Rufin VanRullen

Attention shapes our perception by allowing us to focus on relevant stimuli that are selected for conscious processing. In this work we assessed to what degree attention influences the extraction of modality-invariant information, i.e., information that is independent of the input stimulus modality. To this end we analyze fMRI data of subjects viewing naturalistic images and reading short textual descriptions while paying attention to only one of the two modalities. Using cross-modality decoding we found modality-invariant representations in a small area of the cortex even in the absence of attention, spreading to much larger regions when stimuli are attended. This work demonstrates how state-of-the-art decoding techniques on large-scale data can be used to expand our knowledge on how attention shapes specific high-level representations in the brain.

In AI, existential risk denotes the hypothetical threat posed by an artificial system that would possess both the capability and the objective, either directly or indirectly, to eradicate humanity. This issue is gaining prominence in scientific debate due to recent technical advancements and increased media coverage. In parallel, AI progress has sparked speculation and studies about the potential emergence of artificial consciousness. The two questions, AI consciousness and existential risk, are sometimes conflated, as if the former entailed the latter. Here, I explain that this view stems from a common confusion between consciousness and intelligence. Yet these two properties are empirically and theoretically distinct. Arguably, while intelligence is a direct predictor of an AI system’s existential threat, consciousness is not. There are, however, certain incidental scenarios in which consciousness could influence existential risk, in either direction. Consciousness could be viewed as a means towards AI alignment, thereby lowering existential risk; or, it could be a precondition for reaching certain capabilities or levels of intelligence, and thus positively related to existential risk. Recognizing these distinctions can help AI safety researchers and public policymakers focus on the most pressing issues.

Humans perform tasks involving the manipulation of inputs regardless of how these signals are perceived by the brain, thanks to representations that are invariant to the stimulus modality. In this paper, we present modality-agnostic decoders that leverage such modality-invariant representations to predict which stimulus a subject is seeing, irrespective of the modality in which the stimulus is presented. Training these modality-agnostic decoders is made possible thanks to our new large-scale fMRI dataset SemReps-8K, released publicly along with this paper. It comprises six subjects watching both images and short text descriptions of such images, as well as the conditions during which the subjects were imagining visual scenes. We find that modality-agnostic decoders can perform as well as modality-specific decoders and even outperform them when decoding captions and mental imagery. Furthermore, a searchlight analysis revealed that large areas of the brain contain modality-invariant representations. Such areas are also particularly suitable for decoding visual scenes from the mental imagery condition.

Brain activity unfolds across space and time, giving rise to spatiotemporal dynamics that can manifest as cortical traveling waves –smooth phase shifts propagating across the cortex. Although traveling waves have been observed across species and measurement scales, their functional role in human cognition remains largely inferred from correlational evidence. In healthy humans, large-scale neural dynamics must be studied non-invasively, which provides limited access to their neural origins. Here, we tested whether global traveling waves causally contribute to inter-areal communication during attention. Using transcranial magnetic stimulation (TMS), we induced long-range traveling waves detectable with electroencephalography and assessed their neural and behavioral consequences during an attentional search task. Double-pulse TMS applied over the right frontal eye field transiently disrupted ongoing global waves and selectively induced direction- and frequency-specific traveling waves propagating toward the occipital visual cortex. These TMS-induced anterior-to-posterior theta traveling waves were rhythmically modulated by stimulation latency relative to search-trial onset. Critically, behavioral performance exhibited the same rhythmic pattern, with improved attentional search performance when TMS-induced traveling waves were more prominent. Together, these findings provide causal evidence that large-scale traveling waves support inter-areal communication during rhythmic visual attention.

Electrophysiological and neuroimaging studies have revealed how the brain encodes various visual categories and concepts. An open question is how combinations of multiple visual concepts are represented in terms of the component brain patterns: are brain responses to individual concepts composed according to algebraic rules? To explore this, we generated “conceptual perturbations" in neural space by averaging fMRI responses to images with a shared concept (e.g., “winter" or “summer"). After thresholding to ensure specificity, we applied these perturbations to the neural pattern associated with a base image, forming new brain patterns that incorporate the added concept. These modified brain patterns were then decoded into images using a pretrained fMRI-to-image decoding model. Qualitative and quantitative inspection of the resulting images provides insight into how the brain might combine visual concepts. For example, adding a “winter" perturbation to the brain pattern of a man on a skateboard yields a new pattern representing a man on a snowboard in a winter scene—even when the perturbation modifies only a small subset of voxels. Our findings reveal that compositional processes in neural representations may lead to predictable perceptual outcomes, as interpreted by our decoding model. This suggests that the brain’s combinatory encoding of concepts may follow a systematic, algebraic-like process—what we term “brain algebra." Although our study is model-driven, it opens avenues for future empirical work into the mechanisms of compositionality in the brain.

Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations or to translate signals from one domain to another (as in image captioning or text-to-image generation). However, current approaches mainly rely on brute-force supervised training over large multimodal datasets. In contrast, humans (and other animals) can learn useful multimodal representations from only sparse experience with matched cross-modal data. Here, we evaluate the capabilities of a neural network architecture inspired by the cognitive notion of a “global workspace” (GW): a shared representation for two (or more) input modalities. Each modality is processed by a specialized system (pretrained on unimodal data and subsequently frozen). The corresponding latent representations are then encoded to and decoded from a single shared workspace. Importantly, this architecture is amenable to self-supervised training via cycle-consistency: encoding–decoding sequences should approximate the identity function. For various pairings of vision-language modalities and across two datasets of varying complexity, we show that such an architecture can be trained to align and translate between two modalities with very little need for matched data (from four to seven times less than a fully supervised approach). The GW representation can be used advantageously for downstream classification and cross-modal retrieval tasks and for robust transfer learning. Ablation studies reveal that both the shared workspace and the self-supervised cycle-consistency training are critical to the system’s performance.

Automotive radar sensors provide valuable information for advanced driving assistance systems (ADAS). Radars can reliably estimate the distance to an object and the relative velocity, regardless of weather and light conditions. However, radar sensors suffer from low resolution and huge intra-class variations in the shape of objects. Exploiting the time information (e.g, multiple frames) has been shown to help to capture better the dynamics of objects and, therefore, the variation in the shape of objects. Most temporal radar object detectors use 3D convolutions to learn spatial and temporal information. However, these methods are often non-causal and unsuitable for real-time applications. This work presents RECORD, a new recurrent CNN architecture for online radar object detection. We propose an end-to-end trainable architecture mixing convolutions and ConvLSTMs to learn spatio-temporal dependencies between successive frames. Our model is causal and requires only the past information encoded in the memory of the ConvLSTMs to detect objects. Our experiments show such a method’s relevance for detecting objects in different radar representations (range-Doppler, range-angle) and outperform state-of-the-art models on the ROD2021 and CARRADA datasets while being less computationally expensive.

Previous studies have shown that it is possible to map brain activation data of subjects viewing images onto the feature representation space of not only vision models (modality-specific decoding) but also language models (cross-modal decoding). In this work, we introduce and use a new large-scale fMRI dataset (~8,500 trials per subject) of people watching both images and text descriptions of such images. This novel dataset enables the development of modality-agnostic decoders: a single decoder that can predict which stimulus a subject is seeing, irrespective of the modality (image or text) in which the stimulus is presented. We train and evaluate such decoders to map brain signals onto stimulus representations from a large range of publicly available vision, language and multimodal (vision+language) models. Our findings reveal that (1) modality-agnostic decoders perform as well as (and sometimes even better than) modality-specific decoders (2) modality-agnostic decoders mapping brain data onto representations from unimodal models perform as well as decoders relying on multimodal representations (3) while language and low-level visual (occipital) brain regions are best at decoding text and image stimuli, respectively, high-level visual (temporal) regions perform well on both stimulus types.

In neural decoding research, one of the most intriguing topics is the reconstruction of perceived natural images based on fMRI signals. Previous studies have succeeded in re-creating different aspects of the visuals, such as low-level properties (shape, texture, layout) or high-level features (category of objects, descriptive semantics of scenes) but have typically failed to reconstruct these properties together for complex scene images. Generative AI has recently made a leap forward with latent diffusion models capable of generating high-complexity images. Here, we investigate how to take advantage of this innovative technology for brain decoding. We present a two-stage scene reconstruction framework called “Brain-Diffuser”. In the first stage, starting from fMRI signals, we reconstruct images that capture low-level properties and overall layout using a VDVAE (Very Deep Variational Autoencoder) model. In the second stage, we use the image-to-image framework of a latent diffusion model (Versatile Diffusion) conditioned on predicted multimodal (text and visual) features, to generate final reconstructed images. On the publicly available Natural Scenes Dataset benchmark, our method outperforms previous models both qualitatively and quantitatively. When applied to synthetic fMRI patterns generated from individual ROI (region-of-interest) masks, our trained model creates compelling “ROI-optimal” scenes consistent with neuroscientific knowledge. Thus, the proposed methodology can have an impact on both applied (e.g. brain–computer interface) and fundamental neuroscience.

Research in machine learning has polarized into two general approaches for regression tasks: Transductive methods construct estimates directly from available data but are usually problem unspecific. Inductive methods can be much more specific but generally require compute-intensive solution searches. In this work, we propose a hybrid approach and show that transductive regression principles can be meta-learned through gradient descent to form efficient in-context neural approximators by leveraging the theory of vector-valued Reproducing Kernel Banach Spaces (RKBS). We apply this approach to function spaces defined over finite and infinite-dimensional spaces (function-valued operators) and show that once trained, the Transducer can almost instantaneously capture an infinity of functional relationships given a few pairs of input and output examples and return new image estimates. We demonstrate the benefit of our meta-learned transductive approach to model complex physical systems influenced by varying external factors with little data at a fraction of the usual deep learning training computational cost for partial differential equations and climate modeling applications.