Stay updated with the latest research and technology news
arXiv:2406.18075v2 Announce Type: replace Abstract: The surge in the adoption of smart contracts necessitates rigorous auditing to ensure their security and reliability. Manual auditing, although...
arXiv:2408.08903v3 Announce Type: replace Abstract: This paper investigates source code similarity detection using a transformer model augmented with an execution-derived signal. We extend GraphCodeBERT with...
arXiv:2408.14745v2 Announce Type: replace Abstract: This paper presents a new mixed finite element method for the Cahn-Hilliard equation. The well-posedness of the mixed formulation is...
arXiv:2409.06740v3 Announce Type: replace Abstract: Inverse materials design has proven successful in accelerating novel material discovery. Many inverse materials design methods use unsupervised learning where...
arXiv:2410.02387v5 Announce Type: replace Abstract: Models initialized from self-supervised pretraining may suffer from poor alignment with downstream tasks, reducing the extent to which subsequent fine-tuning...
arXiv:2410.06244v2 Announce Type: replace Abstract: This paper introduces Story-Iter, a new training-free iterative paradigm to enhance long-story generation. Unlike existing methods that rely on fixed...
arXiv:2411.00398v2 Announce Type: replace Abstract: Understanding the emergence of cooperation in social networks has advanced through pairwise interactions, but the corresponding theory for group-based public...
arXiv:2411.00918v4 Announce Type: replace Abstract: Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large...
arXiv:2411.12188v4 Announce Type: replace Abstract: We propose a general framework for optimizing noise schedules in diffusion models, applicable to both training and sampling. Our method...
arXiv:2411.13883v2 Announce Type: replace Abstract: We analyze the unintended effects that recommender systems have on the preferences of users that they are learning. We consider...
arXiv:2411.16598v5 Announce Type: replace Abstract: Diffusion-based purification (DBP) has become a cornerstone defense against adversarial examples (AEs), regarded as robust due to its use of...
arXiv:2412.15768v2 Announce Type: replace Abstract: Processing large amounts of data fast, in constant and small space is the point of stream processing and the reason...
arXiv:2412.19571v3 Announce Type: replace Abstract: We present a novel architecture aimed towards incremental construction and exploitation of a hierarchical 3D scene graph representation during semantic-aware...
arXiv:2501.02673v3 Announce Type: replace Abstract: Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to...
arXiv:2501.04121v2 Announce Type: replace Abstract: Egocentric videos capture scenes from a wearer's viewpoint, resulting in dynamic backgrounds, frequent motion, and occlusions, posing challenges to accurate...
arXiv:2501.16534v4 Announce Type: replace Abstract: Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face...
arXiv:2502.01521v3 Announce Type: replace Abstract: Training reinforcement learning (RL) policies for legged locomotion often requires extensive environment interactions, which are costly and time-consuming. We propose...
arXiv:2502.02088v4 Announce Type: replace Abstract: Recent advances in video generation have enabled thrilling experiences in producing realistic videos driven by scalable diffusion transformers. However, they...
arXiv:2502.04028v3 Announce Type: replace Abstract: This paper presents deep meta coordination graphs (DMCG) for learning cooperative policies in multi-agent reinforcement learning (MARL). Coordination graph formulations...
arXiv:2502.05355v3 Announce Type: replace Abstract: The Nonlinear GMRES (NGMRES) proposed by Washio and Oosterlee [Electron. Trans. Numer. Anal, 6(271-290), 1997] is an acceleration method for...
arXiv:2502.06747v2 Announce Type: replace Abstract: Active vision enables dynamic visual perception, offering an alternative to static feedforward architectures in computer vision, which rely on large...
arXiv:2502.11067v2 Announce Type: replace Abstract: Active feature acquisition (AFA) studies how to sequentially acquire features for each data instance to trade off predictive performance against...
arXiv:2502.16759v2 Announce Type: replace Abstract: Modern recommender systems rely on large-scale ML models that are data-hungry and black-box. Recent advances in LLMs suggest that explicit...
arXiv:2503.05334v4 Announce Type: replace Abstract: This paper investigates quasi-Monte Carlo (QMC) integration of Lebesgue integrable functions with respect to a density function over $\mathbb{R}^s$. We...