This paper investigates the influence of image-generation AI interfaces on human decision making, finding that higher variance in design sets leads to selection of center-proximal designs.

This paper introduces Accessibility Plasticity, a principle of adaptive computation that allows systems to adapt by reorganizing which existing computations can interact and participate, reducing the…

This paper analyzes multi-model self-consuming training, showing that while human curation helps individual models, cross-model interactions can degrade long-term alignment by dampening or inverting t…

The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

The paper argues that purported anthropomorphic attributes of LLMs are not unique to language models but are substrate-dependent, demonstrating this by training a neural network on the game Age of Emp…

The paper identifies specific attention heads in LLMs responsible for 'cultural binding'—associating cultural items with appropriate identities—and demonstrates that this capability is pre-trained and…

The paper tracks the developmental emergence of attention circuits in 1B-class language models, finding that the formation of induction and attention-sink circuits are distinct, temporally separated t…

This paper characterizes the convergence pattern of chain-of-thought reasoning models and finds that convergence fate is partially encoded in intermediate representations.

The paper compares anchorless methods for diversifying LLM-generated idea pools against traditional anchor-dependent methods, finding that semantic direction stratification offers the best balance of…

The paper demonstrates that off-the-shelf image diffusion models, like Stable Diffusion, can be repurposed to generate synthetic structured data, posing a threat of ground truth drift in closed eviden…

The study finds that specific, interpretable neuron populations (Rosetta Neurons) exhibit predictable, scale-dependent changes in selectivity and specialization as neural models grow larger.

This paper argues for the importance of modularity and heterogeneity in AI architectures, contrasting the Transformer model with the structure of the cortex.

The study demonstrates that conditioning AI brand recommendations on a user's persona significantly alters the recommended product set, particularly for mid-market brands, and this effect is largest o…

This study demonstrates that instruction-tuned language model agents exhibit robust, group-contingent in-group bias, structurally mimicking human social biases, even when standard action logs fail to…

The paper demonstrates that in Mamba-2, single-bucket probes can detect a large functional signature (detection layer) that is not fully responsible for the actual computation (execution layer), chall…

This paper proposes a game-theoretic framework using Shapley Effects and Pareto front sets for interpretable hyperparameter-objective interaction analysis.