I’ve been working on a reinforcement learning project around the original Prince of Persia (1989) using SDLPoP. Instead of using raw pixels, I built a grid-based observation directly from the game state. Each room becomes a small multi-channel grid showing platforms, hazards, gates, exits, items, and character positions. The idea is to reduce the CNN’s burden of trying to understand interactable platforms and hazards from just a few pixels and instead give structured spatial information. On the action […]

Ver mais

I am not a NLP guy, but afaik ACL is one of the premium venues of NLP. And given that the results were announced recently, my LinkedIn and Twitter are full of such posts. However, every title I read in those posts has something to do with benchmarks. And even it seems, the young researchers also have like 10+ papers (main + findings) at a single venue. So was just wondering if ACL is majorly about benchmarks now, […]

Ver mais

arXiv:2510.12416v5 Announce Type: replace Abstract: This paper studies how geopolitical and geoeconomic shocks transmit to sovereign risk. Using a daily panel of CDS spreads, financial variables, and news-based indicators for 42 advanced and emerging economies over 2018-2025, we estimate nonlinear Machine Learning models that capture the interactions and threshold effects through which these shocks operate. A Shapley-Taylor decomposition exactly partitions predicted spreads into four channels: Direct, Global Financial Cycle, Uncertainty, and Local. The decomposition reveals a structural distinction. […]

Ver mais

Multi-Asset Momentum: Diversification Drives Activity on SIFX Global retail trading activity continues to evolve, with traders increasingly shifting from single-market exposure toward diversified, cross-asset strategies. In this environment, SIFX has reported measurable growth in multi-asset trading activity across its platform, reflecting broader market trends seen throughout 2026. According to platform data, users are engaging more actively across forex, commodities, cryptocurrencies, and equity-linked CFDs rather than concentrating on a single asset class. This diversification pattern suggests a maturing user […]

Ver mais

arXiv:2602.20229v1 Announce Type: new Abstract: Multi-agent systems (MAS) built on large language models (LLMs) have shown strong performance across many tasks. Most existing approaches improve only one aspect at a time, such as the communication topology, role assignment, or LLM routing, while treating each agent as a single, indivisible unit. This misses the opportunity to use mixtures of LLMs within an agent to strengthen role-specific abilities. We propose HieraMAS, a hierarchical collaboration framework that combines intra-node LLM mixtures […]

Ver mais

arXiv:2602.06164v1 Announce Type: new Abstract: People differ in how much they move their head versus their eyes when shifting gaze, yet such tendencies remain largely unexplored in HCI. We introduce head movement tendencies as a fundamental dimension of individual difference in VR and provide a quantitative account of their population-level distribution. Using a 360{deg} video free-viewing dataset (N=87), we model head contributions to gaze shifts with a hinge-based parametric function, revealing a spectrum of strategies from eye-movers to […]

Ver mais

arXiv:2602.23410v1 Announce Type: new Abstract: Brain foundation models have achieved remarkable advances across a wide range of neuroscience tasks. However, most existing models are limited to a single functional modality, restricting their ability to exploit complementary spatiotemporal dynamics and the collective data scale across imaging techniques. To address this limitation, we propose Brain-OF, the first omnifunctional brain foundation model jointly pretrained on fMRI, EEG and MEG, capable of handling both unimodal and multimodal inputs within a unified framework. […]

Ver mais

arXiv:2603.06654v1 Announce Type: new Abstract: The increasing incidence of IoT-based botnet attacks has driven interest in advanced learning models for detection. Recent efforts have focused on leveraging attention mechanisms to model long-range feature dependencies and Graph Neural Networks (GNNs) to capture relationships between data instances. Since GNNs require graph-structured input, tabular NetFlow data must be transformed accordingly. This study evaluates how the choice of the method for constructing the graph-structured dataset impacts the classification performance of a GNN […]

Ver mais