arXiv:2604.07492v1 Announce Type: cross Abstract: Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers. To increase the receptive field, Graph Transformers with global attention have been proposed; however, global attention does not take into account […]
TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
arXiv:2604.07894v1 Announce Type: cross Abstract: Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual’s needs and preferences. However, they still struggle with long-horizon tasks, such as tracking a user’s extensive history of conversations or activities. Existing memory mechanisms often fail to capture evolving behaviors, and RAG paradigms […]
The Weaponization of Computer Vision: Tracing Military-Surveillance Ties through Conference Sponsorship
arXiv:2604.07803v1 Announce Type: cross Abstract: Computer vision, a core domain of artificial intelligence (AI), is the field that enables the computational analysis, understanding, and generation of visual data. Despite being historically rooted in military funding and increasingly deployed in warfare, the field tends to position itself as a neutral, purely technical endeavor, failing to engage […]
Optimal Decay Spectra for Linear Recurrences
arXiv:2604.07658v1 Announce Type: cross Abstract: Linear recurrent models offer linear-time sequence processing but often suffer from suboptimal long-range memory. We trace this to the decay spectrum: for $N$ channels, random initialization collapses the minimum spectral gap to $O(N^-2)$, yielding sub-exponential error $exp(-Omega(N/log N))$; linear spacing avoids collapse but degrades to $exp(-O(N/sqrtT))$, practically algebraic over long […]
MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models
arXiv:2604.07752v1 Announce Type: cross Abstract: Modern video games are complex, non-deterministic systems that are difficult to test automatically at scale. Although prior work shows that personality-driven Large Language Model (LLM) agents can improve behavioural diversity and test coverage, existing tools largely remain research prototypes and lack cross-game reusability. This tool paper presents MIMIC-Py, a Python-based […]
ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
arXiv:2604.07851v1 Announce Type: cross Abstract: With the rise of LLMs, there is an increasing need for intelligent recommendation assistants that can handle complex queries and provide personalized, reasoning-driven recommendations. LLM-based recommenders show potential but face challenges in multi-step reasoning, underscoring the need for reasoning-augmented systems. To address this gap, we propose ReRec, a novel reinforcement […]
Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation
arXiv:2604.07945v1 Announce Type: cross Abstract: As the demand for mobile robots continues to increase, social navigation has emerged as a critical task, driving active research into deep reinforcement learning (RL) approaches. However, because pedestrian dynamics and social conventions vary widely across different regions, simulations cannot easily encompass all possible real-world scenarios. Real-world RL, in which […]
When Switching Algorithms Helps: A Theoretical Study of Online Algorithm Selection
arXiv:2604.07473v1 Announce Type: cross Abstract: Online algorithm selection (OAS) aims to adapt the optimization process to changes in the fitness landscape and is expected to outperform any single algorithm from a given portfolio. Although this expectation is supported by numerous empirical studies, there are currently no theoretical results proving that OAS can yield asymptotic speedups […]
The Shrinking Lifespan of LLMs in Science
arXiv:2604.07530v1 Announce Type: cross Abstract: Scaling laws describe how language model capabilities grow with compute and data, but say nothing about how long a model matters once released. We provide the first large-scale empirical account of how scientists adopt and abandon language models over time. We track 62 LLMs across over 108k citing papers (2018-2025), […]
Fast and Interpretable Protein Substructure Alignment via Optimal Transport
arXiv:2510.11752v2 Announce Type: replace Abstract: Proteins are essential biological macromolecules that execute life functions. Local structural motifs, such as active sites, are the most critical components for linking structure to function and are key to understanding protein evolution and enabling protein engineering. Existing computational methods struggle to identify and compare these local structures, which leaves […]
Learning is Forgetting: LLM Training As Lossy Compression
arXiv:2604.07569v1 Announce Type: cross Abstract: Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to learning in humans. We argue LLMs are best seen as an instance of […]
Agentic Copyright, Data Scraping & AI Governance: Toward a Coasean Bargain in the Era of Artificial Intelligence
arXiv:2604.07546v1 Announce Type: new Abstract: This paper examines how the rapid deployment of multi-agentic AI systems is reshaping the foundations of copyright law and creative markets. It argues that existing copyright frameworks are ill-equipped to govern AI agent-mediated interactions that occur at scale, speed, and with limited human oversight. The paper introduces the concept of […]