Stay updated with the latest research and technology news
arXiv:2601.12323v2 Announce Type: replace Abstract: Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily...
arXiv:2601.12375v2 Announce Type: replace Abstract: Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Real-Time (Near-RT) latency...
arXiv:2601.12456v2 Announce Type: replace Abstract: In this paper we propose an approach for executing data transformations near- or in-storage on intelligent storage systems. The currently...
arXiv:2601.12503v3 Announce Type: replace Abstract: We show how to convert any unsatisfiable 3-CNF formula which is sparse and exponentially hard to refute in Resolution into...
arXiv:2601.12654v2 Announce Type: replace Abstract: Post-hoc explanations are widely used to justify, contest, and review automated decisions in high-stakes domains such as lending, employment, and...
arXiv:2601.12658v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However,...
arXiv:2601.12662v2 Announce Type: replace Abstract: We address real-time sampling and estimation of autoregressive Markovian sources in dynamic yet structurally similar multi-hop wireless networks. Each node...
arXiv:2601.12815v4 Announce Type: replace Abstract: Legal Judgment Prediction (LJP) aims to predict the outcomes of legal cases based on factual descriptions, serving as a fundamental...
arXiv:2601.12816v2 Announce Type: replace Abstract: Continual learning aims to enable neural networks to acquire new knowledge on sequential tasks. However, the key challenge in such...
arXiv:2601.12823v2 Announce Type: replace Abstract: Aerial remote sensing enables efficient large-area surveying, but accurate direct object-level measurement remains difficult in complex natural scenes. Recent advancements...
arXiv:2601.12954v3 Announce Type: replace Abstract: Image style transfer aims to integrate the visual patterns of a specific artistic style into a content image while preserving...
arXiv:2601.13256v3 Announce Type: replace Abstract: The numerical solution of high dimensional partial differential equations (PDEs) is severely constrained by the curse of dimensionality (CoD), rendering...
arXiv:2601.13260v2 Announce Type: replace Abstract: Tokenization underlies every large language model, yet it remains an under-theorized and inconsistently designed component. Common subword approaches such as...
arXiv:2601.13295v2 Announce Type: replace Abstract: Resolving team conflicts requires not only task-specific competence, but also social intelligence to find common ground and build consensus. As...
arXiv:2601.13545v3 Announce Type: replace Abstract: Evaluating language models and AI agents remains fundamentally challenging because static benchmarks fail to capture real-world uncertainty, distribution shift, and...
arXiv:2601.13742v2 Announce Type: replace Abstract: Large Language Model (LLM) judges exhibit strong reasoning capabilities but are limited to textual content. This leaves current automatic Speech-to-Speech...
arXiv:2601.13953v2 Announce Type: replace Abstract: Learning precise Boolean logic via gradient descent remains challenging: neural networks typically converge to "fuzzy" approximations that degrade under quantization....
arXiv:2601.14047v2 Announce Type: replace Abstract: Suppose we need a deep collective analysis of an open scientific problem: there is a complex scientific hypothesis and a...
arXiv:2601.14054v2 Announce Type: replace Abstract: Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the...
arXiv:2601.14109v2 Announce Type: replace Abstract: Table learning, which lies at the intersection of machine learning and modern database systems, has recently attracted growing attention. However,...
arXiv:2601.14243v2 Announce Type: replace Abstract: Reinforcement learning (RL) is essential for enhancing the complex reasoning capabilities of large language models (LLMs). However, existing RL training...
arXiv:2601.14519v2 Announce Type: replace Abstract: Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains...
arXiv:2601.14724v2 Announce Type: replace Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant improvement in offline video understanding. However, extending these capabilities...
arXiv:2601.14746v2 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training without sharing raw data in edge environments, but is constrained by limited communication...