Inspired by the neural mechanisms that may contribute to the brain's associative power, specifically the cortical modularization and hippocampal pattern completion, here we propose a self-supervised controllable generation (SCG) framework.

The visual system of mammals is comprised of parallel, hierarchical specialized pathways. Different pathways are specialized in so far as they use representations that are more suitable for supporting specific downstream behaviours. In particular, the clearest example is the specialization of the ventral (what) and dorsal (where) pathways of the visual cortex. These two pathways support behaviours related to visual recognition and movement, respectively. To-date, deep neural networks have mostly been used as models of the ventral, recognition pathway.

The human brain exhibits a strong ability to spontaneously associate different visual attributes of the same or similar visual scene, such as associating sketches and graffiti with real-world visual objects, usually without supervising information. In contrast, in the field of artificial intelligence, controllable generation methods like ControlNet heavily rely on annotated training datasets such as depth maps, semantic segmentation maps, and poses, which limits the method's scalability. Inspired by the neural mechanisms that may contribute to the brain's associative power, specifically the cortical modularization and hippocampal pattern completion, here we propose a self-supervised controllable generation (SCG) framework. Firstly, we introduce an equivariance constraint to promote inter-module independence and intra-module correlation in a modular autoencoder network, thereby achieving functional specialization. Subsequently, based on these specialized modules, we employ a self-supervised pattern completion approach for controllable generation training. Experimental results demonstrate that the proposed modular autoencoder effectively achieves functional specialization, including the modular processing of color, brightness, and edge detection, and exhibits brain-like features including orientation selectivity, color antagonism, and center-surround receptive fields. Through self-supervised training, associative generation capabilities spontaneously emerge in SCG, demonstrating excellent zero-shot generalization ability to various tasks such as superresolution, dehaze and associative or conditional generation on painting, sketches, and ancient graffiti. Compared to the previous representative method ControlNet, our proposed approach not only demonstrates superior robustness in more challenging high-noise scenarios but also possesses more promising scalability potential due to its self-supervised manner. Codes are released on Github and Gitee.

Modular exponentiation is crucial to number theory and cryptography, yet remains largely unexplored from a mechanistic interpretability standpoint. We train a 4-layer encoder-decoder Transformer model to perform this operation and investigate the emergence of numerical reasoning during training. Utilizing principled sampling strategies, PCA-based embedding analysis, and activation patching, we examine how number-theoretic properties are encoded within the model. We find that reciprocal operand training leads to strong performance gains, with sudden generalization across related moduli. These synchronized accuracy surges reflect grokking-like dynamics, suggesting the model internalizes shared arithmetic structure. We also find a subgraph consisting entirely of attention heads in the final layer sufficient to achieve full performance on the task of regular exponentiation. These results suggest that transformer models learn modular arithmetic through specialized computational circuits, paving the way for more interpretable and efficient neural approaches to modular exponentiation.

Large language models (LLMs) struggle with representing and generating rare tokens despite their importance in specialized domains. We investigate whether LLMs develop internal specialization mechanisms through discrete modular architectures or distributed parameter-level differentiation. Through systematic analysis of final-layer MLP neurons across multiple model families, we discover that rare-token processing emerges via \textit{distributed specialization}: functionally coordinated but spatially distributed subnetworks that exhibit three distinct organizational principles. First, we identify a reproducible three-regime influence hierarchy comprising highly influential plateau neurons(also termed as rare-token neurons), power-law decay neurons, and minimally contributing neurons, which is absent in common-token processing. Second, plateau neurons demonstrate coordinated activation patterns (reduced effective dimensionality) while remaining spatially distributed rather than forming discrete clusters. Third, these specialized mechanisms are universally accessible through standard attention pathways without requiring dedicated routing circuits. Training dynamics reveal that functional specialization emerges gradually through parameter differentiation, with specialized neurons developing increasingly heavy-tailed weight correlation spectra consistent with Heavy-Tailed Self-Regularization signatures. Our findings establish that LLMs process rare-tokens through distributed coordination within shared architectures rather than mixture-of-experts-style modularity. These results provide insights for interpretable model editing, computational efficiency optimization, and understanding emergent functional organization in transformer networks.

The human brain exhibits a strong ability to spontaneously associate different visual attributes of the same or similar visual scene, such as associating sketches and graffiti with real-world visual objects, usually without supervising information. In contrast, in the field of artificial intelligence, controllable generation methods like ControlNet heavily rely on annotated training datasets such as depth maps, semantic segmentation maps, and poses, which limits the method's scalability. Inspired by the neural mechanisms that may contribute to the brain's associative power, specifically the cortical modularization and hippocampal pattern completion, here we propose a self-supervised controllable generation (SCG) framework. Firstly, we introduce an equivariance constraint to promote inter-module independence and intra-module correlation in a modular autoencoder network, thereby achieving functional specialization. Subsequently, based on these specialized modules, we employ a self-supervised pattern completion approach for controllable generation training. Experimental results demonstrate that the proposed modular autoencoder effectively achieves functional specialization, including the modular processing of color, brightness, and edge detection, and exhibits brain-like features including orientation selectivity, color antagonism, and center-surround receptive fields.

Large language models struggle with representing and generating rare tokens despite their importance in specialized domains. In this study, we identify neuron structures with exceptionally strong influence on language model's prediction of rare tokens, termed as rare token neurons, and investigate the mechanism for their emergence and behavior. These neurons exhibit a characteristic three-phase organization (plateau, power-law, and rapid decay) that emerges dynamically during training, evolving from a homogeneous initial state to a functionally differentiated architecture. In the activation space, rare token neurons form a coordinated subnetwork that selectively co-activates while avoiding co-activation with other neurons. This functional specialization potentially correlates with the development of heavy-tailed weight distributions, suggesting a statistical mechanical basis for emergent specialization.

The visual system of mammals is comprised of parallel, hierarchical specialized pathways. Different pathways are specialized in so far as they use representations that are more suitable for supporting specific downstream behaviours. In particular, the clearest example is the specialization of the ventral ("what") and dorsal ("where") pathways of the visual cortex. These two pathways support behaviours related to visual recognition and movement, respectively. To-date, deep neural networks have mostly been used as models of the ventral, recognition pathway.

As AI systems become increasingly powerful, the need for safe AI has become more pressing. Humans are an attractive model for AI safety: as the only known agents capable of general intelligence, they perform robustly even under conditions that deviate significantly from prior experiences, explore the world safely, understand pragmatics, and can cooperate to meet their intrinsic goals. Intelligence, when coupled with cooperation and safety mechanisms, can drive sustained progress and well-being. These properties are a function of the architecture of the brain and the learning algorithms it implements. Neuroscience may thus hold important keys to technical AI safety that are currently underexplored and underutilized. In this roadmap, we highlight and critically evaluate several paths toward AI safety inspired by neuroscience: emulating the brain's representations, information processing, and architecture; building robust sensory and motor systems from imitating brain data and bodies; fine-tuning AI systems on brain data; advancing interpretability using neuroscience methods; and scaling up cognitively-inspired architectures. We make several concrete recommendations for how neuroscience can positively impact AI safety.