NVILA: Efficient Frontier Visual Language Models
arXiv:2412.04468v3 Announce Type: replace Abstract: Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention
Knowledge catalogue
arXiv:2412.04468v3 Announce Type: replace Abstract: Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention
arXiv:2604.22815v1 Announce Type: cross Abstract: Classical vehicle dynamics contains several widely adopted misconceptions that, while intuitively appealing, may lead to inconsistencies when examined
arXiv:2602.10298v2 Announce Type: replace Abstract: This paper investigates whether LMs recruit shared computational mechanisms for general Theory of Mind (ToM) and language-specific pragmatic reasoni
arXiv:2604.23427v1 Announce Type: cross Abstract: We prove lower bounds on learning the Mobius or Liouville function with a variety of standard learning techniques, including kernel methods, noisy gra
arXiv:2604.22903v1 Announce Type: cross Abstract: The integration of quantum machine learning with classical deep learning offers promising avenues for medical image analysis by mapping data into high
arXiv:2410.15155v3 Announce Type: replace Abstract: Aiming to accelerate the training of large deep neural networks (DNN) in an energy-efficient way, analog in-memory computing (AIMC) emerges as a sol
arXiv:2604.22958v1 Announce Type: new Abstract: Preference-based argumentation frameworks (PAFs) extend Dung's approach to abstract argumentation (AAFs) by encoding preferences over arguments. Such pr
arXiv:2604.23552v1 Announce Type: cross Abstract: Diffusion models are central to modern generative modeling, and understanding how they balance memorization and generalization is critical for reliabl
arXiv:2603.18514v2 Announce Type: replace-cross Abstract: Motivated by the principle of satisficing in decision-making, we study satisficing regret guarantees for nonstationary K-armed bandits. We sho
arXiv:2510.13117v3 Announce Type: replace-cross Abstract: Masked diffusion models (MDMs) for text offer a compelling alternative to traditional autoregressive language models. Parallel generation make
arXiv:2604.23173v1 Announce Type: new Abstract: Video Situation Recognition (VidSitu) addresses the challenging problem of 'who did what to whom, with what, how, and where' in a video. It tests thorou
arXiv:2604.23599v1 Announce Type: cross Abstract: Gaussian basis functions provide an efficient and flexible alternative to spline activations in KANs. In this work, we introduce the partition-of-unit
arXiv:2604.24707v1 Announce Type: new Abstract: Doorways and passages are critical structural elements for indoor robot navigation, yet they remain underexplored in modern Visual SLAM (VSLAM) framewor
arXiv:2604.24371v1 Announce Type: cross Abstract: Cancer survival prediction from multi-omics data remains challenging because prognostic signals are high-dimensional, heterogeneous, and distributed a
arXiv:2604.24338v1 Announce Type: new Abstract: This paper evaluates an advanced jet trainer's utilization of artificial intelligence (AI)-based aircraft aerobatic maneuvers with the intention of deve
arXiv:2604.24758v1 Announce Type: cross Abstract: Adaptive programming practice often relies on fixed libraries of worked examples and practice problems, which require substantial authoring effort and
arXiv:2604.23692v1 Announce Type: cross Abstract: Audio-driven facial animation is essential for immersive digital interaction, yet existing frameworks fail to reconcile real-time streaming with high-
arXiv:2604.24415v1 Announce Type: cross Abstract: Quantitative analysis of the kinematic chain in sports motion is essential for performance evaluation and injury prevention. Conventional methods such
arXiv:2604.23372v1 Announce Type: cross Abstract: Reconstructing high-fidelity fluid dynamics from sparse temporal observations is quite challenging, mainly due to the chaotic and non-linear nature of
arXiv:2604.06094v2 Announce Type: replace-cross Abstract: Convolutional neural networks owe much of their success to hard-coding translation equivariance. Quantum convolutional neural networks (QCNNs)
arXiv:2501.02548v2 Announce Type: replace-cross Abstract: Deploying learned decision-making systems often requires transferring to new sites where the sensing pipeline differs. In such cases, observat
arXiv:2604.24524v1 Announce Type: new Abstract: Clinical fusion of Single Photon Emission Computed Tomography Myocardial Perfusion Imaging (SPECT MPI) and Computed Tomography Angiography (CTA) remains
arXiv:2510.17881v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. W
arXiv:2511.19339v2 Announce Type: replace Abstract: In computer vision, machine unlearning aims to remove the influence of specific visual concepts or training images without retraining from scratch.
arXiv:2602.03886v3 Announce Type: replace-cross Abstract: Prenatal psychological stress affects 15-25% of pregnancies and increases risks of preterm birth, low birth weight, and adverse neurodevelopme
arXiv:2604.23514v1 Announce Type: cross Abstract: The health condition of components in civil infrastructures can be described by various discrete states according to their performance degradation. In
arXiv:2604.23333v1 Announce Type: cross Abstract: Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability
arXiv:2604.24674v1 Announce Type: new Abstract: Radar offers unique advantages for localization in unstructured environments, including robustness to weather, lighting, and airborne particulates. Whil
arXiv:2604.23407v1 Announce Type: cross Abstract: Large vision-language models (VLMs) can recognize extit{what} happens in video but fail to count extit{how many} times. We introduce extbf{PushupBench
arXiv:2604.24597v1 Announce Type: cross Abstract: We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using qua
arXiv:2604.23922v1 Announce Type: cross Abstract: In this paper, we introduce the Quasi-Quadratic Gradient (QQG), a novel search direction designed to accelerate the BFGS method within the quasi-Newto
arXiv:2604.23816v1 Announce Type: cross Abstract: Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand compl
arXiv:2603.19670v3 Announce Type: replace Abstract: Nonasymptotic diffusion analyses often decompose sampling error into score estimation, continuous reverse-time propagation, discretization, and term
arXiv:2604.24230v1 Announce Type: new Abstract: Skull-base meningiomas are often characterized by favorable long-term prognosis, yet their anatomical complexity and proximity to critical neurovascular
arXiv:2604.24334v1 Announce Type: new Abstract: Standard Retrieval-Augmented Generation (RAG) chunking methods often create excessive redundancy, increasing storage costs and slowing retrieval. This s
arXiv:2508.03121v3 Announce Type: replace Abstract: Regression Mean (RegMean), an approach that formulates model merging as a linear regression problem, aims to find the optimal weights for each linea
arXiv:2604.23804v1 Announce Type: new Abstract: We generalise the reparameterization trick applied in variational autoencoders (VAEs) letting these have latent spaces of non-trivial topology - i.e. th
arXiv:2604.23443v1 Announce Type: new Abstract: Stochastic sampling strategies are widely adopted in large language models (LLMs) to balance output coherence and diversity. These heuristics are often
arXiv:2604.07533v2 Announce Type: replace-cross Abstract: Time Slotted Channel Hopping (TSCH) is a widely adopted Media Access Control (MAC) protocol within the IEEE 802.15.4e standard, designed to pr
arXiv:2603.20711v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) depl
arXiv:2604.23933v1 Announce Type: new Abstract: Developing robust and clinically reliable EEG biomarkers requires evaluation frameworks that explicitly address cross population generalization in multi
arXiv:2511.09242v2 Announce Type: replace-cross Abstract: The paper studies a geometrically robust least-squares problem that extends classical and norm-based robust formulations. Rather than minimizi
arXiv:2604.23783v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterativ
arXiv:2604.23437v1 Announce Type: cross Abstract: The global financial ecosystem confronts a critical asymmetry: while fraud syndicates operate as borderless, distributed networks, banking institution
arXiv:2604.23255v1 Announce Type: cross Abstract: Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing share
arXiv:2604.05013v2 Announce Type: replace-cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting
arXiv:2604.22948v1 Announce Type: new Abstract: History-dependent sampling can reduce long-run Monte Carlo variance by discouraging redundant revisits, but existing schemes typically encode history th
arXiv:2512.23213v3 Announce Type: replace-cross Abstract: We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for
arXiv:2604.24372v1 Announce Type: cross Abstract: LLM-guided evolutionary search has emerged as a promising paradigm for automated algorithm discovery, yet most systems track search progress primarily
arXiv:2604.24515v1 Announce Type: new Abstract: Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. It presents two key challenges: generating correct reaso
arXiv:2512.12844v2 Announce Type: replace-cross Abstract: Reliable uncertainty quantification is essential for deploying machine learning systems in high-stakes domains. Conformal prediction provides
arXiv:2604.24313v1 Announce Type: cross Abstract: Training large-scale deep neural networks effectively and stably is essential for applying deep learning across various fields. However, conventional
arXiv:2604.24109v1 Announce Type: new Abstract: Semi-supervised learning (SSL) has become a promising solution to alleviate the annotation burden of deep learning-based medical image segmentation mode
arXiv:2604.24720v1 Announce Type: new Abstract: Indonesian marketplace reviews mix standard vocabulary with slang, regional loanwords, numeric shorthands, and emoji, making lexicon-based sentiment too
arXiv:2604.23812v1 Announce Type: cross Abstract: Rootkits are among the most elusive types of malware, capable of bypassing traditional static analysis methods due to their metamorphic behavior. Sign
arXiv:2604.22825v1 Announce Type: cross Abstract: Large segmentation foundation models such as the Segment Anything Model (SAM) have reshaped promptable segmentation in natural images, and recent effo
arXiv:2604.23046v1 Announce Type: new Abstract: We argue that current definitions of machine unlearning are underspecified for second-order optimizers. We compare first-order and second-order learners
arXiv:2602.05676v2 Announce Type: replace Abstract: Recent advancements in 3D foundation models have enabled the generation of high-fidelity assets, yet precise 3D manipulation remains a significant c
arXiv:2604.24000v1 Announce Type: cross Abstract: The Laplacian operator transforms the image into its Laplacian field, which usually is sparse and satisfies a stable distribution. On the other hand,
arXiv:2602.00417v2 Announce Type: replace-cross Abstract: We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. W