arXiv Machine Learning

When Does the Real Wiring Win? Testing connectome structure-function claims against unmeasured physiology

The paper investigates whether real neural wiring diagrams truly confer functional advantages over shuffled or rewired alternatives by disentangling the effects of model tuning and physiology. It introduces three estimands—physiology tuned on real wiring transferred to nulls (P1), wiring‑specific tuning (P2), and P2 constrained by independent physiological data (P3)—and applies them to synthetic data and three Drosophila circuit models. The study finds that some structure‑function claims hold across all protocols (e.g., segregated dopamine pathways and head‑direction topography), while others fail when realistic physiology is enforced, revealing that apparent wiring advantages may stem from model tuning rather than true biological superiority.

Hugging Face Trending Papers
Oct 9

FlyHack: Stress-Testing Mechanistic Claims in a Connectome-Constrained Visual Model

FlyHack evaluates how mechanistic conclusions drawn from connectome-constrained neural networks depend on model choice, interventions, circuit representation, and training outcomes. Using a 50‑model ensemble of the flyvis motion‑vision system and task‑matched causal CNN controls, the study finds that key behavioral phenomena—such as reverse‑phi reversal and stationary‑sawtooth responses—vary across models and are not consistently reproduced by CNNs. At the mechanistic level, attribution accuracy and circuit conclusions also differ markedly with representation and ensemble member, indicating that mechanistic claims must be scoped to the specific model family and experimental conditions.

arXiv Computer Vision
Oct 12

FlyHack: Stress-Testing Mechanistic Claims in a Connectome-Constrained Visual Model

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.

By Aashish Dhawan
arXiv AI
Nov 6

ApproxBrain: Certified Sufficiency Frontiers in Connectome-Constrained Neural Systems

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.

By Ali Mahdavi, Azadeh Zamanifar, Amirfarhad Farhadi, Omid Kashefi
arXiv Machine Learning
Oct 22

Reconstruction differences rival individual differences in the fly compass connectome and break trained circuit models

The study compares nine reconstructions of the Drosophila head‑direction circuit, including four different flies and five variants of the same fly with altered thresholds, proofreading, or synapse detection. It finds that changes within a single fly’s reconstruction can alter the circuit more than half the difference seen between different flies, and that neural‑network models trained on one wiring fail to transfer to others, with errors increasing dramatically when weights are perturbed. Despite these reconstruction differences, imaging data show that the biological compass remains functional and stable.

By Md Ali Ashraf Yad, Nazifa Tabassum Nabila
arXiv Machine Learning
6d ago

Are Causal Neuron Circuits Unique and Transferable?

The paper investigates whether groups of neurons that influence a model’s answer are uniquely necessary and transferable across inputs. By exhaustively testing all 4,096 subsets of 12 MLP neurons in Qwen3 and other models, the authors find that only a few neurons are often sufficient to alter predictions, that many subsets can independently flip answers, and that the effect is strongest on the same input chain but weaker on different chains. The study shows that causal neuron circuits are not uniquely defined and that their influence can vary with context and model architecture.

By \"Omer Tekin Yavuz (\.Ileti\c{s}im Yaz{\i}l{\i}m)
arXiv Machine Learning
Nov 2

AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn

AutoHebb introduces autonomous Hebbian networks that combine external feedback with internally generated neuromodulatory signals to gate a biologically grounded 3‑factor Hebbian learning rule. These networks, optimized via meta‑learning for fixed weights, demonstrate strong inductive biases and autonomous learning control, enabling zero‑shot inference and continual learning without external optimization. They outperform contemporary models on these tasks and can be reverse‑engineered into explicit algorithms, highlighting the importance of meta‑learning, Hebbian plasticity, and autonomous learning control.

By Daniel Levine, David van Dijk, Kenneth Kay
arXiv AI
Oct 9

Harness Evolution Hits a Ceiling: When Weight Training Should Begin

The paper investigates when to evolve a harness versus training model weights for long‑horizon LLM agents. By labeling failed trajectories with the first signal that fires, the authors separate process failures from content failures, showing that harness evolution fixes the former while weight training addresses the latter. Experiments on DeepPlanning and WebArena‑Lite demonstrate significant performance gains, with LoRA adapters trained on evolved harness trajectories further improving held‑out scores and reducing content failures.

By Yuan Tian, Bing Hu, Hao Wang, Binghang Lu, Fang Wu