technocracy

While clients may join federated learning to improve performance on data they rarely observe locally, they often remain self-interested, expecting the global model to perform well on their own data. This motivates an objective that ensures all clients achieve a similar loss gap -the difference in performance between the global model and the best model they could train using only their local data-. To this end, we propose EAGLE, a novel federated learning algorithm that explicitly regularizes the […]

Ver mais

You already sense it. The headlines talk about crypto rallies and AI breakthroughs, and part of you knows this is bigger than just news, it’s a shift that should include you. But the path feels lonely. Savings shrink, banks offer nothing, borders slow everything, and the tools that matter seem reserved for someone else. You want to participate, to build, to rise, but you want to do it with people who get it, who lift you as you […]

Ver mais

Large language models (LLMs) have transformed how we interact with AI, but one size doesn’t fit at all. Out-of-the-box LLMs are trained with broad, general knowledge and improved for a wide range of use cases, but they often fall short when it comes to domain-specific tasks, proprietary workflows, or unique business requirements. Enterprise customers increasingly need specialized LLMs that deeply understand their proprietary data, business processes, and domain-specific terminology. Without customization, you’re forced to choose between accepting generic […]

Ver mais

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio clipping mechanism in PPO is structurally ill-suited for the large vocabularies inherent to LLMs. PPO constrains policy updates based on the probability ratio of sampled tokens, which serves as a noisy single-sample Monte Carlo estimate of the true policy divergence. This creates a sub-optimal […]

Ver mais

arXiv:2602.01018v1 Announce Type: new Abstract: Hierarchical Imitation Learning is a powerful paradigm for acquiring complex robot behaviors from demonstrations. A central challenge, however, lies in discovering reusable skills from long-horizon, multi-task offline data, especially when the data lacks explicit rewards or subtask annotations. In this work, we introduce LOKI, a three-stage end-to-end learning framework designed for offline skill discovery and hierarchical imitation. The framework commences with a two-stage, weakly supervised skill discovery process: Stage one performs coarse, task-aware […]

Ver mais

arXiv:2602.16762v1 Announce Type: new Abstract: Modern machine learning-based wireless localization using Wi-Fi signals continues to face significant challenges in achieving groundbreaking performance across diverse environments. A major limitation is that most existing algorithms do not appropriately weight the information from different routers during aggregation, resulting in suboptimal convergence and reduced accuracy. Motivated by traditional weighted triangulation methods, this paper introduces the concept of attention to routers, ensuring that each router’s contribution is weighted differently when aggregating information from […]

Ver mais

been thinking about this after working around a few ML systems in production. a lot of focus goes into improving models — architecture, fine-tuning, evals — but it feels like less attention goes into how model outputs actually get used. in practice, the breakdown isn’t always model quality. it’s things like: high-signal outputs getting lost in streams of low-priority events predictions arriving after the window to act has already passed no clear routing of outputs to the right […]

Ver mais

arXiv:2603.25891v1 Announce Type: new Abstract: Pre-trained vision-language models (VLMs) excel in multimodal tasks, commonly encoding images as embedding vectors for storage in databases and retrieval via approximate nearest neighbor search (ANNS). However, these models struggle with compositional queries and out-of-distribution (OOD) image-text pairs. Inspired by human cognition’s ability to learn from minimal examples, we address this performance gap through few-shot learning approaches specifically designed for image retrieval. We introduce the Few-Shot Text-to-Image Retrieval (FSIR) task and its accompanying […]

Ver mais

arXiv:2602.04043v1 Announce Type: new Abstract: The growing demand for rapid and scalable 3D asset creation has driven interest in feed-forward 3D reconstruction methods, with 3D Gaussian Splatting (3DGS) emerging as an effective scene representation. While recent approaches have demonstrated pose-free reconstruction from unposed image collections, integrating stylization or appearance control into such pipelines remains underexplored. Existing attempts largely rely on image-based conditioning, which limits both controllability and flexibility. In this work, we introduce AnyStyle, a feed-forward 3D reconstruction […]

Ver mais

arXiv:2604.06333v1 Announce Type: new Abstract: Drifting models generate high-quality samples in a single forward pass by transporting generated samples toward the data distribution using a vector valued drift field. We investigate whether this procedure is equivalent to optimizing a scalar loss and find that, in general, it is not: drift fields are not conservative – they cannot be written as the gradient of any scalar potential. We identify the position-dependent normalization as the source of non-conservatism. The Gaussian […]

Ver mais