arXiv:2510.00512v1 Announce Type: cross Abstract: The transcriptional response to genetic perturbation reveals fundamental insights into complex cellular systems. While current approaches have made progress in predicting genetic perturbation responses, they provide limited biological understanding and cannot systematically refine existing knowledge.…
arXiv:2510.00253v1 Announce Type: new Abstract: We introduce the coded-smoothing module, which can be seamlessly integrated into standard training pipelines, both supervised and unsupervised, to regularize learning and improve generalization with minimal computational overhead. In addition, it can be incorporated into…
arXiv:2510.00600v1 Announce Type: cross Abstract: Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful recipe for solving complex language tasks. In robotics, similar embodied CoT strategies, generating thoughts before actions,…
arXiv:2510.01169v1 Announce Type: cross Abstract: Data is vital in enabling machine learning models to advance research and practical applications in finance, where accurate and robust models are essential for investment and trading decision-making. However, real-world data is limited despite its…
The approach could enable autonomous vehicles, commercial aircraft, or transportation networks that are more reliable in the face of real-world unpredictability.
arXiv:2510.00845v1 Announce Type: cross Abstract: The development of trustworthy artificial intelligence requires moving beyond black-box performance metrics toward an understanding of models’ internal computations. Mechanistic Interpretability (MI) aims to meet this need by identifying the algorithmic mechanisms underlying model behaviors.…
arXiv:2510.01004v1 Announce Type: cross Abstract: Deep neural networks (DNNs) have achieved remarkable success across domains but remain difficult to interpret, limiting their trustworthiness in high-stakes applications. This paper focuses on deep vision models, for which a dominant line of explainability…
arXiv:2509.11149v2 Announce Type: replace-cross Abstract: Designing robust controllers for precise trajectory tracking with quadrotors is challenging due to nonlinear dynamics and underactuation, and becomes harder with flexible cable-suspended payloads that add degrees of freedom and hybrid dynamics. Classical model-based methods…
arXiv:2510.00023v1 Announce Type: new Abstract: Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted computational resources,…
arXiv:2509.26574v2 Announce Type: replace Abstract: While large language models (LLMs) with reasoning capabilities are progressing rapidly on high-school math competitions and coding, can they reason effectively through complex, open-ended challenges found in frontier physics research? And crucially, what kinds of…
