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 · 681–690 / 984
This paper reveals that while KV cache compression improves throughput, it can severely degrade performance in multi-instruction scenarios by causing specific instructions to be ignored and system prompts to leak, but proposes simple eviction policy adjustments to mitigate these issues.
The paper presents SuperADD, a training-free, class-agnostic anomaly segmentation pipeline that leverages a DINOv3 backbone and robust preprocessing techniques to achieve state-of-the-art performance on the MVTec AD 2 dataset under challenging distribution shifts without requiring per-class hyperparameter tuning.
This paper argues that securing LLM-based AI agents requires applying operating system security principles, demonstrating through a unified architecture analysis and case study that while some risks are inherent, many vulnerabilities can be mitigated using established OS techniques like resource isolation and privilege separation.
This paper demonstrates that in the weak coupling regime of the IKKT model, quantum fluctuations are negligible compared to noncommutativity scales, thereby validating the emergence of semi-classical 3+1-dimensional geometry and gravity from specific matrix vacua.
The paper argues that while a finite-dimensional quantum model of de Sitter space is inherently ambiguous due to measurement limitations, a precise mathematical description of our universe might still be achievable if it can be embedded within a sequence of models converging to a unique superstring theory in asymptotically flat space.
The paper introduces Chem-GMNet, a novel sphere-native geometric transformer that replaces standard transformer modules with spherical counterparts to achieve state-of-the-art molecular property prediction performance on MoleculeNet benchmarks, often outperforming large-scale pretrained SMILES-based models with significantly fewer parameters and no pretraining.
This paper introduces the modified Lidov integral () as a reliable diagnostic tool to identify von Zeipel--Lidov--Kozai resonance in irregular satellites of giant planets, a method validated by -body simulations that successfully confirmed 26 out of 27 predicted resonant candidates.
The paper introduces VERA-MH, a clinically validated framework that evaluates the safety of AI chatbots in mental health contexts—specifically regarding suicidal ideation—by simulating diverse user interactions with role-playing agents and assessing responses using a structured, clinical rubric.
This study presents a combined photometric and spectroscopic analysis of four solar-type twin detached eclipsing binaries, revealing significant diversity in their evolutionary stages and magnetic activity levels despite their nearly equal masses, while also identifying a potential tertiary companion in one system.
This paper benchmarks agentic AI's ability to automate the reuse of fragmented neuroscience data by testing its performance on loading, understanding, and reformatting datasets from eight recent studies, revealing that while agents excel at individual sub-tasks, they currently struggle to produce fully error-free end-to-end solutions and require human-in-the-loop oversight.