Search: “context”

arXiv:2510.03323v2 Announce Type: replace Abstract: Integrating textual graphs into Large Language Models (LLMs) is promising for complex graph-based QA. However, a key bottleneck is retrieving inform

arXiv:2604.12176v1 Announce Type: new Abstract: Relational reasoning is the ability to infer relations that jointly bind multiple entities, attributes, or variables. This ability is central to scienti

arXiv:2604.12568v1 Announce Type: new Abstract: Conventional deep network training generally optimizes all samples under a largely uniform learning paradigm, without explicitly modeling the heterogene

arXiv:2506.14092v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in decision-support systems for high-stakes domains such as hiring and university admissions,

arXiv:2604.12351v1 Announce Type: new Abstract: Automated diagnosis based on color fundus photography is essential for large-scale glaucoma screening. However, existing deep learning models are typica

arXiv:2604.12390v1 Announce Type: new Abstract: This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their reasoning processes exhibit Bayesian-like st

arXiv:2511.17537v2 Announce Type: replace-cross Abstract: Wireless Sensor Networks (WSN) are the backbone of essential monitoring applications, but their deployment in unfavourable conditions increase

arXiv:2604.12229v1 Announce Type: new Abstract: Small language models (SLMs) often struggle with complex mathematical reasoning due to limited capacity to maintain long chains of intermediate steps an

arXiv:2604.12250v1 Announce Type: new Abstract: This study examines how model-specific characteristics of Large Language Model (LLM) agents, including internal alignment, shape the effect of memory on

arXiv:2511.21356v2 Announce Type: replace-cross Abstract: Adversarial Inverse Reinforcement Learning (AIRL) has shown promise in addressing the sparse reward problem in reinforcement learning (RL) by

arXiv:2604.12303v1 Announce Type: new Abstract: Batch active learning (BAL) is a crucial technique for reducing labeling costs and improving data efficiency in training large-scale deep learning model

arXiv:2604.12493v1 Announce Type: cross Abstract: LLMs can perform seemingly planning-intensive tasks, like writing coherent stories or functioning code, without explicitly verbalizing a plan; however

arXiv:2604.12994v1 Announce Type: cross Abstract: Logical vulnerabilities in software stem from flaws in program logic rather than memory safety, which can lead to critical security failures. Although

arXiv:2604.12126v1 Announce Type: new Abstract: Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing m

arXiv:2604.12056v1 Announce Type: new Abstract: Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipel

arXiv:2604.11995v1 Announce Type: new Abstract: The central goal of active learning is to gather data that maximises downstream predictive performance, but popular approaches have limited flexibility

arXiv:2604.12066v1 Announce Type: new Abstract: Large language models can increasingly adapt educational tasks to learners characteristics. In the present study, we examine a multi-agent teacher-in-th

arXiv:2604.12700v1 Announce Type: new Abstract: Understanding human intent in complex multi-turn interactions remains a fundamental challenge in human-computer interaction and behavioral analysis. Whi

arXiv:2507.04227v2 Announce Type: replace-cross Abstract: Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute d

arXiv:2604.12213v1 Announce Type: new Abstract: Preserving multimodal signals across agent boundaries is necessary for accurate cross-modal reasoning, but it is not sufficient. We show that modality-n

arXiv:2602.23061v3 Announce Type: replace-cross Abstract: Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and

arXiv:2604.11972v1 Announce Type: new Abstract: Coherent nonlinear wave dynamics are often strongly shaped by a compact set of physically meaningful descriptors of the initial state. Traditional neura

arXiv:2604.12076v1 Announce Type: cross Abstract: The Identifiable Victim Effect (IVE) - the tendency to allocate greater resources to a specific, narratively described victim than to a statistically

arXiv:2604.12374v1 Announce Type: cross Abstract: We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention

arXiv:2512.13961v2 Announce Type: replace Abstract: We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets

arXiv:2504.02169v3 Announce Type: replace-cross Abstract: We study the geometry of Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves in binary classification problems. The key f

arXiv:2604.13017v1 Announce Type: new Abstract: AI-driven education platforms have made some progress in personalisation, yet most remain constrained to static adaptation--predefined quizzes, uniform

arXiv:2604.12986v1 Announce Type: cross Abstract: Autonomous AI agents are rapidly transitioning from experimental tools to operational infrastructure, with projections that 80% of enterprise applicat

arXiv:2604.12177v1 Announce Type: new Abstract: LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational polic

arXiv:2604.12068v1 Announce Type: new Abstract: Visual localization is the task of estimating the camera pose of an image relative to a scene representation. In practice, visual localization systems a

arXiv:2601.09152v2 Announce Type: replace Abstract: Prior work on LLM-based privacy focuses on norm judgment over synthetic vignettes, rather than how people think about a specific data practice and f

arXiv:2604.12918v1 Announce Type: new Abstract: Bird's-eye-view (BEV) representations are the dominant paradigm for 3D perception in autonomous driving, providing a unified spatial canvas where detect

arXiv:2604.13021v1 Announce Type: cross Abstract: Computed tomography (CT) enterography is a primary imaging modality for assessing inflammatory bowel disease (IBD), yet the representational choices t

arXiv:2511.09803v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves factuality but retrieving for every query often hurts quality while inflating tokens and latency. We p

arXiv:2604.12500v1 Announce Type: new Abstract: Specification gaming under Reinforcement Learning (RL) is known to cause LLMs to develop sycophantic, manipulative, or deceptive behavior, yet the condi

arXiv:2512.04585v3 Announce Type: replace Abstract: Segment Anything Model 3 (SAM3) advances open-vocabulary segmentation through promptable concept segmentation, enabling users to segment all instanc

arXiv:2602.15876v1 Announce Type: cross Abstract: Adapting instruction to the fine-grained needs of individual students is a powerful application of recent advances in large language models. These gen

arXiv:2510.20093v2 Announce Type: replace-cross Abstract: Although recent advancements in diffusion models have significantly enriched the quality of generated images, challenges remain in synthesizin

arXiv:2604.12116v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents capable of executing system-level operations. While existing benchmarks

arXiv:2604.12648v1 Announce Type: cross Abstract: Despite the recent success of large language models (LLMs) in time-series forecasting, most existing methods still adopt a Deep Synchronous Fusion str

arXiv:2604.12503v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenari

arXiv:2512.05812v5 Announce Type: replace-cross Abstract: Scalable multi-agent driving simulation requires behavior models that are both realistic and computationally efficient. We address this by opt

arXiv:2410.03000v3 Announce Type: replace Abstract: Existing certified training methods can only train models to be robust against a certain perturbation type (e.g. l_infty or l_2). However, an l_inft

arXiv:2603.03249v2 Announce Type: replace Abstract: Generative artificial intelligence (AI) offers scalable support for formative feedback, yet most AI-generated feedback relies on task-specific rubri

arXiv:2604.05818v2 Announce Type: replace-cross Abstract: Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-

arXiv:2604.10456v1 Announce Type: new Abstract: The surging demand for adapting long-form cinematic content into short videos has motivated the need for versatile automatic video compilation systems.