Papers where the original authors have engaged with our plain-language explanation.
For every paper on this page, at least one of the original authors has seen our plain-language explanation and engaged with it — either confirming it reads accurately or requesting corrections that we then applied. An endorsement does not mean the authors formally approve every sentence, but it does mean the explanation has passed the eyes of the people who wrote the paper.
1335 papers reviewed by authors · 211–220 / 1335
This paper proposes and validates a method for generating "desirable" collective rankings of alternatives based on agents' preferences relative to their matches, demonstrating through theoretical analysis, simulations, and real-world data that this approach converges to true quality rankings and outperforms existing benchmarks like revealed preference and Borda counts.
This paper proposes a training-free method to halve the computational cost of fine-grained Mixture-of-Experts models at inference by decoupling expert selection from probability renormalization, thereby preserving performance by normalizing against a larger reference set of experts rather than the reduced active set.
This paper introduces a new multilayer analytic raytracing method in the NuRadioMC framework that models complex, piecewise exponential refractive index profiles to enable realistic and computationally efficient simulation of radio signal propagation in diverse neutrino detector environments, including the atmosphere.
This paper presents a technical manual for an open-source toolkit designed to measure how transformer language models individuate word senses across different contexts using "bridge forms," detailing the methodology, design choices, and failure modes of the pipeline without reporting empirical results.
This paper introduces a sample-efficient, dynamic context adaptation framework that combines a validation agent's execution trace analysis, a knowledge graph for semantic constraints, and simulated annealing to outperform existing LLM-based code generation methods in solving problems where correctness relies on runtime-dependent coupling between components.
This paper presents a CPU-oriented algorithm that leverages Intel AMX BF16 matrix products to emulate high-precision FP32 and FP64 GEMM operations, achieving competitive throughput and tunable accuracy by decomposing operands into multiple low-precision components and accumulating them in higher precision.
This study establishes a pre-mining ecohydrological baseline for bauxite deposits in Minas Gerais, revealing that while current soil conditions remain viable, unregulated water withdrawals and a critical inverse relationship between soil mechanical resistance and infiltration capacity pose severe risks to spring flow and water security, necessitating rigorous rehabilitation strategies for future mining operations.
This study presents the design and pilot evaluation of a locally deployed, AI-assisted mobile health platform at the University of Abuja Teaching Hospital, demonstrating its technical feasibility, high usability, and substantial clinical concordance in improving healthcare access for Nigerian university students.
This paper introduces Hardware-Aware FP4 FlashAttention-4, a method that overcomes the limitations of Blackwell's FP4 tensor cores by employing Direct-P for noncausal inference and a causal path with FP8 gradients, achieving up to 2.13× faster forward throughput and 1.14× faster single-GPU training updates while avoiding the divergence issues observed in MXFP4 training.
This paper proposes and demonstrates a "superconducting Peierls instability" in two-dimensional superconductors, where enhanced quasiparticle responses at edge Bogoliubov Fermi points drive a pairing-mode softening that spontaneously generates an edge pair-density wave, thereby gapping the Andreev bound states and breaking translation symmetry.