Stay updated with the latest research and technology news
arXiv:2512.01153v2 Announce Type: replace Abstract: Adversarially guided diffusion sampling often achieves the target class, but sample quality degrades as deviations between the adversarially controlled and...
arXiv:2512.03194v3 Announce Type: replace Abstract: Large robot fleets are now common in warehouses and other logistics settings, where small control gains translate into large operational...
arXiv:2512.03575v2 Announce Type: replace Abstract: Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to...
arXiv:2512.03973v2 Announce Type: replace Abstract: Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such...
arXiv:2512.04277v2 Announce Type: replace Abstract: Post-training with reinforcement learning (RL) typically optimizes a single scalar objective and ignores structure in how solutions are produced. We...
arXiv:2512.04551v2 Announce Type: replace Abstract: Speech emotion recognition (SER) is an important technology in human-computer interaction. However, achieving high performance is challenging due to emotional...
arXiv:2512.04772v2 Announce Type: replace Abstract: In recent years, precision agriculture has been introducing groundbreaking innovations in the field, with a strong focus on automation. However,...
arXiv:2512.05106v3 Announce Type: replace Abstract: Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional...
arXiv:2512.05865v4 Announce Type: replace Abstract: We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under...
arXiv:2512.06690v3 Announce Type: replace Abstract: Preference alignment has enabled large language models (LLMs) to better reflect human expectations, but current methods mostly optimize for population-level...
arXiv:2512.07081v2 Announce Type: replace Abstract: Heart failure (HF) is one of the leading causes of rehospitalization among older adults in the United States. Although clinical...
arXiv:2512.07352v3 Announce Type: replace Abstract: Existing speech anti-spoofing benchmarks rely on a narrow set of public models, creating a substantial gap from real-world scenarios in...
arXiv:2512.07419v2 Announce Type: replace Abstract: Mixed-Precision Quantization (MPQ) liberates Deep Neural Networks (DNNs) from the Out-Of-Memory (OOM) bottleneck and has garnered increasing research attention. However,...
arXiv:2512.07618v2 Announce Type: replace Abstract: We study approximation algorithms for two natural generalizations of the Maximum Quadratic Assignment Problem (MaxQAP). In the Maximum List-Restricted Quadratic...
arXiv:2512.07668v2 Announce Type: replace Abstract: We address the challenge of predicting human visual attention during real-world navigation by measuring and modeling egocentric pedestrian eye gaze...
arXiv:2512.10268v2 Announce Type: replace Abstract: Canada is internationally recognized for its leadership in science and its commitment to equity, diversity, and inclusion (EDI) in STEM...
arXiv:2512.10534v3 Announce Type: replace Abstract: Large language model (LLM) agents exhibit strong mathematical problem-solving abilities and can even solve International Mathematical Olympiad (IMO) level problems...
arXiv:2512.12112v2 Announce Type: replace Abstract: Industry 5.0's increasing integration of IT and OT systems is transforming industrial operations but also expanding the cyber-physical attack surface....
arXiv:2512.13183v2 Announce Type: replace Abstract: Path generation, the process of converting high-level mission specifications, such as sequences of waypoints from a path planner, into smooth,...
arXiv:2512.13586v2 Announce Type: replace Abstract: Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer...
arXiv:2512.13872v3 Announce Type: replace Abstract: We make two contributions to the problem of estimating the $L_1$ calibration error of a binary classifier from a finite...
arXiv:2512.14106v3 Announce Type: replace Abstract: Advances in sensor networks have enabled real-time stream discharge monitoring, yet persistent sensor malfunctions limit data utility. Manual quality control...
arXiv:2512.14266v3 Announce Type: replace Abstract: Predicting driver attention is a critical problem for developing explainable autonomous driving systems and understanding driver behavior in mixed human-autonomous...
arXiv:2512.14391v2 Announce Type: replace Abstract: In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure...