like bionic hands and sleep aids, highlighting the growing BCI industry and U.S.-China tech rivalry.
The paper introduces a graph-regularized deep learning framework for EEG-based emotion recognition that incorporates psychologically-grounded emotion topology into the training objective, achieving up to +5.42% accuracy and 39% reduction in psychologically implausible misclassifications on SEED datasets.
Proposes Stacked LoRA, a framework that decouples subject-invariant and subject-specific knowledge for adapting EEG foundation models to motor imagery decoding, achieving improved accuracy across multiple benchmarks.
Meta发布了Brain2Qwerty v2，一种非侵入式脑机接口，能够实时解码句子，标志着脑机接口走向现实。
Meta open-sourced Brain2Qwerty v2, a non-invasive brain-to-text system using MEG signals and deep learning, achieving up to 78% word accuracy.
A daily AI newsletter covering multiple stories including warnings from central bankers about AI debt bubbles, Chinese developers buying cheap Claude access via gray-market APIs, Sakana's Fugu report, cost comparisons of Chinese vs American AI models, Deepseek's new inference optimization, and Meta's open-source brain-to-text system.
A new non-invasive method translates brain waves into words, offering a communication pathway without the need for surgery.