Stay updated with the latest research and technology news
arXiv:2506.18777v2 Announce Type: replace Abstract: Large language models (LLMs) are typically trained to acquire behaviours from demonstrations or experience, yet much of their training data...
arXiv:2506.18882v5 Announce Type: replace Abstract: Universal photometric stereo (PS) is defined by two factors: it must (i) operate under arbitrary, unknown lighting conditions and (ii)...
arXiv:2506.21220v4 Announce Type: replace Abstract: General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results...
arXiv:2506.21324v2 Announce Type: replace Abstract: Neuromorphic and quantum computing have recently emerged as promising paradigms for advancing artificial intelligence, each offering complementary strengths. Neuromorphic systems...
arXiv:2507.00994v3 Announce Type: replace Abstract: Learning high-quality text representations is fundamental to a wide range of NLP tasks. While encoder pretraining has traditionally relied on...
arXiv:2507.04002v2 Announce Type: replace Abstract: Birds' Eye View (BEV) semantic segmentation is an indispensable perception task in end-to-end autonomous driving systems. Unsupervised and semi-supervised learning...
arXiv:2507.04448v2 Announce Type: replace Abstract: We develop a theory of transfer learning in infinitely wide neural networks under gradient flow that quantifies when pretraining on...
arXiv:2507.08100v2 Announce Type: replace Abstract: In crowded environments, individuals must navigate around other occupants to reach their destinations. Understanding and controlling traffic flows in these...
arXiv:2507.12265v2 Announce Type: replace Abstract: Optical Circuit Switching (OCS) technology is increasingly being adopted in data centers due to its advantages of low power consumption...
arXiv:2507.12442v3 Announce Type: replace Abstract: Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local...
arXiv:2507.12707v3 Announce Type: replace Abstract: We consider the probability that a spanning tree chosen uniformly at random from a graph can be partitioned into a...
arXiv:2507.19575v2 Announce Type: replace Abstract: Data scarcity is a major challenge in medical imaging, particularly for deep learning models. While data pooling (combining datasets from...
arXiv:2507.23592v3 Announce Type: replace Abstract: Hand exoskeletons are critical tools for dexterous teleoperation and immersive manipulation interfaces, but achieving accurate hand tracking remains a challenge...
arXiv:2508.01012v2 Announce Type: replace Abstract: Electronic Design Automation (EDA) remains heavily reliant on tool command language (Tcl) scripting to drive complex RTL-to-GDSII flows. This scripting-based...
arXiv:2508.01115v2 Announce Type: replace Abstract: User attributes are essential in multiple stages of modern recommendation systems and are particularly important for mitigating the cold-start problem...
arXiv:2508.03250v3 Announce Type: replace Abstract: The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse...
arXiv:2508.03467v2 Announce Type: replace Abstract: We introduce an expurgation method for source coding with side information that enables direct dual-domain derivations of expurgated error exponents....
arXiv:2508.03616v2 Announce Type: replace Abstract: We present the first comprehensive analysis of massive activation development throughout transformer training, using the Pythia model family as our...
arXiv:2508.06878v2 Announce Type: replace Abstract: Infrared small target detection and segmentation (IRSTDS) is a critical yet challenging task in defense and civilian applications, owing to...
arXiv:2508.09639v2 Announce Type: replace Abstract: Explainable Artificial Intelligence (XAI) techniques, such as SHapley Additive exPlanations (SHAP), have become essential tools for interpreting complex ensemble tree-based...
arXiv:2508.09691v2 Announce Type: replace Abstract: Facial representation pre-training is crucial for tasks like facial recognition, expression analysis, and virtual reality. However, existing methods face three...
arXiv:2508.10453v2 Announce Type: replace Abstract: Online video super-resolution (VSR) is an important technique for many real-world video processing applications, which aims to restore the current...
arXiv:2508.11479v2 Announce Type: replace Abstract: Open-vocabulary Object Goal Navigation requires an embodied agent to reach objects described by free-form language, including categories never seen during...
arXiv:2508.13404v4 Announce Type: replace Abstract: Real-world financial filings report critical information about an entity's investment holdings, essential for assessing that entity's risk, profitability, and relationship...