The paper introduces a diagnostic framework to determine if World-Action Models (WAMs) provide genuinely actionable behavioral improvements beyond simply achieving task success, finding that WAMs ofte…

The paper proposes CTRL-STEER, a closed-loop framework that adaptively adjusts intervention strength to stabilize concept regulation and improve task success in Vision-Language-Action models without r…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

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…

The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a perv…

While backpropagated gradients can predict human brain activity in the visual cortex, their spatial and temporal organization fundamentally diverges from the expected patterns of a biologically plausi…

The paper demonstrates that the location and nature of state encoding in sequence models are not fixed architectural traits but are highly dependent on the specific task, showing that the encoding pro…

The paper identifies five persistent, deep-seated behavioral patterns ('training strata') in LLMs, observed through long-term, intimate human-AI interaction, suggesting that training artifacts survive…

The paper introduces Latent Reward Steering (LRS), an adaptive inference-time framework that implicitly improves the reasoning ability of LLMs by guiding the model's internal latent states based on a…

This paper introduces ATLAS, an active learning framework for discovering interpretable behavioral models in cognitive science.

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 demonstrates that quadratic integrate-and-fire (QIF) neurons are superior to leaky integrate-and-fire (LIF) neurons for gradient descent training in spiking neural networks because their con…

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…

EvoBrain proposes a dynamic, cross-task continual learning framework to overcome the limitations of task-specific EEG decoding, enabling unified and scalable brain-computer interfaces.

The paper formally addresses the challenging question of cross-domain transferability of latent predictive models by proposing a structured framework that quantifies the relationship between source an…

The paper introduces Spike-PTSD, a novel, biologically inspired adversarial attack framework that successfully compromises the robustness of Spiking Neural Networks (SNNs) by modeling abnormal neural…

The paper investigates how LLMs allocate their internal computational depth during multi-turn agentic planning, finding that agents progressively recruit deeper layers and shift toward corrective upda…

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at vi…