arXiv:2602.07047v1 Announce Type: new Abstract: Pixel-level feature attributions are an important tool in eXplainable AI for Computer Vision (XCV), providing visual insights into how image features influence model predictions. The Owen formula for hierarchical Shapley values has been widely used to interpret machine learning (ML) models and their learned representations. However, existing hierarchical Shapley approaches do not exploit the multiscale structure of image data, leading to slow convergence and weak alignment with the actual morphological features. Moreover, no […]

Ver mais

The Markup, now a part of CalMatters, uses investigative reporting, data analysis, and software engineering to challenge technology to serve the public good. Sign up for Klaxon, a newsletter that delivers our stories and tools directly to your inbox. If you opened Instagram last week, you may have seen one of many tutorials on how to opt out of a setting that was quietly released in February: Instagram and Threads users will no longer be recommended political content […]

Ver mais

This paper addresses complex decision-making scenarios characterized by high uncertainty and high-cost errors, researching a risk-sensitive decision-oriented reinforcement learning mining method. It focuses on resolving the reliability issues arising from tail instability in the reward distribution and out-of-distribution actions under offline data conditions. Methodologically, the decision-making process is modeled using a Markov framework, with the reward distribution as the learning object to retain value information under adverse conditions. Based on this, a conditional risk-value metric is introduced to […]

Ver mais

Google Antigravity Changes the Way Everyone Operates with Computers :::warning The world we knew—where you were the bottleneck, the typist, the clicker—is gone. ::: :::tip Imagine a reality where the laws of digital physics no longer apply. ::: A world where your computer isn’t just a reactive tool waiting for a keystroke, but a proactive partner that defies the gravity of mundane tasks. :::tip Welcome to Google Antigravity. ::: This isn’t just another chatbot wrapper or a fancy […]

Ver mais

Deep reinforcement learning (RL) suffers from plasticity loss severely due to the nature of non-stationarity, which impairs the ability to adapt to new data and learn continually. Unfortunately, our understanding of how plasticity loss arises, dissipates, and can be dissolved remains limited to empirical findings, leaving the theoretical end underexplored.To address this gap, we study the plasticity loss problem from the theoretical perspective of network optimization. By formally characterizing the two culprit factors in online RL process: the […]

Ver mais

arXiv:2604.05076v1 Announce Type: new Abstract: Music-grounded mashup video creation is a challenging form of video non-linear editing, where a system must compose a coherent timeline from large collections of source videos while aligning with music rhythm, user intent, story completeness, and long-range structural constraints. Existing approaches typically rely on fixed pipelines or simplified retrieval-and-concatenation paradigms, limiting their ability to adapt to diverse prompts and heterogeneous source materials. In this paper, we present GLANCE, a global-local coordination multi-agent framework […]

Ver mais

arXiv:2602.13287v1 Announce Type: new Abstract: Cooperative perception enables autonomous agents to share encoded representations over wireless communication to enhance each other’s live situational awareness. However, the tension between the limited communication bandwidth and the rich sensor information hinders its practical deployment. Recent studies have explored selection strategies that share only a subset of features per frame while striving to keep the performance on par. Nevertheless, the bandwidth requirement still stresses current wireless technologies. To fundamentally ease the tension, […]

Ver mais

arXiv:2604.15494v1 Announce Type: new Abstract: Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balancing high accuracy with inherent interpretability, which makes them suitable for critical domains such as healthcare. However, these models are limited by their reliance on training data, which hampers their robustness to distribution shifts. While test-time adaptation (TTA) improves the robustness of deep networks by updating parameters and statistics, the prototypes of interpretable models […]

Ver mais