Stay updated with the latest research and technology news
arXiv:2602.07135v2 Announce Type: replace Abstract: Loss landscapes are a powerful tool for understanding neural network optimization and generalization, yet traditional low-dimensional analyses often miss complex...
arXiv:2602.07294v2 Announce Type: replace Abstract: With the increasing deployment of Large Language Models (LLMs) in the finance domain, LLMs are increasingly expected to parse complex...
arXiv:2602.07300v2 Announce Type: replace Abstract: This paper proposes distributed omniscient observers for both heterogeneous and homogeneous linear multi-agent systems, such that each agent can correctly...
arXiv:2602.07432v2 Announce Type: replace Abstract: When AI agents on the social platform Moltbook appeared to develop consciousness, found religions, and declare hostility toward humanity, the...
arXiv:2602.07488v2 Announce Type: replace Abstract: Despite the fact that experimental neural scaling laws have substantially guided empirical progress in large-scale machine learning, no existing theory...
arXiv:2602.07497v2 Announce Type: replace Abstract: Cultural context profoundly shapes how people interpret online content, yet vision-language models (VLMs) remain predominantly trained through Western or English-centric...
arXiv:2602.07512v2 Announce Type: replace Abstract: Detecting objects from UAV-captured images is challenging due to the small object size. In this work, a simple and efficient...
arXiv:2602.07774v3 Announce Type: replace Abstract: Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and...
arXiv:2602.07837v3 Announce Type: replace Abstract: Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world...
arXiv:2602.08126v2 Announce Type: replace Abstract: Reliable 3D object detection is fundamental to autonomous driving, and multimodal fusion algorithms using cameras and LiDAR remain a persistent...
arXiv:2602.08322v2 Announce Type: replace Abstract: In task-oriented dialogue systems, spoken language understanding (SLU) is a critical component, which consists of two sub-tasks, intent detection and...
arXiv:2602.08449v2 Announce Type: replace Abstract: Safety evaluation for advanced AI systems implicitly assumes that behavior observed under evaluation predicts behavior in deployment. This assumption becomes...
arXiv:2602.08517v2 Announce Type: replace Abstract: Tensor is the most basic and essential data structure of nowadays artificial intelligence (AI) system. The natural properties of Tensor,...
arXiv:2602.08520v3 Announce Type: replace Abstract: Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings...
arXiv:2602.08535v2 Announce Type: replace Abstract: Generative modeling typically seeks the path of least action via deterministic flows (ODE). While effective for in-distribution tasks, we argue...
arXiv:2602.08615v2 Announce Type: replace Abstract: While generative models have become powerful tools for image synthesis, they are typically optimized for executing carefully crafted textual prompts,...
arXiv:2602.08711v2 Announce Type: replace Abstract: This paper proposes Omni Dense Captioning, a novel task designed to generate continuous, fine-grained, and structured audio-visual narratives with explicit...
arXiv:2602.08751v2 Announce Type: replace Abstract: Current biological AI models lack interpretability -- their internal representations do not correspond to biological relationships that researchers can examine....
arXiv:2602.08907v2 Announce Type: replace Abstract: We study a setting where the goal is to learn a target function f(x) with respect to a target distribution...
arXiv:2602.08930v3 Announce Type: replace Abstract: Open-vocabulary keyword spotting (OV-KWS) enables personalized device control via arbitrary voice commands. Recently, researchers have explored using audio-text joint embeddings,...
arXiv:2602.09013v2 Announce Type: replace Abstract: Multi-finger robotic hand manipulation and grasping are challenging due to the high-dimensional action space and the difficulty of acquiring large-scale...
arXiv:2602.09070v2 Announce Type: replace Abstract: Synthesizing coherent soundtracks for long-form videos remains a formidable challenge, currently stalled by three critical impediments: computational scalability, temporal coherence,...
arXiv:2602.09255v2 Announce Type: replace Abstract: Mobile robots are often deployed over long durations in diverse open, dynamic scenes, including indoor setting such as warehouses and...
arXiv:2602.09316v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) based Large Language Models (LLMs) have achieved superior performance, yet the massive memory overhead caused by storing multiple...