arXiv:2602.22261v1 Announce Type: new Abstract: Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference strategy where most systems route every request to the same large model, regardless of task complexity, leading to substantial and unnecessary energy waste. To address this issue, we propose a context-aware model switching approach that dynamically selects an appropriate language […]

Ver mais

Google AI Research team recently released Groundsource, a new methodology that uses Gemini model to extract structured historical data from unstructured public news reports. The project addresses the lack of historical data for rapid-onset natural disasters. Its first output is an open-source dataset containing 2.6 million historical urban flash flood events across more than 150 countries. The Hydro-Meteorological Data Gap Machine learning models for early warning systems (EWS) require extensive historical baselines for training and validation. However, hydro-meteorological […]

Ver mais

Post-training algorithms based on deep reinforcement learning can push the limits of robotic models for specific objectives, such as generalizability, accuracy, and robustness. However, Intervention-requiring Failures (IR Failures) (e.g., a robot spilling water or breaking fragile glass) during real-world exploration happen inevitably, hindering the practical deployment of such a paradigm. To tackle this, we introduce Failure-Aware Offline-to-Online Reinforcement Learning (FARL), a new paradigm minimizing failures during real-world reinforcement learning. We create FailureBench, a benchmark that incorporates common failure […]

Ver mais

arXiv:2603.02224v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for adapting large pre-trained models, yet its behavior under continual learning remains poorly understood. We present a geometric theory characterizing catastrophic forgetting in LoRA through the lens of gradient subspace interactions. Our central finding is that forgetting is governed by a simple geometric law: $mathcal{F} = alpha(1 – cos^2theta_{min}) + beta$, where $theta_{min}$ is the minimum principal angle between task gradient subspaces. This formulation […]

Ver mais

Research: SQLite WAL Mode Across Docker Containers Sharing a Volume Inspired by this conversation on Hacker News about whether two SQLite processes in separate Docker containers that share the same volume might run into problems due to WAL shared memory. The answer is that everything works fine – Docker containers on the same host and filesystem share the same shared memory in a way that allows WAL to collaborate as it should. Tags: docker, sqlite

Ver mais

Offline safe reinforcement learning (RL) aims to learn policies from a fixed dataset while maximizing performance under cumulative cost constraints. In practice, deployment requirements often vary across scenarios, necessitating a single policy that can adapt zero-shot to different cost thresholds. However, most existing offline safe RL methods are trained under a pre-specified threshold, yielding policies with limited generalization and deployment flexibility across cost thresholds. Motivated by recent progress in conditional sequence modeling (CSM), which enables flexible goal-conditioned control […]

Ver mais

arXiv:2603.12368v1 Announce Type: new Abstract: Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers directly for a given query. While this paradigm shows promise in retrieval tasks, existing GR models struggle with complex queries in numerical contexts, such as those involving semantic reasoning over financial reports, due to limited reasoning capabilities. This limitation leads to suboptimal retrieval accuracy and hinders practical applicability. We propose ReasonGR, a framework designed to enhance multi-step semantic […]

Ver mais

Most teams chasing 100% code coverage are optimizing for a number, not for quality. Here’s why that obsession is actively making your software worse. Quick Answer Is 100% test coverage bad? No. Is chasing 100% test coverage bad? Almost always yes. Coverage tells you which lines of code executed during tests. It says nothing about whether your tests validate the right behavior, handle edge cases, or catch regressions. A codebase with 70% meaningful coverage will outperform one with 100% shallow […]

Ver mais

arXiv:2602.15962v1 Announce Type: new Abstract: Holstein-Friesian detection and re-identification (Re-ID) methods capture individuals well when targets are spatially separate. However, existing approaches, including YOLO-based species detection, break down when cows group closely together. This is particularly prevalent for species which have outline-breaking coat patterns. To boost both effectiveness and transferability in this setting, we propose a new detect-segment-identify pipeline that leverages the Open-Vocabulary Weight-free Localisation and the Segment Anything models as pre-processing stages alongside Re-ID networks. To evaluate […]

Ver mais

arXiv:2603.05689v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description language (HDL) datasets. This knowledge gap constrains LLM performance in detecting vulnerabilities within HDL designs. To address this challenge, we propose SecureRAG-RTL, a novel Retrieval-Augmented Generation (RAG)-based approach that significantly enhances LLM-based security verification of hardware designs. Our approach integrates domain-specific retrieval with […]

Ver mais