arXiv:2601.10120v2 Announce Type: replace-cross
Abstract: Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where …
arXiv:2604.11502v2 Announce Type: replace
Abstract: Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate this skill in fragmented settings, failing to ensur…
arXiv:2604.14141v2 Announce Type: replace
Abstract: Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency, and computational …
arXiv:2604.13630v1 Announce Type: cross
Abstract: The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same a…
arXiv:2604.14261v1 Announce Type: new
Abstract: The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate superficial, formulaic c…
arXiv:2604.14781v1 Announce Type: new
Abstract: Obstacle detection in railway environments is crucial for ensuring safety. However, very few studies address the problem using a complete, modular, and flexible system that can both detect objects in the…
arXiv:2604.14306v1 Announce Type: new
Abstract: While Large Language Models (LLMs) have demonstrated high proficiency on English-centric medical examinations, their performance often declines when faced with non-English languages and multimodal diagno…
arXiv:2604.14268v1 Announce Type: new
Abstract: We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prompts, single-view images…
arXiv:2604.14805v1 Announce Type: new
Abstract: Grain-edge segmentation (GES) and lithology semantic segmentation (LSS) are two pivotal tasks for quantifying rock fabric and composition. However, these two tasks are often treated separately, and the s…
arXiv:2604.14816v1 Announce Type: new
Abstract: This paper presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction. The goal of the challenge participants was to develop automatic saliency map prediction methods for the provided …