Stay updated with the latest research and technology news
arXiv:2602.04244v1 Announce Type: new Abstract: This paper aims to train a graph foundation model that is able to represent any graph as a vector preserving...
arXiv:2602.04246v1 Announce Type: new Abstract: Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs), and latent reasoning methods...
arXiv:2602.04248v1 Announce Type: new Abstract: Inference-time scaling strategies, particularly Monte Carlo Tree Search (MCTS), have significantly enhanced the reasoning capabilities of Large Language Models (LLMs)....
arXiv:2602.04251v1 Announce Type: new Abstract: Traditional Simultaneous Localization and Mapping (SLAM) systems often face limitations including coarse rendering quality, insufficient recovery of scene details, and...
arXiv:2602.04252v1 Announce Type: new Abstract: Continual learning (or class incremental learning) is a realistic learning scenario for computer vision systems, where deep neural networks are...
arXiv:2602.04254v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a...
arXiv:2602.04255v1 Announce Type: new Abstract: In partial multi-label learning (PML), the true labels are unobserved, which makes label disambiguation important but difficult. A key challenge...
arXiv:2602.04256v1 Announce Type: new Abstract: End-to-end autonomous driving has emerged as a promising paradigm integrating perception, decision-making, and control within a unified learning framework. Recently,...
arXiv:2602.04257v1 Announce Type: new Abstract: Monocular video human mesh recovery faces fundamental challenges in maintaining metric consistency and temporal stability due to inherent depth ambiguities...
arXiv:2602.04258v1 Announce Type: new Abstract: The agile mobility of Unmanned Aerial Vehicles (UAVs) makes them ideal for low-altitude edge computing. This paper proposes a novel...
arXiv:2602.04260v1 Announce Type: new Abstract: Human multimodal emotion recognition (MER) seeks to infer human emotions by integrating information from language, visual, and acoustic modalities. Although...
arXiv:2602.04261v1 Announce Type: new Abstract: Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation,...
arXiv:2602.04262v1 Announce Type: new Abstract: This paper investigates parameter-privacy-preserving data sharing in continuous-state dynamical systems, where a data owner designs a data-sharing policy to support...
arXiv:2602.04263v1 Announce Type: new Abstract: Multimodal document retrieval aims to retrieve query-relevant components from documents composed of textual, tabular, and visual elements. An effective multimodal...
arXiv:2602.04264v1 Announce Type: new Abstract: Residual connections are the de facto standard for mitigating vanishing gradients, yet they impose structural constraints and fail to address...
arXiv:2602.04265v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LLMs)....
arXiv:2602.04268v1 Announce Type: new Abstract: Despite the significant progress of Multimodal Large Language Models (MLLMs) across diverse tasks, hallucination -- corresponding to the generation of...
arXiv:2602.04270v1 Announce Type: new Abstract: Many fields collect large-scale temporal data through repeated measurements (trials), where each trial is labeled with a set of metadata...
arXiv:2602.04271v1 Announce Type: new Abstract: 4D generation has made remarkable progress in synthesizing dynamic 3D objects from input text, images, or videos. However, existing methods...
arXiv:2602.04277v1 Announce Type: new Abstract: Non Pneumatic tires offer a promising alternative to pneumatic tires. However, their discontinuous spoke structures present challenges in stiffness tuning,...
arXiv:2602.04278v1 Announce Type: new Abstract: The integration of reinforcement learning (RL) into large language models (LLMs) has opened new opportunities for recommender systems by eliciting...
arXiv:2602.04279v1 Announce Type: new Abstract: Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable...
arXiv:2602.04284v1 Announce Type: new Abstract: Managing agent thought and observation during multi-turn agent-environment interactions is an emerging strategy to improve agent efficiency. However, existing studies...
arXiv:2602.04287v1 Announce Type: new Abstract: We propose the Convolutional Operator Network for Forward and Inverse Problems (FI-Conv), a framework capable of predicting system evolution and...