Stay updated with the latest research and technology news
arXiv:2601.13319v2 Announce Type: replace Abstract: Dialectal Arabic (DA) speech data vary widely in domain coverage, dialect labeling practices, and recording conditions, complicating cross-dataset comparison and...
arXiv:2601.13346v2 Announce Type: replace Abstract: Language Identification (LID) is the task of determining the language of a given text and is a fundamental preprocessing step...
arXiv:2601.13380v2 Announce Type: replace Abstract: Learning in data-scarce settings has recently gained significant attention in the research community. Semi-supervised object detection(SSOD) aims to improve detection...
arXiv:2601.13465v2 Announce Type: replace Abstract: We demonstrate that a single training trajectory can transform a graph neural network into an unsupervised heuristic for combinatorial optimization....
arXiv:2601.13663v2 Announce Type: replace Abstract: The Longest Edge Bisection of a triangle is performed by joining the midpoint of its longest edge to the opposite...
arXiv:2601.14210v2 Announce Type: replace Abstract: LLMs often produce fluent but incorrect answers, yet detecting such hallucinations typically requires multiple sampling passes or post-hoc verification, adding...
arXiv:2601.14652v2 Announce Type: replace Abstract: While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliver. Such shortcomings...
arXiv:2601.14743v3 Announce Type: replace Abstract: The effectiveness of collision-free trajectory planners depends on the quality and diversity of training data, especially for rare scenarios. A...
arXiv:2601.15017v2 Announce Type: replace Abstract: While video-to-audio generation has achieved remarkable progress in semantic and temporal alignment, most existing studies focus solely on these aspects,...
arXiv:2601.15036v2 Announce Type: replace Abstract: Factorizable joint shift (FJS) represents a type of distribution shift (or dataset shift) that comprises both covariate and label shift....
arXiv:2601.15158v2 Announce Type: replace Abstract: Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought)....
arXiv:2601.15260v2 Announce Type: replace Abstract: Perception is a cornerstone of autonomous driving, enabling vehicles to understand their surroundings and make safe, reliable decisions. Developing robust...
arXiv:2601.15930v2 Announce Type: replace Abstract: Model merging (MM) offers an efficient mechanism for integrating multiple specialized models without access to original training data or costly...
arXiv:2601.16272v2 Announce Type: replace Abstract: We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require...
arXiv:2601.16651v2 Announce Type: replace Abstract: Gradient-based methods for instance-based explanation for large language models (LLMs) are hindered by the immense dimensionality of model gradients. In...
arXiv:2601.16740v2 Announce Type: replace Abstract: Generative AI (GenAI) systems are inherently non-deterministic, producing varied outputs even for identical inputs. While this variability is central to...
arXiv:2601.17550v2 Announce Type: replace Abstract: Autonomous aerial navigation in absolute darkness is crucial for post-disaster search and rescue operations, which often occur from disaster-zone power...
arXiv:2601.17865v2 Announce Type: replace Abstract: The predictive probability of the next token (P_token) in large language models (LLMs) is inextricably linked to the probability of...
arXiv:2601.17868v2 Announce Type: replace Abstract: Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM...
arXiv:2601.17915v2 Announce Type: replace Abstract: LLM agents excel when environments are mostly static and the needed information fits in a model's context window, but they...
arXiv:2601.17962v2 Announce Type: replace Abstract: Collaborative problem solving (CPS) is a fundamental practice in middle-school mathematics education; however, student groups frequently stall or struggle without...
arXiv:2601.18154v2 Announce Type: replace Abstract: Endometriosis ultrasound reports are often unstructured free-text documents that require manual abstraction for downstream tasks such as analytics, machine learning...
arXiv:2601.18368v2 Announce Type: replace Abstract: We present OREHAS (Optimized Recognition & Evaluation of volumetric Hydrops in the Auditory System), the first fully automatic pipeline for...
arXiv:2601.18537v2 Announce Type: replace Abstract: Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and environmental factors. Existing methods...