arXiv:2511.21923v1 Announce Type: new Abstract: Understanding how backdoor data influences neural network training dynamics remains a complex and underexplored challenge. In this paper, we present a rigorous analysis of the impact of backdoor data on the learning process, with a…
arXiv:2503.22738v2 Announce Type: replace Abstract: Autonomous agents powered by foundation models have seen widespread adoption across various real-world applications. However, they remain highly vulnerable to malicious instructions and attacks, which can result in severe consequences such as privacy breaches and…
arXiv:2511.21928v1 Announce Type: new Abstract: Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical feedback with language, prior…
arXiv:2506.07619v2 Announce Type: replace Abstract: Machine learning has promised to change the landscape of laboratory chemistry, with impressive results in molecular property prediction and reaction retro-synthesis. However, chemical datasets are often inaccessible to the machine learning community as they tend…
arXiv:2511.21931v1 Announce Type: new Abstract: In this work, we propose a simple and computationally efficient framework to evaluate whether machine learning models align with the structure of the data they learn from; that is, whether textit{the model says what the…
arXiv:2509.01886v2 Announce Type: replace Abstract: Rapid post-disaster road damage assessment is critical for effective emergency response, yet traditional optimization methods suffer from excessive computational time and require domain knowledge for algorithm design, making them unsuitable for time-sensitive disaster scenarios. This…
arXiv:2511.23224v1 Announce Type: cross Abstract: This article proposes a Graph Neural Network (GNN) approach to estimate nonstabilizerness in quantum circuits, measured by the stabilizer R’enyi entropy (SRE). Nonstabilizerness is a fundamental resource for quantum advantage, and efficient SRE estimations are…
arXiv:2501.01457v3 Announce Type: replace Abstract: While inference-time thinking allows Large Language Models (LLMs) to address complex problems, the extended thinking process can be unreliable or inconsistent because of the model’s probabilistic nature, especially near its knowledge boundaries. Existing approaches attempt…
arXiv:2511.20558v2 Announce Type: replace-cross Abstract: The abundance of fine-grained spatio-temporal data, such as traffic sensor networks, offers vast opportunities for scientific discovery. However, inferring causal relationships from such observational data remains challenging, particularly due to unobserved confounders that are specific…
arXiv:2511.22904v1 Announce Type: cross Abstract: To interact effectively with humans in the real world, it is important for agents to understand language that describes the dynamics of the environment–that is, how the environment behaves–rather than just task instructions specifying “what…
