arXiv:2501.00382v3 Announce Type: replace-cross Abstract: This paper advances empirical demand analysis by integrating multimodal product representations derived from artificial intelligence (AI). Using a detailed dataset of toy cars on textit{Amazon.com}, we combine text descriptions, images, and tabular covariates to represent each product using transformer-based embedding models. These embeddings capture nuanced attributes, such as quality, branding, and visual characteristics, that traditional methods often struggle to summarize. Moreover, we fine-tune these embeddings for causal inference tasks. We show that the […]

Ver mais

Some people love meetings—they can jump the entire day from one meeting to the next, believing all of them are important. There’s another group of people who absolutely hate meetings—they avoid meetings, express their disdain when they do have to attend one, and consider them a complete waste of time. Then there are people in the middle who neither love nor hate them—they understand that some meetings are necessary to resolve conflicts, avoid confusion, and seek alignment. They […]

Ver mais

… and I’d love to talk to people about it. I don’t want to just spam links, but I have them if anyone is interested. I’ve done three cool things that I would like to share and get opinions on. – a dense integer only neural network. It fits in l1 cache in most uses and so I have NPCs with little brains that learn. – a demo I’ve been sharing of an NPC solving logic puzzles through […]

Ver mais

Urban bus transit agencies need reliable, network-wide delay predictions to provide accurate arrival information to passengers and support real-time operational control. Accurate predictions help passengers plan their trips, reduce waiting time, and allow operations staff to adjust headways, dispatch extra vehicles, and manage disruptions. Although real-time feeds such as GTFS-Realtime (GTFS-RT) are now widely available, most existing delay prediction systems handle only a few routes, depend on hand-crafted features, and offer little guidance on how to design a […]

Ver mais

arXiv:2603.04323v1 Announce Type: cross Abstract: Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions degrade aggregation quality. We introduce PTOPOFL, a framework that addresses both challenges simultaneously by replacing gradient communication with topological descriptors derived from persistent homology (PH). Clients transmit only 48-dimensional PH feature vectors-compact shape summaries whose many-to-one structure makes inversion provably ill-posed-rather than model gradients. The server performs topology-guided personalised aggregation: clients are clustered by Wasserstein similarity between […]

Ver mais

arXiv:2603.00586v1 Announce Type: new Abstract: Production-ready human video generation requires digital actors to maintain strictly consistent full-body identities across dynamic shots, viewpoints and motions, a setting that remains challenging for existing methods. Prior methods often suffer from face-centric behavior that neglects body-level consistency, or produce copy-paste artifacts where subjects appear rigid due to pose locking. We present Actor-18M, a large-scale human video dataset designed to capture identity consistency under unconstrained viewpoints and environments. Actor-18M comprises 1.6M videos with […]

Ver mais

Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second […]

Ver mais

arXiv:2601.14333v1 Announce Type: new Abstract: Contextual Bandit (CB) algorithms are widely adopted for personalized recommendations but often struggle in dynamic environments typical of fantasy sports, where rapid changes in user behavior and dramatic shifts in reward distributions due to external influences necessitate frequent retraining. To address these challenges, we propose a Hierarchical Contextual Uplift Bandit framework. Our framework dynamically adjusts contextual granularity from broad, system-wide insights to detailed, user-specific contexts, using contextual similarity to facilitate effective policy transfer […]

Ver mais