Large Language Models

arXiv:2603.29194v1 Announce Type: cross Abstract: Long-horizon dialogue systems suffer from semanticdrift and unstable memory retention across extended sessions

arXiv:2603.29200v1 Announce Type: cross Abstract: Deep learning-based tropical cyclone (TC) forecasting methods have demonstrated significant potential and appl

arXiv:2603.29219v1 Announce Type: cross Abstract: Sign language is the primary approach of communication for the Deaf and Hard-of-Hearing (DHH) community. While

arXiv:2603.29224v1 Announce Type: cross Abstract: Fine-scale-faithful neural simulation under fixed storage budgets remains challenging. Many existing methods r

arXiv:2603.29247v1 Announce Type: cross Abstract: LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for persona

arXiv:2603.29281v1 Announce Type: cross Abstract: A critical gap exists between the general-purpose visual understanding of state-of-the-art physical AI models

arXiv:2603.29288v1 Announce Type: cross Abstract: Social and personal decisions in relational domains such as matchmaking are deeply entwined with cultural norm

arXiv:2603.29292v1 Announce Type: cross Abstract: Improving the code generation capabilities of large language models (LLMs) typically relies on supervised fine

arXiv:2603.29328v1 Announce Type: cross Abstract: Backdoor attacks on federated learning (FL) are most often evaluated with synthetic corner patches or out-of-d

arXiv:2603.29386v1 Announce Type: cross Abstract: The rapid democratization of prompt-based AI image editing has recently exacerbated the risks associated with

arXiv:2603.29403v1 Announce Type: cross Abstract: LLM-as-a-Judge (LaaJ) is a novel paradigm in which powerful language models are used to assess the quality, sa

arXiv:2603.29405v1 Announce Type: cross Abstract: Large Vision-Language Models have demonstrated exceptional performance in multimodal reasoning and complex sce

arXiv:2603.29410v1 Announce Type: cross Abstract: Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adv

arXiv:2603.29418v1 Announce Type: cross Abstract: Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their

arXiv:2603.29450v1 Announce Type: cross Abstract: While state-of-the-art Handwritten Text Recognition (HTR) models perform well on standard benchmarks, they fre

arXiv:2603.29466v1 Announce Type: cross Abstract: Existing methods for quantifying predictive uncertainty in neural networks are either computationally intracta

arXiv:2603.29467v1 Announce Type: cross Abstract: This paper presents a Multilingual Vision Large Language Model, named M-MiniGPT4. Our model exhibits strong vi

arXiv:2603.29493v1 Announce Type: cross Abstract: Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recen

arXiv:2603.29518v1 Announce Type: cross Abstract: Conversational systems should generate diverse language forms to interact fluently and accurately with users.

arXiv:2603.29522v1 Announce Type: cross Abstract: Modern language models (LMs) must be trained on many orders of magnitude more words of training data than huma

arXiv:2603.29552v1 Announce Type: cross Abstract: Multilingualism is incredibly common around the world, leading to many important theoretical and practical que

arXiv:2603.29617v1 Announce Type: cross Abstract: Understanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscienc

arXiv:2603.29654v1 Announce Type: cross Abstract: Aligning human-interpretable concepts with the internal representations learned by modern machine learning sys

arXiv:2603.29661v1 Announce Type: cross Abstract: Existing narrative extraction methods face a trade-off between coherence, interactivity, and multi-storyline s

arXiv:2603.29677v1 Announce Type: cross Abstract: Multimodal learning enables neural networks to integrate information from heterogeneous sources, but active le

arXiv:2603.29689v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they some

arXiv:2603.29741v1 Announce Type: cross Abstract: BotVerse is a scalable, event-driven framework for high-fidelity social simulation using LLM-based agents. It

arXiv:2603.29805v1 Announce Type: cross Abstract: A key problem in the modern study of AI is predicting and understanding emergent capabilities in models during

arXiv:2603.29844v1 Announce Type: cross Abstract: The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Visio

arXiv:2603.29860v1 Announce Type: cross Abstract: Implicit Neural Representations (INRs) provide compact models of geometry, but it is unclear when their learne

arXiv:2603.29878v1 Announce Type: cross Abstract: Cloud systems generate large, heterogeneous log data containing critical infrastructure, application, and secu

arXiv:2603.29888v1 Announce Type: cross Abstract: In collaboration with Alibaba, this study leverages a large-scale field experiment to assess the impact of a g

arXiv:2603.29890v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong performance on standardized social science instruments, but the

arXiv:2603.29897v1 Announce Type: cross Abstract: Reranking is a critical component in many information retrieval pipelines. Despite remarkable progress in text

arXiv:2603.29932v1 Announce Type: cross Abstract: We explore the capability of a Large Language Model (LLM) to perform specific computations in mathematical phy

arXiv:2603.29997v1 Announce Type: cross Abstract: Analogical reasoning is a key driver of human generalization in problem-solving and argumentation. Yet, analog

arXiv:2603.30022v1 Announce Type: cross Abstract: This paper introduces a new hybrid framework that combines Reinforcement Learning (RL) and Large Language Mode

arXiv:2603.30033v1 Announce Type: cross Abstract: The pursuit of reducing the memory footprint of the self-attention mechanism in multi-headed self attention (M

arXiv:2603.30036v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approa

arXiv:2506.21458v2 Announce Type: replace Abstract: Can Vision-Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form

arXiv:2509.21035v2 Announce Type: replace Abstract: Knowledge graphs provide structured context for multi-hop question answering, but deployed systems must bala

arXiv:2510.14538v2 Announce Type: replace Abstract: Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge

arXiv:2511.10788v3 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intel

arXiv:2511.16625v2 Announce Type: replace Abstract: We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models

arXiv:2512.00818v2 Announce Type: replace Abstract: MLLMs MLLMs are beginning to appear in clinical workflows, but their ability to perform complex medical reas

arXiv:2601.13358v2 Announce Type: replace Abstract: Scale does not uniformly improve reasoning - it restructures it. Analyzing 25,000+ chain-of-thought trajecto

arXiv:2602.03006v2 Announce Type: replace Abstract: Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, c

arXiv:2403.10853v4 Announce Type: replace-cross Abstract: Online learning methods often rely on supervised data. However, under data distribution shifts, such a