MLINFO COLLECTION
Living neuronal networks transform inputs through recurrent cellular and population dynamics, yet it is unknown which network architecture supports which computation. Neurons-on-a-chip turn this…
The Independent Chip Model (ICM) converts the chip stacks of the players remaining in a poker tournament into finishing-place probabilities and prize equities. It is the standard model in tournament…
We study sender-receiver games in which players commit, before the state is drawn, to payments contingent on the subsequently verified state and the receiver's action. Payments may be transferred or…
Frameworks that use large language models for scientific discovery typically rely on a fixed, human-designed algorithm that decides what the model sees at each step, leaving the model only the role…
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically…
Integer-valued leaky integrate-and-fire (I-LIF) neurons and spike firing approximation (SFA) reduce temporal training cost by representing spike trains as firing counts and normalized firing rates,…
The investment acceleration principle is a heuristic for modelling investment time series out of consumption time series. The model presented herein develops a disaggregated accelerator equation…
Deploying a pretrained controller exposes it to conditions that are absent from its training data. Sensor drift, outright sensor failure and accumulating measurement noise all induce a distribution…
Hybrid quantum classical neural networks integrate parameterized quantum circuits (PQCs) with established deep learning architectures, but their performance depends strongly on the choice of quantum…
Aggregate accuracy cannot reveal which utterances are locally vulnerable or how internal activity changes when labels remain stable. We retain every prediction for 725,070 adjacent-bin, one-count…
Edge intelligence requires models to sense continuously in real time and to keep adapting on-device, all under tight compute, energy, and memory budgets. Although spiking neural networks (SNNs)…
This paper presents a construction of a small universal machine within the framework of Multi-set Reaction Systems. We encode the machine state using elements that represent registers and instruction…
Spiking Neural Networks (SNNs) have attracted increasing attention due to their impressive temporal dynamics, energy efficiency, and brain-inspired mechanisms. Although SNNs have demonstrated…
Low-cost NAS must both explore high-performing architectures and identify them reliably, yet reducing evaluation cost often weakens the fidelity of candidate comparisons. Training-free methods reduce…
End-to-end backpropagation has been the dominant mode of training in deep learning, allowing for the coordination of parameter updates across layers of a neural network. Prior studies have explored…
Pseudo-random number generation often requires trade-offs among quality, power consumption, and bandwidth to produce unpredictable sequences of numbers. The brain, on the other hand, efficiently…
Spiking neural networks (SNNs) offer low-energy sequence modeling through sparse, event-driven computation. However, interactions among spike encoding, neuronal dynamics, and information propagation…
Compact regulatory DNA can free up space in vector payloads, reduce synthesis and assay burden, and expose which sequence features drive predicted activity. Yet most model-based nucleic-acid…
Randomised copies of a connectome are the usual baseline for asking whether measured wiring matters, and the answer depends on what the randomisation preserves. We evolved embodied foraging agents…
Parameter-efficient reinforcement learning aims to improve reasoning with a compact trainable interface to a pretrained model. We introduce the Thalamic Router (T-Router), which concentrates…
Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorithms. Many successful algorithm-design agents…
基礎モデルの前処理を行うためのライブラリ。最小限でシームレスにスケールできる。
This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the network weights. Two e-puck-type robots,…
Hyperdimensional computing and vector symbolic architectures often represent quantized scalar levels by dense binary codebooks whose level-to-level similarity is intended to follow a prescribed…