Stay updated with the latest research and technology news
arXiv:2602.03324v1 Announce Type: new Abstract: Route recommendation systems commonly adopt a multi-stage pipeline involving fine-ranking and re-ranking to produce high-quality ordered recommendations. However, this paradigm...
arXiv:2602.03327v1 Announce Type: new Abstract: Novel view synthesis has evolved rapidly, advancing from Neural Radiance Fields to 3D Gaussian Splatting (3DGS), which offers real-time rendering...
arXiv:2602.03328v1 Announce Type: new Abstract: We present GuardReasoner-Omni, a reasoning-based guardrail model designed to moderate text, image, and video data. First, we construct a comprehensive...
arXiv:2602.03329v1 Announce Type: new Abstract: Standard federated learning algorithms are vulnerable to adversarial nodes, a.k.a. Byzantine failures. To solve this issue, robust distributed learning algorithms...
arXiv:2602.03331v1 Announce Type: new Abstract: Bayesian posterior predictive densities as non-conformity scores and Bayesian quadrature are used to estimate and minimise the expected prediction set...
arXiv:2602.03333v1 Announce Type: new Abstract: Recent progress in adversarial attacks on 3D point clouds, particularly in achieving spatial imperceptibility and high attack performance, presents significant...
arXiv:2602.03334v1 Announce Type: new Abstract: This paper examines biases in large language models (LLMs) when generating synthetic populations from responses to personality questionnaires. Using five...
arXiv:2602.03337v1 Announce Type: new Abstract: In bioinformatics, minimizers have become an inescapable method for handling $k$-mers (words of fixed size $k$) extracted from DNA or...
arXiv:2602.03338v1 Announce Type: new Abstract: Proactive interventions by LLM critic models are often assumed to improve reliability, yet their effects at deployment time are poorly...
arXiv:2602.03339v1 Announce Type: new Abstract: We introduce CompTok, a training framework for learning visual tokenizers whose tokens are enhanced for compositionality. CompTok uses a token-conditioned...
arXiv:2602.03340v1 Announce Type: new Abstract: Mental health disorders represent a burgeoning global public health challenge. While Large Language Models (LLMs) have demonstrated potential in psychiatric...
arXiv:2602.03342v1 Announce Type: new Abstract: Text-conditioned diffusion models have advanced image and video super-resolution by using prompts as semantic priors, but modern super-resolution pipelines typically...
arXiv:2602.03344v1 Announce Type: new Abstract: Robustness is often regarded as a critical future challenge for real-world applications, where stability is essential. However, as models often...
arXiv:2602.03345v1 Announce Type: new Abstract: Ranking is central to information distribution in web search and recommendation. Nowadays, in ranking optimization, the fairness to item providers...
arXiv:2602.03346v1 Announce Type: new Abstract: Max-min-plus-scaling (MMPS) systems generalize max-plus, min-plus and max-min-plus models with more flexibility in modelling discrete-event dynamics. Especially, implicit MMPS models...
arXiv:2602.03348v1 Announce Type: new Abstract: This work provides a comparative assessment of several low-dissipation numerical schemes for hyperbolic conservation laws, highlighting their performance relative to...
arXiv:2602.03350v1 Announce Type: new Abstract: Efficient and robust trajectories play a crucial role in contact-rich manipulation, which demands accurate mod- eling of object-robot interactions. Many...
arXiv:2602.03351v1 Announce Type: new Abstract: We build a custom transformer model to study how neural networks make moral decisions on trolley-style dilemmas. The model processes...
arXiv:2602.03352v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown strong promise for LLM-based machine translation, with recent methods such as GRPO demonstrating notable gains;...
arXiv:2602.03353v1 Announce Type: new Abstract: This paper introduces a new framework for recovering causal graphs from observational data, leveraging the observation that the distribution of...
arXiv:2602.03354v1 Announce Type: new Abstract: Stateful Middleboxes are integral part of enterprise and campus networks that provide essential in-network, security, and value-added services. These stateful...
arXiv:2602.03355v1 Announce Type: new Abstract: Audio is a fundamental modality for analyzing speech, music, and environmental sounds. Although pretrained audio models have significantly advanced audio...
arXiv:2602.03357v1 Announce Type: new Abstract: This paper proposes FedNMap, a normal map-based method for composite federated learning, where the objective consists of a smooth loss...
arXiv:2602.03358v1 Announce Type: new Abstract: Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are...