✓ Reviewed

Author-Reviewed Papers

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 · 41–50 / 438

The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth

This paper introduces the Concept Allocation Zone (CAZ), a framework that redefines concept formation in transformer models as a depth-extended process occurring across a contiguous region of the residual stream rather than at a single "best" layer, utilizing new metrics to identify these zones and revealing that many concepts reside in subtle, multimodal allocation regions that are causally active yet invisible to standard peak detection methods.

James Henry2026-05-26✓ Author reviewed ⓘ🤖 cs.LG

Forgotten Words: Benchmarking NeoBERT for Dementia Detection in Low-Resource Conversational Filipino and English Speech

This paper presents the first systematic evaluation of transformer-based dementia detection in Filipino-English code-switched speech, demonstrating that while monolingual models fail to generalize across languages, bilingual fine-tuning effectively eliminates cross-lingual performance degradation and achieves high accuracy regardless of model architecture.

Rez Samantha Z. Floresca, Edric Castel C. Hao, Hannah Grachiella Buñales, Chelsea Dominique E. Temprosa, Georgianna Z. Reyes, Kervin Gabriel L. Chua2026-05-26✓ Author reviewed ⓘ💬 cs.CL

Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning

This paper introduces orthogonal bottlenecks, a lightweight, architecture-agnostic mechanism that constrains reinforcement learning representations to low-dimensional subspaces via fixed orthonormal projections, demonstrating both theoretically and empirically that task-relevant value functions can be preserved and often improved upon with minimal dimensionality while stabilizing feature geometry.

Aleksandar Todorov, Matthia Sabatelli2026-05-26✓ Author reviewed ⓘ🤖 cs.LG

Geometric Workspace Analysis and Transmission-Aware Dynamics of a Serial Spherical Tool for Microsurgery

This paper presents a kinematic and transmission-aware design framework for a serial spherical microsurgical tool, featuring an analytical workspace formulation and a dynamics-informed methodology for self-locking transmissions, which are validated through experiments on a purpose-built robotic system for vitreoretinal surgery.

Anestis Mablekos-Alexiou, Lyndon da Cruz, Christos Bergeles2026-05-26✓ Author reviewed ⓘ💻 cs

Cross-Domain Generalization Limits of Vision Foundation Models in Facial Deepfake Detection

This paper systematically evaluates the cross-domain generalization limits of Vision Foundation Models in facial deepfake detection, revealing that while these models excel at identifying full-face synthesis, they struggle with localized editing techniques due to inherent trade-offs between pre-training paradigms and linear probe evaluation structures.

Ibrahim Delibasoglu2026-05-26✓ Author reviewed ⓘ🤖 cs.AI

Scaling up Energy-Aware Multi-Agent Reinforcement Learning for Mission-Oriented Drone Networks with Individual Reward

This paper proposes an energy-aware Multi-Agent Reinforcement Learning model utilizing Deep Q-Networks with individual reward functions to enhance the robustness, energy efficiency, and success rate of mission-oriented drone networks, particularly when scaling up environment size and agent numbers compared to traditional shared reward approaches.

Changling Li, Ying Li2026-05-26✓ Author reviewed ⓘ🤖 cs.AI

Hedging Options on Asset Portfolios against Just One Underlying Asset in the Presence of Transaction Costs

This study investigates the optimal hedging strategy for options on a two-asset portfolio when transaction costs are present, demonstrating through simulation that hedging with a correlated but non-underlying asset can be preferable to hedging with the correct asset if the correlation is sufficiently high and transaction costs are low, as determined by risk-adjusted value metrics.

Erina Nanyonga, Matt Davison2026-05-26✓ Author reviewed ⓘ💰 q-fin

Excitonic optical interface for GHz-THz collective excitations in a van der Waals magnet

This study demonstrates that excitonic resonances in the van der Waals antiferromagnet CrSBr serve as a unified broadband optical interface for GHz magnon and THz phonon collective excitations by transiently activating a nominally dark exciton through boson-driven modulation of the dielectric response.

Sophie Bork, Richard Leven, Vincent Wirsdörfer, Alessandro Ferretti, Rafael R. Rojas-Lopez, Mattia Benini, David Maximilian Janas, Umut Parlak, Alberto Brambilla, Alexey V. Scherbakov, Swagata Acharya (…)2026-05-25✓ Author reviewed ⓘ🔬 cond-mat.mtrl-sci

Superrotation and Jet Migration in Simulations of Jupiter's Convective Zone and Weather Layer

By implementing 3D anelastic convection simulations of Jupiter that isolate or couple the deep convective zone with a shallow weather layer, the study reveals that Busse columns drive equatorial superrotation while potential vorticity homogenization generates high-latitude jets that slowly migrate poleward, with the weather layer significantly altering thermal wind balance and jet alignment.

Loren Matilsky, Geoffrey Vallis, Matthew Browning, Nicholas Brummell2026-05-25✓ Author reviewed ⓘ🔭 astro-ph