Stay updated with the latest research and technology news
arXiv:2506.09016v3 Announce Type: replace Abstract: Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive...
arXiv:2506.09984v2 Announce Type: replace Abstract: End-to-end human animation with rich multi-modal conditions, e.g., text, image and audio has achieved remarkable advancements in recent years. However,...
arXiv:2506.14020v4 Announce Type: replace Abstract: Graph generation has emerged as a critical task in fields ranging from drug discovery to circuit design. Contemporary approaches, notably...
arXiv:2506.14067v3 Announce Type: replace Abstract: As interactive generative systems are increasingly deployed in real-world applications, their tendency to generate unreliable or false responses raises serious...
arXiv:2506.16112v3 Announce Type: replace Abstract: Inspired by text prompts in large language models, visual prompts have been explored to enhance the perceptual capabilities of large...
arXiv:2506.18339v3 Announce Type: replace Abstract: Understanding and modeling nonlinear dynamical systems is a fundamental challenge across science and engineering. Deep learning has shown remarkable potential...
arXiv:2506.18812v2 Announce Type: replace Abstract: Physics-informed deep learning has achieved remarkable progress by embedding geometric priors, such as Hamiltonian symmetries and variational principles, into neural...
arXiv:2506.23036v3 Announce Type: replace Abstract: This paper explores reinforcement learning (RL) policy robustness by systematically analyzing network parameters under internal and external stresses. \textcolor{black}{We apply...
arXiv:2506.23508v4 Announce Type: replace Abstract: Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt (multimodal) large language models...
arXiv:2507.00091v2 Announce Type: replace Abstract: We consider a coded distributed computing problem in a ring-based communication network, where $N$ computing nodes are arranged in a...
arXiv:2507.00677v2 Announce Type: replace Abstract: We present an imitation learning framework that extracts distinctive legged locomotion behaviors and transitions between them from unlabeled real-world motion...
arXiv:2507.01785v3 Announce Type: replace Abstract: Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on...
arXiv:2507.01853v5 Announce Type: replace Abstract: The rapid evolution of Large Language Models' has underscored the need for evaluation frameworks that are globally applicable, flexible, and...
arXiv:2507.07999v2 Announce Type: replace Abstract: Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no...
arXiv:2507.09264v2 Announce Type: replace Abstract: Transformer-based PDE surrogates achieve remarkable performance but face two key challenges: fixed patch sizes cause systematic error accumulation at harmonic...
arXiv:2507.10345v2 Announce Type: replace Abstract: This paper examines the $L_p$ and $W^1_p$ norm approximation errors of ReLU neural networks for Korobov functions. In terms of...
arXiv:2507.12742v3 Announce Type: replace Abstract: We verify quasi-optimality of the Crouzeix-Raviart FEM for nonlinear problems of $p$-Laplace type. More precisely, we show that the error...
arXiv:2507.14529v2 Announce Type: replace Abstract: We consider the maximum causal entropy inverse reinforcement learning (IRL) problem for infinite-horizon stationary mean-field games (MFG), in which we...
arXiv:2507.16810v4 Announce Type: replace Abstract: We consider an inverse initial-data problem for the compressible anisotropic Navier--Stokes equations, in which the goal is to reconstruct the...
arXiv:2507.18534v2 Announce Type: replace Abstract: Although EDM aims to unify the design space of diffusion models, its reliance on fixed Gaussian noise prevents it from...
arXiv:2508.02338v2 Announce Type: replace Abstract: PAL Robotics, in Spain, builds a variety of Autonomous Mobile Robots (AMRs), which are deployed in diverse environments (e.g., warehouses,...
arXiv:2508.02464v2 Announce Type: replace Abstract: Foundation models have shown strong performance in multi-object segmentation with visual prompts, yet histopathology images remain challenging due to high...
arXiv:2508.02833v3 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO), recently introduced by DeepSeek, is a critic-free reinforcement learning algorithm for fine-tuning large language models....
arXiv:2508.04112v2 Announce Type: replace Abstract: We prove the convergence of hyperbolic approximations for several classes of higher-order PDEs, including the Benjamin-Bona-Mahony, Korteweg-de Vries, Gardner, Kawahara,...