Stay updated with the latest research and technology news
arXiv:2602.11554v2 Announce Type: replace Abstract: 4D mmWave radar provides weather-robust, velocity-aware measurements and is more cost-effective than LiDAR. However, radar-only 3D detection still trails LiDAR-based...
arXiv:2602.11575v2 Announce Type: replace Abstract: Visual navigation models often struggle in real-world dynamic environments due to limited robustness to the sim-to-real gap and the difficulty...
arXiv:2602.11712v2 Announce Type: replace Abstract: We introduce potential-energy gating, a method for robust state estimation in systems governed by double-well stochastic dynamics. The observation noise...
arXiv:2602.11858v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is...
arXiv:2602.11938v3 Announce Type: replace Abstract: Large language models (LLMs) perform well on well-posed questions, yet standard question-answering (QA) benchmarks remain far from solved. We argue...
arXiv:2602.12063v2 Announce Type: replace Abstract: The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction....
arXiv:2602.12095v2 Announce Type: replace Abstract: The automation of warehouse operations is crucial for improving productivity and reducing human exposure to hazardous environments. One operation frequently...
arXiv:2602.12150v2 Announce Type: replace Abstract: Do Large Language Models (LLMs) possess a Theory of Mind (ToM)? Research into this question has focused on evaluating LLMs...
arXiv:2602.12157v2 Announce Type: replace Abstract: High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing...
arXiv:2602.12242v2 Announce Type: replace Abstract: In order to comprehensively investigate the multiphysics coupling in spintronic devices, it is essential to parallelize and utilize GPU-acceleration to...
arXiv:2602.12247v2 Announce Type: replace Abstract: Unstructured documents like PDFs contain valuable structured information, but downstream systems require this data in reliable, standardized formats. LLMs are...
arXiv:2602.12289v2 Announce Type: replace Abstract: The DC-side ground fault (GF) poses significant risks to three-phase TN-earthed photovoltaic (PV) systems, as the resulting high fault current...
arXiv:2602.12384v2 Announce Type: replace Abstract: Understanding why gradient-based training in deep networks exhibits strong implicit bias remains challenging, in part because tractable singular-value dynamics are...
arXiv:2602.12430v2 Announce Type: replace Abstract: The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs)...
arXiv:2602.12628v2 Announce Type: replace Abstract: Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most...
arXiv:2602.12705v2 Announce Type: replace Abstract: We present MedXIAOHE, a medical vision-language foundation model designed to advance general-purpose medical understanding and reasoning in real-world clinical applications....
arXiv:2602.12723v2 Announce Type: replace Abstract: Objective assessment of speech that reflects meaningful changes in communication is crucial for clinical decision making and reproducible research. While...
arXiv:2602.12916v2 Announce Type: replace Abstract: As a multimodal extension of Chain-of-Thought (CoT), Thinking with Images (TWI) has recently emerged as a promising avenue to enhance...
arXiv:2602.12950v2 Announce Type: replace Abstract: Understanding what drives code instability is essential for effective software maintenance, as unstable classes require larger or more frequent edits...
arXiv:2602.13021v2 Announce Type: replace Abstract: Symbolic Regression (SR) aims to discover interpretable equations from observational data, with the potential to reveal underlying principles behind natural...
arXiv:2602.13093v2 Announce Type: replace Abstract: Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains...
arXiv:2602.13103v2 Announce Type: replace Abstract: Self-play bootstraps LLM reasoning through an iterative Challenger-Solver loop: the Challenger is trained to generate questions that target the Solver's...
arXiv:2602.13154v2 Announce Type: replace Abstract: Foundational results in machine learning -- the universal approximation theorem and deep reinforcement learning convergence -- imply that the vast...
arXiv:2103.14203v5 Announce Type: replace-cross Abstract: Matrix reordering is a task to permute the rows and columns of a given observed matrix such that the resulting...