The paper introduces a framework for defining and certifying computational sufficiency in neural systems constrained by a connectome. It formalises sufficiency as a cost-indexed family of neuron subsets conditioned on a task and a tolerance pair, and certifies candidate circuits using one-sided bounds over held-out parameter draws. Experiments on a walking simulator demonstrate that the published 148-neuron circuit is uniquely sufficient, while variations in task or tolerance yield different sufficient subsets, highlighting that sufficiency is set-valued and task-dependent.
arXiv:2605.12049v2 Announce Type: replace-cross Abstract: Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent...
arXiv:2606. 30676v1 Announce Type: cross Abstract: Deploying spiking neural networks (SNNs) on neuromorphic hardware demands aggressive synaptic pruning while preserving temporal computation integrity.
arXiv:2604. 23878v3 Announce Type: replace Abstract: ZenBrain is a seven-layer, neuroscience-derived memory architecture for LLM agents that unifies fifteen mechanisms - from Two-Factor synaptic consolidation to a Simulation-Selection sleep loop - under a single MemoryCoordinator: nine foundational algorithms plus six Predictive Memory Architecture components.
The paper introduces GAPS, a dimension‑level gating approach for activation steering in language models. GAPS uses two training‑free gates—a static separability gate based on AUROC and a dynamic posterior gate based on a Gaussian model—to selectively apply steering vectors only to neurons that carry reliable concept information or are currently mis‑activated. Experiments on Gemma‑3 and Qwen‑3 show that GAPS improves or matches the performance of token‑level methods, notably reducing Gemma‑3’s toxicity rate from 6.52% to 0.48% under a fixed capability budget.
The study investigates the consistency and specificity of language model circuits across six tasks and five models, focusing on component-level (attention heads and MLP blocks) and neuron-level circuits. Component-level circuits are highly consistent and causally important but lack task specificity, as ablating a circuit for one task similarly harms performance on other tasks. Neuron-level circuits show higher task specificity but lower consistency, with overlap mainly between closely related tasks. The analysis of Llama‑3.2‑3B reveals that shared components are predominantly MLP blocks, while attention heads act as generic attention‑sink heads.
arXiv:2607. 18921v1 Announce Type: cross Abstract: Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior.
arXiv:2607. 10439v2 Announce Type: replace-cross Abstract: We model human motor cortex, recorded during rest and motor-imagery BCI conditions, as a port-Hamiltonian system: a conservative interconnection (skew-symmetric coupling between band-limited neural phasors) together with a dissipative port whose state-dependent decay is set by a graph-neural-network surrogate.
FlyHack examines how mechanistic claims in a connectome‑constrained visual model depend on the comparison model, intervention, circuit representation, and trained solution. Using a 50‑model ensemble of the Drosophila motion‑vision model (flyvis) and task‑matched causal CNN controls, the study finds that behavioral phenomena such as reverse‑phi reversal and stationary‑sawtooth responses vary with period, velocity, and model family, while adversarial robustness differs between flyvis and CNNs. At the mechanistic level, attribution accuracy and circuit conclusions also shift with representation choices and ensemble members, indicating that conclusions drawn from connectome‑constrained models are highly context‑dependent.
The paper introduces Circuit Condensation, a post‑training method that prunes low‑attribution edges from large causal graphs and trains a low‑rank adapter to preserve behavior. Across four behaviors and eight models, the condensed circuits are on average 8.1× smaller than the strongest frozen baseline, with reductions up to 316×. Experiments show that weight updates drive the size reduction, and detailed ablations reveal dependencies among remaining edges and a more focused set of heads for indirect object identification.
Activation steering suppresses undesired behaviors in language models by adding a steering vector to the hidden state during generation. Recent conditional methods such as CAST and DSAS improve the be...
arXiv:2608.22347v1 Announce Type: new Abstract: A cognitive architecture is more than the module that reasons: it must also decide how long to think and what deserves the effort. We built a minimal b...
A recurring design choice in building AI systems is whether, when a task is too hard for a model, to expand the model (make it larger, better-prompted, fine-tuned), or to decompose the task (extract t...