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.
438 papers reviewed by authors · 181–190 / 438
This paper introduces a U-Net-based Generative Adversarial Network (GAN) trained on realistic Planck-like simulations that successfully reconstructs high-fidelity Cosmic Microwave Background maps by simultaneously removing foreground contamination, instrumental noise, and beam convolution effects, achieving reconstruction errors below 1% outside the Galactic region.
This paper proposes and validates the "Agent-First Tool API" paradigm, which replaces traditional human-oriented CRUD interfaces with a semantic six-verb protocol and structured decision-support metadata to significantly enhance autonomous agent task success rates and error recovery in enterprise production systems.
The paper proposes Contextual Plackett-Luce (CPL), an efficient neural model that combines parallel scoring with a lightweight autoregressive selection process to effectively handle ambiguous, multi-modal sequence prediction tasks while maintaining computational efficiency.
The paper introduces Key-Value Means (KVM), a novel block-recurrence mechanism for attention that unifies the benefits of transformers and linear RNNs by enabling efficient, chunk-parallelizable training with flexible state growth and subquadratic prefill time, all while using standard operations and minimal additional parameters.
The paper introduces DP-LAC, a lightweight method for differentially private federated fine-tuning of language models that efficiently estimates and adapts the clipping threshold without extra privacy costs or hyperparameter tuning, achieving a 6.6% accuracy improvement over existing approaches.
This paper introduces Test-Time Speculation (TTS), an online distillation method that continuously adapts a draft model during inference using the target model's verification signals, thereby overcoming the performance degradation of existing speculators on long sequences and significantly improving acceptance lengths.
This paper presents the construction of the Financial Annotated Dataset (FIAD), a Korean linguistic resource derived from banking app reviews and Local Grammar Graphs, which is used to generate annotated training data that significantly improves the performance of various NLU models in banking customer service dialog systems.
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.