Stay updated with the latest research and technology news
arXiv:2501.08219v4 Announce Type: replace Abstract: LLM inference exhibits substantial variability across queries and execution phases, yet inference configurations are often applied uniformly. We present a...
arXiv:2501.10538v2 Announce Type: replace Abstract: The practical success of deep learning has led to the discovery of several surprising phenomena. One of these phenomena, that...
arXiv:2501.16613v2 Announce Type: replace Abstract: This work introduces a toolchain for applying Reinforcement Learning (RL), specifically the Deep Deterministic Policy Gradient (DDPG) algorithm, in safety-critical...
arXiv:2502.01310v4 Announce Type: replace Abstract: Neural network-based optimal transport (OT) is a recent and fruitful direction in the generative modeling community. It finds its applications...
arXiv:2502.03652v2 Announce Type: replace Abstract: We consider the problem of differentially private (DP) convex empirical risk minimization (ERM). While the standard DP-SGD algorithm is theoretically...
arXiv:2502.05310v4 Announce Type: replace Abstract: Large Language Models can solve a wide range of tasks from just a few examples, but they remain difficult to...
arXiv:2502.12108v2 Announce Type: replace Abstract: Integrated Gradients (IG), a widely used axiomatic path-based attribution method, assigns importance scores to input features by integrating model gradients...
arXiv:2502.12600v3 Announce Type: replace Abstract: Generalization to unseen degradations remains a fundamental challenge for low-level vision models. This paper aims to investigate the underlying mechanism...
arXiv:2502.12927v3 Announce Type: replace Abstract: Providing high-quality feedback on student assignments is crucial for student success, but it is heavily limited by time and budgetary...
arXiv:2502.17028v3 Announce Type: replace Abstract: Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval. Previous multimodal approaches like CLIP utilize...
arXiv:2502.17364v2 Announce Type: replace Abstract: Natural Language Processing (NLP) is becoming a dominant subset of artificial intelligence as the need to help machines understand human...
arXiv:2502.18680v2 Announce Type: replace Abstract: GPGPU-accelerated clusters and supercomputers are central to modern high-performance computing (HPC). Over the past decade, these systems continue to expand,...
arXiv:2503.00229v4 Announce Type: replace Abstract: Armijo line-search (Armijo-LS) is a standard method to set the step-size for gradient descent (GD). For smooth functions, Armijo-LS alleviates...
arXiv:2503.01852v2 Announce Type: replace Abstract: Autonomous vehicles must negotiate with pedestrians in ways that are both safe and socially compliant. We present an interaction-aware model...
arXiv:2503.04398v4 Announce Type: replace Abstract: Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficiency of...
arXiv:2503.06437v2 Announce Type: replace Abstract: We present SEED (Semantic Evaluation for Visual Brain Decoding), a novel metric for evaluating the semantic decoding performance of visual...
arXiv:2503.09160v4 Announce Type: replace Abstract: We introduce \textit{WonderVerse}, a simple but effective framework for generating extendable 3D scenes. Unlike existing methods that rely on iterative...
arXiv:2503.10353v2 Announce Type: replace Abstract: The so-called algebraic approach to the constraint satisfaction problem (CSP) has been a prevalent method of the study of complexity...
arXiv:2503.10547v2 Announce Type: replace Abstract: While concept-based explanations improve interpretability over local attributions, they often rely on correlational signals and lack causal validation. We introduce...
arXiv:2503.12016v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated impressive success across various tasks. Integrating LLMs with Federated Learning (FL), a paradigm known...
arXiv:2503.12434v2 Announce Type: replace Abstract: With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential...
arXiv:2503.21852v4 Announce Type: replace Abstract: The synthesis of reactive systems aims for the automated construction of strategies for systems that interact with their environment. Whereas...
arXiv:2503.23434v2 Announce Type: replace Abstract: Graphical User Interface (GUI) agents extend large language models from text generation to action execution in real-world digital environments. Unlike...
arXiv:2504.03449v3 Announce Type: replace Abstract: We establish Sobolev-Poincar\'e inequalities for piecewise $W^{1,p}$ functions over families of fairly general polytopic (thence also shape-regular simplicial and Cartesian)...