4arXiv cs.CL (Computation and Language)·
RABBiT: Foundation model for zero-shot and few-shot prediction of speech-elicited fMRI brain responses
Researchers introduce RABBiT, a compact audio-to-fMRI encoder foundation model designed to predict brain responses to natural speech with zero or few participant-specific data. Evaluated on 324 participants across multiple unseen fMRI datasets, RABBiT outperforms the current state-of-the-art fMRI foundation model and group-average baselines in auditory and language-selective brain regions. With only 10 minutes of participant data, parameter-efficient fine-tuning further improves performance substantially over per-participant linear models. Key innovations include learned region-specific attention and a decomposition of brain responses into shared and subject-specific components.
Related guides (1)
Related events (8)
Meta Introduces TRIBE v2: Predictive Foundation Model for Human Brain Activity
Meta AI has released TRIBE v2, a foundation model that predicts high-resolution fMRI brain activity in response to visual, auditory, and language stimuli. Trained on data from over 700 healthy volunteers, it achieves a 70x resolution increase over comparable models and supports zero-shot generalization to new subjects, languages, and tasks. The release includes model weights, codebase, a research paper, and an interactive demo under a CC BY-NC license. Meta positions the work as a bridge between neuroscience and AI development, enabling hypothesis testing without requiring human subjects in every experiment.
RAT: Reference-Augmented Training improves deepfake audio detection without reference at inference
Researchers introduce Reference-Augmented Training (RAT), a training strategy for automatic speaker verification (ASV) anti-spoofing that conditions a model on speaker-reference recordings during training but discovers the model learns to ignore the reference at inference. Counterintuitively, this training regime induces invariances that improve deepfake detection even when the reference is replaced with a zero vector at test time. RAT achieves state-of-the-art 2.57% EER and 0.074 minDCF on the ASVspoof 5 benchmark with a single detector, outperforming large ensemble systems.
Probing bioacoustic embeddings for speech-like acoustic features reveals no-free-lunch pattern
A new arXiv preprint investigates which acoustic features are encoded in pretrained bioacoustic audio embeddings using 88 eGeMAPS speech features across six taxonomic groups. Linear and nonlinear regression probes reveal that no single model captures the full acoustic feature space, with loudness best recovered (R²=0.76) and fundamental frequency hardest (R²=0.33). A concatenated embedding approach achieves highest overall performance, suggesting complementary coverage across models. The work provides data-driven model selection guidance for bioacoustics tasks involving rare species or low-resource domains.
BrainJanus: Unified autoregressive model for brain encoding/decoding across vision and language
BrainJanus is a unified model that integrates brain neural activity, vision, and language within a single autoregressive framework using next-token prediction. The system introduces a Unified Brain Tokenizer to quantize neural dynamics into discrete tokens aligned with visual and linguistic representations in a shared embedding space. It supports any-to-any generation including image-to-brain, text-to-brain, brain-to-image, and brain-to-text tasks, with reported zero-shot generalization and interpretable biological topography. The work positions itself as a general-purpose brain modeling paradigm at the intersection of neuroscience and multimodal AI.
Foundation Model for Wearable Health Data Pretrained on 1 Trillion Minutes from 5 Million Participants
Researchers propose a large-scale foundation model for wearable health data, pretrained on over one trillion minutes of unlabeled sensor signals from five million participants. The model demonstrates systematic performance improvements across 35 health prediction tasks spanning cardiovascular, metabolic, sleep, and mental health domains, with joint scaling of model capacity and data volume. A 'classroom' of LLM agents autonomously searches downstream predictive head configurations, and the resulting embeddings are integrated into a Personal Health Agent validated by 1,860 clinician ratings. The work establishes label-efficient few-shot learning and generative capabilities for daily health metric estimation.
TxFM: Masked Autoencoding Foundation Model for RNA-seq Gene Expression Representation
The paper introduces TxFM, a self-supervised masked autoencoder model for transcriptomic (RNA-seq) data representation learning, trained on a curated 1.4M-sample corpus called DiverseRNA-1.4M. TxFM outperforms existing transcriptomic foundation models trained on datasets over 100x larger, addressing the known problem of deep models underperforming linear baselines on gene expression data. The work provides ablation studies identifying critical architecture choices and argues that careful data curation combined with inductive self-supervised learning is sufficient for strong transfer performance in transcriptomics.
Meta releases Brain2Qwerty v2: non-invasive brain-to-text decoding at 61% word accuracy
Meta AI released Brain2Qwerty v2, an end-to-end deep learning pipeline that decodes text from non-invasive magnetoencephalography (MEG) brain recordings in real time, achieving 61% word accuracy — up from 8% for prior non-invasive methods and approaching surgical-implant performance. The system was trained on ~22,000 sentences from nine participants and uses fine-tuned large language models on neural data to bridge noisy brain signals and coherent language. Meta is releasing full training code for both v1 and v2, and partner institution BCBL is releasing the v1 dataset. The work is part of Meta's broader Digital Brain Project and open neuroscience initiative.
Evaluating Audio Reasoning with Big Bench Audio
Hugging Face introduces Big Bench Audio, a new benchmark designed to evaluate audio reasoning capabilities in AI models. The benchmark appears to extend the Big Bench evaluation framework into the audio domain, targeting multimodal models that process and reason over audio inputs. This release addresses a gap in evaluation tooling for audio-capable language models.