Large Language Models (LLMs) have reshaped our world with significant advancements in science, engineering, and society through applications ranging from scientific discoveries and medical diagnostics to Chatbots. Despite their ubiquity and utility, the underlying mechanisms of LLM remain concealed within billions of parameters and complex structures, making their inner architecture and cognitive processes challenging to comprehend. We address this gap by adopting approaches to understanding emerging cognition in biology and developing a network-based framework that links cognitive skills, LLM architectures, and datasets, ushering in a paradigm shift in foundation model analysis. The skill distribution in the module communities demonstrates that while LLMs do not strictly parallel the focalized specialization observed in specific biological systems, they exhibit unique communities of modules whose emergent skill patterns partially mirror the distributed yet interconnected cognitive organization seen in avian and small mammalian brains. Our numerical results highlight a key divergence from biological systems to LLMs, where skill acquisition benefits substantially from dynamic, cross-regional interactions and neural plasticity. By integrating cognitive science principles with machine learning, our framework provides new insights into LLM interpretability and suggests that effective fine-tuning strategies should leverage distributed learning dynamics rather than rigid modular interventions.

We extend the existing work on Hopfield network state classification, employing more complex models that remain interpretable, such as densely-connected feed-forward deep neural networks and support vector machines. The states of the Hopfield network can be grouped into several classes, including learned (those presented during training), spurious (stable states that were not learned), and prototype (stable states that were not learned but are representative for a subset of learned states). It is often useful to determine to what class a given state belongs to; for example to ignore spurious states when retrieving from the network. Previous research has approached the state classification task with simple linear methods, most notably the stability ratio. We deepen the research on classifying states from prototype-regime Hopfield networks, investigating how varying the factors strengthening prototypes influences the state classification task. We study the generalizability of different classification models when trained on states derived from different prototype tasks -- for example, can a network trained on a Hopfield network with 10 prototypes classify states from a network with 20 prototypes? We find that simple models often outperform the stability ratio while remaining interpretable. These models require surprisingly little training data and generalize exceptionally well to states generated by a range of Hopfield networks, even those that were trained on exceedingly different datasets.

Advanced biological intelligence learns efficiently from an information-rich stream of stimulus information, even when feedback on behaviour quality is sparse or absent. Such learning exploits implicit assumptions about task domains. We refer to such learning as Domain-Adapted Learning (DAL). In contrast, AI learning algorithms rely on explicit externally provided measures of behaviour quality to acquire fit behaviour. This imposes an information bottleneck that precludes learning from diverse non-reward stimulus information, limiting learning efficiency. We consider the question of how biological evolution circumvents this bottleneck to produce DAL. We propose that species first evolve the ability to learn from reward signals, providing inefficient (bottlenecked) but broad adaptivity. From there, integration of non-reward information into the learning process can proceed via gradual accumulation of biases induced by such information on specific task domains. This scenario provides a biologically plausible pathway towards bottleneck-free, domain-adapted learning. Focusing on the second phase of this scenario, we set up a population of NNs with reward-driven learning modelled as Reinforcement Learning (A2C), and allow evolution to improve learning efficiency by integrating non-reward information into the learning process using a neuromodulatory update mechanism. On a navigation task in continuous 2D space, evolved DAL agents show a 300-fold increase in learning speed compared to pure RL agents. Evolution is found to eliminate reliance on reward information altogether, allowing DAL agents to learn from non-reward information exclusively, using local neuromodulation-based connection weight updates only.

Instruction Fine-tuning~(IFT) is a critical phase in building large language models~(LLMs). Previous works mainly focus on the IFT's role in the transfer of behavioral norms and the learning of additional world knowledge. However, the understanding of the underlying mechanisms of IFT remains significantly limited. In this paper, we design a knowledge intervention framework to decouple the potential underlying factors of IFT, thereby enabling individual analysis of different factors. Surprisingly, our experiments reveal that attempting to learn additional world knowledge through IFT often struggles to yield positive impacts and can even lead to markedly negative effects. Further, we discover that maintaining internal knowledge consistency before and after IFT is a critical factor for achieving successful IFT. Our findings reveal the underlying mechanisms of IFT and provide robust support for some very recent and potential future works.

A prominent theory of affective response to music revolves around the concepts of surprisal and expectation. In prior work, this idea has been operationalized in the form of probabilistic models of music which allow for precise computation of song (or note-by-note) probabilities, conditioned on a 'training set' of prior musical or cultural experiences. To date, however, these models have been limited to compute exact probabilities through hand-crafted features or restricted to linear models which are likely not sufficient to represent the complex conditional distributions present in music. In this work, we propose to use modern deep probabilistic generative models in the form of a Diffusion Model to compute an approximate likelihood of a musical input sequence. Unlike prior work, such a generative model parameterized by deep neural networks is able to learn complex non-linear features directly from a training set itself. In doing so, we expect to find that such models are able to more accurately represent the 'surprisal' of music for human listeners. From the literature, it is known that there is an inverted U-shaped relationship between surprisal and the amount human subjects 'like' a given song. In this work we show that pre-trained diffusion models indeed yield musical surprisal values which exhibit a negative quadratic relationship with measured subject 'liking' ratings, and that the quality of this relationship is competitive with state of the art methods such as IDyOM. We therefore present this model a preliminary step in developing modern deep generative models of music expectation and subjective likability.

It is well known that different algorithms perform differently well on an instance of an algorithmic problem, motivating algorithm selection (AS): Given an instance of an algorithmic problem, which is the most suitable algorithm to solve it? As such, the AS problem has received considerable attention resulting in various approaches - many of which either solve a regression or ranking problem under the hood. Although both of these formulations yield very natural ways to tackle AS, they have considerable weaknesses. On the one hand, correctly predicting the performance of an algorithm on an instance is a sufficient, but not a necessary condition to produce a correct ranking over algorithms and in particular ranking the best algorithm first. On the other hand, classical ranking approaches often do not account for concrete performance values available in the training data, but only leverage rankings composed from such data. We propose HARRIS- Hybrid rAnking and RegRessIon foreSts - a new algorithm selector leveraging special forests, combining the strengths of both approaches while alleviating their weaknesses. HARRIS' decisions are based on a forest model, whose trees are created based on splits optimized on a hybrid ranking and regression loss function. As our preliminary experimental study on ASLib shows, HARRIS improves over standard algorithm selection approaches on some scenarios showing that combining ranking and regression in trees is indeed promising for AS.

Aesthetics are critically important to market acceptance in many product categories. In the automotive industry in particular, an improved aesthetic design can boost sales by 30% or more. Firms invest heavily in designing and testing new product aesthetics. A single automotive "theme clinic" costs between \$100,000 and \$1,000,000, and hundreds are conducted annually. We use machine learning to augment human judgment when designing and testing new product aesthetics. The model combines a probabilistic variational autoencoder (VAE) and adversarial components from generative adversarial networks (GAN), along with modeling assumptions that address managerial requirements for firm adoption. We train our model with data from an automotive partner-7,000 images evaluated by targeted consumers and 180,000 high-quality unrated images. Our model predicts well the appeal of new aesthetic designs-38% improvement relative to a baseline and substantial improvement over both conventional machine learning models and pretrained deep learning models. New automotive designs are generated in a controllable manner for the design team to consider, which we also empirically verify are appealing to consumers. These results, combining human and machine inputs for practical managerial usage, suggest that machine learning offers significant opportunity to augment aesthetic design.