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.
984 papers reviewed by authors · 731–740 / 984
NEO is a hyperparameter-free, computationally efficient Test-Time Adaptation method that improves model robustness and calibration under distribution shifts by re-centering target data embeddings at the origin, achieving superior accuracy across multiple datasets and devices with minimal compute overhead.
The paper introduces Scam2Prompt, a scalable framework that reveals a critical and worsening security vulnerability in production Large Language Models, where automated prompts derived from malicious scam sites successfully trigger the generation of harmful code in up to 47.3% of cases across multiple models, rendering current safety measures like guardrails and RAG insufficient.
This paper establishes that context-free languages which are substitutable under a fixed finite-monoid typing can be identified in the limit from positive data, with hypothesis construction and update running in polynomial time in the sample size for the general fixed-h class and a full polynomial time-and-data guarantee (including a polynomial bound on the characteristic-sample size) for the linear subclass, via a finite typed reconstruction theory built around a canonical hypothesis grammar derived from a finite observation set.
The paper proves that the complexity class NL is distinct from logCFL, a result that further implies the separations L ≠ Ptime and NL ≠ Ptime.
This paper introduces INCAMA, a physics-aware framework that combines latent-space inversion with a delay-aware Mamba encoder to recover directed neural causal structures from distorted neuroimaging signals, demonstrating superior performance over baselines in both simulations and real-world fMRI data.
This paper establishes a quadratic-form representation of the scalar Casimir trace by deriving an induced Green kernel from a codimension-three Riesz reduction, which allows the expectation of a heat-regularized Gaussian source's energy to exactly reproduce the trace and confirms standard finite-part results in Dirichlet parallel-plate geometries.
This paper extends the restricted phase space formalism to quasi-local regimes with static observers at finite distances, demonstrating that RN black holes in this setting exhibit thermodynamic behaviors and phase transitions strikingly similar to asymptotic RN-AdS black holes, including Hawking-Page-like transitions in the neutral limit, provided an extra pair of thermodynamic variables (pressure and boundary area) is included.
This paper presents an overview, observing strategy, and initial results of a coordinated HST imaging survey covering 1.1 square degrees in the Galactic Bulge, designed to create a high-resolution legacy dataset that will significantly enhance the scientific return of the upcoming Nancy Grace Roman Galactic Bulge Time Domain Survey.
This paper generalizes the graph-theoretic concept of "blow-up," where vertices are replaced by copies, to a broader combinatorial framework and explores its potential applications.
The paper introduces You Only Stack Once (YOSO), a novel deep-learning pipeline that utilizes a Gaussian Motion Filter to efficiently detect faint, slow-moving Solar System objects with an extremely low false positive rate, offering a scalable alternative to traditional shift-and-stack methods for large-scale astronomical surveys.