Stay updated with the latest research and technology news
arXiv:2510.18619v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We...
arXiv:2510.19155v3 Announce Type: replace Abstract: Catastrophic forgetting is a well-documented challenge in model fine-tuning, particularly when the downstream domain has limited labeled data or differs...
arXiv:2510.19229v2 Announce Type: replace Abstract: Infants discover categories, detect novelty, and adapt to new contexts without supervision-a challenge for current machine learning. We present a...
arXiv:2510.19764v2 Announce Type: replace Abstract: The majority of research in both training Artificial Neural Networks (ANNs) and modeling learning in biological brains focuses on synaptic...
arXiv:2510.19950v3 Announce Type: replace Abstract: In financial applications, reinforcement learning (RL) agents are commonly trained on historical data, where their actions do not influence prices....
arXiv:2510.20406v3 Announce Type: replace Abstract: Robotic manipulation systems benefit from complementary sensing modalities, where each provides unique environmental information. Point clouds capture detailed geometric structure,...
arXiv:2510.20844v3 Announce Type: replace Abstract: Agentic systems have recently emerged as a promising tool to automate literature-based ideation. However, current systems often remain black-box, with...
arXiv:2510.20984v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities but typically require extensive computational resources and memory for inference. Post-training quantization...
arXiv:2510.21366v2 Announce Type: replace Abstract: In this work, we propose a novel framework to enable diffusion models to adapt their generation quality based on real-time...
arXiv:2510.21938v2 Announce Type: replace Abstract: All or Nothing, Water Walk, and Remembered Length are pencil puzzles that involve constructing a continuous loop on a rectangular...
arXiv:2510.22048v2 Announce Type: replace Abstract: Power flow (PF) calculations are the backbone of real-time grid operations, across workflows such as contingency analysis (where repeated PF...
arXiv:2510.22345v2 Announce Type: replace Abstract: Constitutive model discovery refers to the task of identifying an appropriate model structure, usually from a predefined model library, while...
arXiv:2510.22590v2 Announce Type: replace Abstract: In today's rapidly expanding data landscape, knowledge extraction from unstructured text is vital for real-time analytics, temporal inference, and dynamic...
arXiv:2510.22767v2 Announce Type: replace Abstract: Large Language Models (LLMs) are typically deployed using a fixed architecture, despite growing evidence that not all layers contribute equally...
arXiv:2510.22860v3 Announce Type: replace Abstract: Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in...
arXiv:2510.22881v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF)...
arXiv:2510.22922v4 Announce Type: replace Abstract: The reasoning capabilities of Large Language Models (LLMs) have led to their increasing employment in several critical applications, particularly education,...
arXiv:2510.22955v2 Announce Type: replace Abstract: Accurate prediction of remaining useful life (RUL) is essential to enhance system reliability and reduce maintenance risk. Yet many strong...
arXiv:2510.23118v4 Announce Type: replace Abstract: We propose a task-agnostic framework for multimodal fusion of time series and single timestamp images, enabling cross-modal generation and robust...
arXiv:2510.23912v3 Announce Type: replace Abstract: The Query, Key, Value weight triplet is a building block of current attention mechanisms in state-of-the-art LLMs. We theoretically investigate...
arXiv:2510.24936v2 Announce Type: replace Abstract: Wi-Fi sensing is a leading technology for Human Activity Recognition (HAR), offering a non-intrusive and cost-effective solution for healthcare and...
arXiv:2510.24940v3 Announce Type: replace Abstract: The verbosity of Chain-of-Thought (CoT) reasoning hinders its mass deployment in efficiency-critical applications. Recently, implicit CoT approaches have emerged, which...
arXiv:2510.25369v2 Announce Type: replace Abstract: Neither the classical nor intuitionistic logic traditions are perfectly-aligned with the purpose of reasoning about computation, in that neither tradition...
arXiv:2510.25423v2 Announce Type: replace Abstract: AI Agents have rapidly gained prominence in both research and industry as systems that extend large language models with planning,...