The Archive

Euler system enables multi-agent mathematical discovery with shared context and interpretable reasoning steps for collaborative proof development.

LAGO meta-agent framework treats specialized agents as reusable options; resolves 58.6% of SWE-bench tasks with frozen Qwen3.5-35B.

PROMETHEUS framework applies causal multi-treatment ranking to population health stratification for resource-constrained clinical care prioritization.

Analysis of looped transformers reveals failure modes beyond computation: recurrent reasoners lose retention or state reusability when iterating past training depth.

OpenAI analysis of agentic AI adoption trends across EU enterprises and SMBs, identifying gaps in value realization.

Max Hodak, the former president and co-founder of Neuralink, detailed on stage at TechCrunch Disrupt how his company's work with PRIMA is part of its path toward a novel brain-computer interface (BCI).

Neural inference pipeline with Set Attention learns summary statistics for Bayesian inference over chemical reaction networks.

Analytical study of grokking phenomenon identifying sharp conditions and asymptotic expressions for delayed generalization in neural networks.

CarryOn organizes long-horizon agent context around reusable task objects instead of interaction histories, reducing redundant processing.

SolBehave benchmarks behavioral correctness of LLM-generated Solidity contracts via differential fuzzing and transaction replay across 250 Ethereum contracts.

Gauge-equivariant GNNs exhibit loop geometry with rapid contour growth and slow spatial expansion independent of network training.

Neural network approach to quantum state discrimination improves mid-circuit measurement reliability on superconducting hardware, bounded by Bayes risk.

MemoryVLN addresses context-length limits in vision-language navigation via memory construction and spatial reuse mechanisms for long-horizon trajectories.

Graph Metanetworks extends weight-space learning to transformers by accounting for attention-induced continuous symmetries beyond neuron permutations.

LLM agents with persistent textual memory show unstable performance; randomized experiments curate effective playbooks to improve multi-step task reuse.

Theory of representation reuse defines task-relevant state as coarsest deterministic state sufficient for families of downstream tasks.

Journalists, entrepreneurs, and even some public relations professionals will tell you that the PR process is broken. But could AI actually make things better?

Fisher information matrix analysis on CIFAR-10 vision models reveals how top eigenvectors decouple generalization from memorization under controlled noise.

Hashrope unifies four LLM context management mechanisms (edits, branching, KV-cache reuse, segment encoding) via persistent weight-balanced rope.

Extends distributional regression to arbitrary response spaces using ReLU networks and event-based probability indexing.

CloneOT uses lineage-supervised neural optimal transport to predict single-cell perturbation responses by learning transport costs from heritable barcodes.

VLCQ post-training quantization method uses variable-length coding instead of fixed-point integers to achieve higher compression rates on resource-constrained devices.

NARS combines retrieval-augmented LLM reasoning with gradual argumentation semantics to detect persuasiveness in online debate discussions via neuro-symbolic structures.

Theoretical framework for neural network topological expressivity using Betti numbers of network output rather than decision boundaries.

Backdoor attacks prove AI models can provably hide capabilities via encrypted neural circuits resilient to elicitation under cryptographic assumptions.

Multi-scale spiking neural network model integrates sleep homeostasis and circadian rhythms to simulate clinical sleep disorders.

Constrained decoding with structural automata ensures well-formed semantic parse generation in DRS and AMR parsing.

IntWorld and PermWorld are mathematical task ecosystems designed to study how neural networks learn under task diversity similar to modern language model training.

LISCO learns primal-dual solver steps via neural networks to reduce real-time cost of nonlinear MPC for constrained optimization.

Oído: 13M-parameter Conformer-CTC speech recognition on ESP32-S3 microcontroller ($5, 512KB SRAM) via int8 quantization and SIMD optimization.