Stay updated with the latest research and technology news
arXiv:2509.15370v4 Announce Type: replace Abstract: Unfolding networks are interpretable networks emerging from iterative algorithms, incorporate prior knowledge of data structure, and are designed to solve...
arXiv:2509.15724v4 Announce Type: replace Abstract: Large deep learning models such as BERT and ResNet achieve state-of-the-art performance but are costly to deploy at the edge...
arXiv:2509.15735v4 Announce Type: replace Abstract: Large language models (LLMs) offer broad utility but remain prone to hallucination and out-of-distribution (OOD) errors. We propose EigenTrack, an...
arXiv:2509.15867v2 Announce Type: replace Abstract: This paper investigates how large language models (LLMs) are reshaping competitive programming. The field functions as an intellectual contest within...
arXiv:2509.15953v2 Announce Type: replace Abstract: Turning garments right-side out is a challenging manipulation task: it is highly dynamic, entails rapid contact changes, and is subject...
arXiv:2509.16461v2 Announce Type: replace Abstract: The aim of this work is to analyze the finite element approximation of the two-dimensional stationary Navier-Stokes equations with non-smooth...
arXiv:2509.16690v2 Announce Type: replace Abstract: In coded aperture snapshot spectral imaging (CASSI), the captured measurement entangles spatial and spectral information, posing a severely ill-posed inverse...
arXiv:2509.20624v4 Announce Type: replace Abstract: Autoregressive language models (ARMs) deliver strong likelihoods, but are inherently serial: they generate one token per forward pass, which limits...
arXiv:2509.20899v2 Announce Type: replace Abstract: Concept Bottleneck Models (CBMs) enable interpretable image classification by structuring predictions around human-understandable concepts, but extending this paradigm to video...
arXiv:2509.20975v2 Announce Type: replace Abstract: The goal of personalized medicine is to discover a treatment regimen that optimizes a patient's clinical outcome based on their...
arXiv:2509.21628v3 Announce Type: replace Abstract: Large vision models differ widely in architecture and training paradigm, yet we lack principled methods to determine which aspects of...
arXiv:2509.22277v2 Announce Type: replace Abstract: It is known that the online firefighting is 2-competitive on trees (Coupechoux et al. 2019), which suggests that the problem...
arXiv:2509.23023v2 Announce Type: replace Abstract: Mafia is a social deduction game where informed mafia compete against uninformed townsfolk. Its asymmetry of information and reliance on...
arXiv:2509.24291v2 Announce Type: replace Abstract: Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their...
arXiv:2510.00468v3 Announce Type: replace Abstract: We provide evidence that eigenanalysis of the empirical neural tangent kernel (eNTK) can surface the features used by trained neural...
arXiv:2510.02183v2 Announce Type: replace Abstract: In this paper, we investigate data-driven attack detection and identification in a model-free setting. We consider a practically motivated scenario...
arXiv:2510.03944v2 Announce Type: replace Abstract: Large language models (LLMs) raise concerns about content authenticity and integrity because they can generate human-like text at scale. Text...
arXiv:2510.04284v2 Announce Type: replace Abstract: The professionalism of a human doctor in outpatient service depends on two core abilities: the ability to make accurate medical...
arXiv:2510.04331v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning (PEFT) methods have become the standard paradigm for adapting large-scale models. Among these techniques, Weight-Decomposed Low-Rank Adaptation (DoRA)...
arXiv:2510.07210v2 Announce Type: replace Abstract: We present a novel hybrid learning-assisted planning method, named HyPlan, for solving the collision-free navigation problem for self-driving cars in...
arXiv:2510.07245v2 Announce Type: replace Abstract: We study the theoretical properties of the interactive learning protocol Discriminative Feature Feedback (DFF) (Dasgupta et al., 2018). The DFF...
arXiv:2510.08460v2 Announce Type: replace Abstract: Many researchers have reached the conclusion that AI models should be trained to be aware of the possibility of variation...
arXiv:2510.09311v2 Announce Type: replace Abstract: An extended regular expression $R$ specifies a set of strings formed by characters from an alphabet combined with concatenation, union,...
arXiv:2510.09796v2 Announce Type: replace Abstract: The training of deep neural networks predominantly relies on a combination of gradient-based optimisation and back-propagation for the computation of...