Stay updated with the latest research and technology news
arXiv:2602.01984v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as...
arXiv:2602.01986v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support heterogeneous tasks within a single interface, requiring users to form, update, and act upon...
arXiv:2602.01990v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually expand their...
arXiv:2602.01991v1 Announce Type: new Abstract: Diffusion models emerged as a leading approach in text-to-image generation, producing high-quality images from textual descriptions. However, attempting to achieve...
arXiv:2602.01992v1 Announce Type: new Abstract: Analogy is a central faculty of human intelligence, enabling abstract patterns discovered in one domain to be applied to another....
arXiv:2602.01995v1 Announce Type: new Abstract: Conversational diagnosis requires multi-turn history-taking, where an agent asks clarifying questions to refine differential diagnoses under incomplete information. Existing approaches...
arXiv:2602.01996v1 Announce Type: new Abstract: Deep neural networks (DNNs) have become indispensable in many real-life applications like natural language processing, and autonomous systems. However, deploying...
arXiv:2602.01997v1 Announce Type: new Abstract: Recent works have shown that layer pruning can compress large language models (LLMs) while retaining strong performance on classification benchmarks...
arXiv:2602.01999v1 Announce Type: new Abstract: R1-style LLMs have attracted growing attention for their capacity for self-reflection, yet the internal mechanisms underlying such behavior remain unclear....
arXiv:2602.02000v1 Announce Type: new Abstract: Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture...
arXiv:2602.02001v1 Announce Type: new Abstract: Quantization Error Reconstruction (QER) reduces accuracy loss in Post-Training Quantization (PTQ) by approximating weights as $\mathbf{W} \approx \mathbf{Q} + \mathbf{L}\mathbf{R}$,...
arXiv:2602.02002v1 Announce Type: new Abstract: World models have demonstrated significant promise for data synthesis in autonomous driving. However, existing methods predominantly concentrate on single-modality generation,...
arXiv:2602.02003v1 Announce Type: new Abstract: This paper presents MLH-ALE, a monolithic localized high-order arbitrary Lagrangian-Eulerian finite element method for multi-scale fluid-structure interaction (FSI). The framework...
arXiv:2602.02004v1 Announce Type: new Abstract: Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode...
arXiv:2602.02005v1 Announce Type: new Abstract: Domain-specialized FPGAs have delivered unprecedented performance for low-latency inference across scientific and industrial workloads, yet nearly all existing accelerators assume...
arXiv:2602.02006v1 Announce Type: new Abstract: Precise localization with respect to a set of objects of interest enables mobile robots to perform various tasks. With the...
arXiv:2602.02007v1 Announce Type: new Abstract: Agent memory systems often adopt the standard Retrieval-Augmented Generation (RAG) pipeline, yet its underlying assumptions differ in this setting. RAG...
arXiv:2602.02009v1 Announce Type: new Abstract: Neuro-symbolic systems aim to combine the expressive structure of symbolic logic with the flexibility of neural learning; yet, generative models...
arXiv:2602.02010v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) often suffer from \emph{overthinking}, a phenomenon in which redundant reasoning steps are generated after a correct...
arXiv:2602.02013v1 Announce Type: new Abstract: We introduce SNAP (Self-coNsistent Agreement Principle), a self-supervised framework for robust computation based on mutual agreement. Based on an Agreement-Reliability...
arXiv:2602.02014v1 Announce Type: new Abstract: Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive...
arXiv:2602.02015v1 Announce Type: new Abstract: Domain generalization (DG) aims to learn predictive models that can generalize to unseen domains. Most existing DG approaches focus on...
arXiv:2602.02016v1 Announce Type: new Abstract: Shampoo is one of the leading approximate second-order optimizers: a variant of it has won the MLCommons AlgoPerf competition, and...
arXiv:2602.02018v1 Announce Type: new Abstract: Factual hallucination remains a central challenge for large language models (LLMs). Existing mitigation approaches primarily rely on either external post-hoc...