Stay updated with the latest research and technology news
arXiv:2504.14158v2 Announce Type: replace Abstract: Refinement is a fundamental technique in the verification and systematic development of computer programs. It supports a disciplined approach to...
arXiv:2504.21730v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are vulnerable to backdoor attacks, where an attacker manipulates a small portion of the training data...
arXiv:2505.02819v4 Announce Type: replace Abstract: We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining...
arXiv:2505.08021v4 Announce Type: replace Abstract: Graph Neural Networks (GNNs) address two key challenges in applying deep learning to graph-structured data: they handle varying size input...
arXiv:2505.11235v3 Announce Type: replace Abstract: Driven by the rapid growth of model parameters, parameter-efficient fine-tuning (PEFT) has become essential for adapting large models to diverse...
arXiv:2505.11951v2 Announce Type: replace Abstract: This paper investigates a reach-avoid game between two players with damped double integrator dynamics. An optimal state-feedback strategy is derived...
arXiv:2505.12537v2 Announce Type: replace Abstract: Compact quadrupedal robots are proving increasingly suitable for deployment in real-world scenarios. Their smaller size fosters easy integration into human...
arXiv:2505.15547v3 Announce Type: replace Abstract: After a renaissance phase in which researchers revisited the message-passing paradigm through the lens of deep learning, the graph machine...
arXiv:2505.16723v3 Announce Type: replace Abstract: Most LLM fingerprinting methods teach the model to respond to a few fixed queries with predefined atypical responses (keys). This...
arXiv:2505.16928v3 Announce Type: replace Abstract: We introduce $\infty$-THOR, a new framework for long-horizon embodied tasks that advances long-context understanding in embodied AI. $\infty$-THOR provides: (1)...
arXiv:2505.17508v4 Announce Type: replace Abstract: Policy gradient algorithms have been successfully applied to enhance the reasoning capabilities of large language models (LLMs). KL regularization is...
arXiv:2505.17786v5 Announce Type: replace Abstract: Graph Contrastive Learning (GCL) is a powerful self-supervised learning framework that performs data augmentation through graph perturbations, with growing applications...
arXiv:2505.21862v3 Announce Type: replace Abstract: The scalability of current language-image pre-training for 3D medical imaging, such as CT and MRI, is constrained by the need...
arXiv:2506.02529v2 Announce Type: replace Abstract: Web applications are critical to modern software ecosystems, yet ensuring their reliability remains challenging due to the complexity and dynamic...
arXiv:2506.06968v2 Announce Type: replace Abstract: We present a dependently-typed cross-linguistic framework for analyzing the telicity and culminativity of events, accompanied by examples of using our...
arXiv:2506.07198v2 Announce Type: replace Abstract: Generating graphs with hierarchical structures remains a fundamental challenge due to the limitations of Euclidean geometry in capturing exponential complexity....
arXiv:2506.11373v2 Announce Type: replace Abstract: Deception is a common defense mechanism against adversaries with an information disadvantage. It can force such adversaries to select suboptimal...
arXiv:2506.11798v3 Announce Type: replace Abstract: Large Language Models (LLMs) display remarkable capabilities to understand or even produce political discourse but have been found to consistently...
arXiv:2506.12819v2 Announce Type: replace Abstract: Computationally cheap yet accurate dynamical models are a key requirement for real-time capable nonlinear optimization and model-based control. When given...
arXiv:2506.14518v4 Announce Type: replace Abstract: We study a two-player zero-sum game in which the row player aims to maximize their payoff against a competing column...
arXiv:2506.15733v2 Announce Type: replace Abstract: Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating...
arXiv:2506.16404v3 Announce Type: replace Abstract: Directed graphs naturally model systems with asymmetric, ordered relationships, essential to applications in biology, transportation, social networks, and visual understanding....
arXiv:2506.16777v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to generate summaries from clinical notes. However, their ability to preserve essential diagnostic...
arXiv:2506.20642v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex multi-hop questions, often falling...