Stay updated with the latest research and technology news
arXiv:2602.11835v1 Announce Type: new Abstract: We consider the problem of finding a Nash equilibrium (NE) in a general-sum game, where player $i$'s objective is $f_i(x)=f_i(x_1,...,x_n)$,...
arXiv:2602.11832v1 Announce Type: new Abstract: Recent vision-language-action (VLA) models built upon pretrained vision-language models (VLMs) have achieved significant improvements in robotic manipulation. However, current VLAs...
arXiv:2602.11829v1 Announce Type: new Abstract: Addressing climate change requires global coordination, yet rational economic actors often prioritize immediate gains over collective welfare, resulting in social...
arXiv:2602.11826v1 Announce Type: new Abstract: This paper introduces a framework for combinatorial variants of perpetual-scheduling problems. Given a set system $(E,\mathcal{I})$, a schedule consists of...
arXiv:2602.11825v1 Announce Type: new Abstract: Quantifying the impacts of air pollution on health and climate relies on key atmospheric particle properties such as toxicity and...
arXiv:2602.11824v1 Announce Type: new Abstract: Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual...
arXiv:2602.11822v1 Announce Type: new Abstract: This paper investigates the non-trivial consensus problem on directed signed matrix-weighted networks\textemdash a novel convergence state that has remained largely...
arXiv:2602.11820v1 Announce Type: new Abstract: The Open Radio Access Network (O-RAN) offers flexibility and innovation but introduces unique security vulnerabilities, particularly from cryptographically relevant quantum...
arXiv:2602.11814v1 Announce Type: new Abstract: Maximum-a-posteriori (MAP) approaches are an effective framework for inverse problems with known forward operators, particularly when combined with expressive priors...
arXiv:2602.11812v1 Announce Type: new Abstract: The long-tailed distribution of sequence lengths in LLM serving and reinforcement learning (RL) sampling causes significant computational waste due to...
arXiv:2602.11810v1 Announce Type: new Abstract: Synthetic datasets are being recognized in the deep learning realm as a valuable alternative to exhaustively labeled real data. One...
arXiv:2602.11808v1 Announce Type: new Abstract: Agentic LLM inference with long contexts is increasingly limited by memory bandwidth rather than compute. In this setting, SwiGLU MLP...
arXiv:2602.11807v1 Announce Type: new Abstract: Latent diffusion models (LDMs) suffer from limited diffusability in high-resolution (
arXiv:2602.11805v1 Announce Type: new Abstract: Path signatures embed trajectories into tensor algebra and constitute a universal, non-parametric representation of paths; however, in the standard form,...
arXiv:2602.11804v1 Announce Type: new Abstract: Segment Anything Models (SAM) achieve impressive universal segmentation performance but require massive datasets (e.g., 11M images) and rely solely on...
arXiv:2602.11802v1 Announce Type: new Abstract: Graph link prediction (LP) plays a critical role in socially impactful applications, such as job recommendation and friendship formation. Ensuring...
arXiv:2602.11801v1 Announce Type: new Abstract: Accurate localization of the seizure onset zone (SOZ) from intracranial EEG (iEEG) is essential for epilepsy surgery but is challenged...
arXiv:2602.11800v1 Announce Type: new Abstract: Recently, there have been numerous attempts to enhance the sample efficiency of off-policy reinforcement learning (RL) agents when interacting with...
arXiv:2602.11799v1 Announce Type: new Abstract: Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discretize this...
arXiv:2602.11798v1 Announce Type: new Abstract: Next-generation communication networks are characterized by integrated ultra-high reliability, ultra-low latency, massive connectivity, and ubiquitous coverage. However, this paradigm faces...
arXiv:2602.11795v1 Announce Type: new Abstract: This paper presents an embedding-based approach to detecting variation without relying on prior normalisation or predefined variant lists. The method...
arXiv:2602.11794v1 Announce Type: new Abstract: We study the problem of learning the law of linear stochastic partial differential equations (SPDEs) with additive Gaussian forcing from...
arXiv:2602.11793v1 Announce Type: new Abstract: Watermarking has emerged as a crucial technique for detecting and attributing content generated by large language models. While recent advancements...
arXiv:2602.11792v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is central to training modern reasoning models, but the undisclosed training data raises concerns...