digitado

Autonomous vehicles (AVs) rely on accurate trajectory prediction for safe navigation in diverse traffic environments, yet existing models struggle with long-tail scenarios-rare but safety-critical events characterized by abrupt maneuvers, high collision risks, and complex interactions. These challenges stem from data imbalance, inadequate definitions of long-tail trajectories, and suboptimal learning strategies that prioritize common behaviors over infrequent ones. To address this, we propose SAIL, a novel framework that systematically tackles the long-tail problem by first defining and modeling trajectories […]

Ver mais

AI systems are starting to move beyond simple responses. In many organisations, AI agents are now being tested to plan tasks, make decisions, and carry out actions with limited human input. It is no longer just about whether a model gives the right answer. It is about what happens when that model is allowed to act. Autonomous systems need clear boundaries. They need rules that define what they can access, what they are allowed to do, and how […]

Ver mais

Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly distributed on-policy data limits accurate policy evaluation in high-dimensional state and action spaces. Off-policy methods can overcome this limitation by learning from a broader state-action distribution, yet suffer from slow convergence and instability, as fitting a value function over diverse data requires many gradient […]

Ver mais

Where are the engineering productivity and velocity gains we were promised with AI coding tools? AI tools assist in writing half of Google’s code. Microsoft is not far behind at 30%. With so many more lines of code generated by AI, you may wonder: where are the massive engineering productivity improvements? Where are the spades of new features being delivered? Consider this: shovelware apps have not exploded since coding tools emerged. They’ve actually declined. In fact, there’s a growing […]

Ver mais

The self-attention mechanism has revolutionized sequence modeling but suffers from quadratic computational complexity with respect to sequence length, limiting its applicability to long sequences. We propose Sparse Projection Attention (SPA), a novel attention variant that leverages learnable sparse projections to reduce the effective dimensionality of queries and keys while maintaining expressive power. Our method is grounded in the Johnson-Lindenstrauss lemma and provides theoretical guarantees on distance preservation. We introduce a comprehensive mathematical framework including error bounds, convergence analysis, […]

Ver mais

Modern machine learning systems, such as generative models and recommendation systems, often evolve through a cycle of deployment, user interaction, and periodic model updates. This differs from standard supervised learning frameworks, which focus on loss or regret minimization over a fixed sequence of prediction tasks. Motivated by this setting, we revisit the classical model of learning from equivalence queries, introduced by Angluin (1988). In this model, a learner repeatedly proposes hypotheses and, when a deployed hypothesis is inadequate, […]

Ver mais

User interests typically encompass both long-term preferences and short-term intentions, reflecting the dynamic nature of user behaviors across different timeframes. The uneven temporal distribution of user interactions highlights the evolving patterns of interests, making it challenging to accurately capture shifts in interests using comprehensive historical behaviors. To address this, we propose SLSRec, a novel Session-based model with the fusion of Long- and Short-term Recommendations that effectively captures the temporal dynamics of user interests by segmenting historical behaviors over […]

Ver mais

We study the problem of constructing group-invariant embeddings that faithfully represent data modulo group symmetries, a task that arises naturally in signal processing, physics, and machine learning. A central challenge is to design embeddings that are simultaneously orbit-separating, stable, and computationally tractable. To address this, we develop a general lifting framework for constructing such embeddings. The key idea is to start from a group-invariant embedding defined on a low-dimensional reduced space, and lift it to the ambient space […]

Ver mais

Deep Neural Networks (DNNs) are increasingly utilized in high-stakes domains like medical diagnostics and autonomous driving where model reliability is critical. However, the research landscape for ensuring this reliability is terminologically fractured across communities that pursue the same goal of ensuring models rely on causally relevant features rather than confounding signals. While frameworks such as distributionally robust optimization (DRO), invariant risk minimization (IRM), shortcut learning, simplicity bias, and the Clever Hans effect all address model failure due to […]

Ver mais