Search: “models”

arXiv:2605.10159v1 Announce Type: new Abstract: jNO (jax Neural Operators) is a JAX-native library for neural operators and foundation models with unified support for both data-driven and physics-info

arXiv:2605.08632v1 Announce Type: cross Abstract: Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verifi

arXiv:2605.09305v1 Announce Type: cross Abstract: Interactive assessments generate sequential process data that are not well handled by conventional item response models. Existing MDP-based measuremen

arXiv:2603.26089v2 Announce Type: replace-cross Abstract: The ability to represent oneself and others as agents with knowledge, intentions, and belief states that guide their behavior - Theory of Mind

arXiv:2605.10129v1 Announce Type: new Abstract: Large language models (LLMs) rely on web-scale corpora for pre-training. The noise inherent in these datasets tends to obscure meaningful patterns and u

arXiv:2603.13224v2 Announce Type: replace-cross Abstract: Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured r

arXiv:2605.07105v1 Announce Type: cross Abstract: Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common

arXiv:2602.04774v2 Announce Type: replace-cross Abstract: Setting the learning rate (LR) for a deep learning model is a critical part of successful training. Choosing LRs is often done empirically wit

arXiv:2605.07013v1 Announce Type: new Abstract: Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregres

arXiv:2511.03182v2 Announce Type: replace-cross Abstract: Large language models (LLMs) for code are increasingly used in software development, but they remain static after pretraining while APIs and s

arXiv:2605.07579v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models hinges on baseline estimation for variance reduction, but existing ap

arXiv:2510.01641v3 Announce Type: replace Abstract: Recent advancements in image motion deblurring, driven by CNNs and transformers, have made significant progress. Large-scale pre-trained diffusion m

arXiv:2602.10144v2 Announce Type: replace-cross Abstract: Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoreti

arXiv:2605.02545v1 Announce Type: new Abstract: Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strateg

arXiv:2605.03802v1 Announce Type: cross Abstract: ML climate model emulators are useful for scenario planning and adaptation, allowing for cost-efficient experimentation. Recently, the diffusion model

arXiv:2605.01799v1 Announce Type: new Abstract: World models have made significant progress in modeling dynamic environments; however, most embodied world models are still restricted to 2D representat

arXiv:2605.01711v1 Announce Type: new Abstract: Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process

arXiv:2605.01191v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced the field of embodied manipulation by harnessing broad world knowledge and strong generalization. Howe

arXiv:2605.01364v1 Announce Type: new Abstract: The building energy community lacks a foundational thermal model, i.e., a single pretrained model capable of generalizing across diverse buildings, clim

arXiv:2605.00431v1 Announce Type: cross Abstract: Although recent video-to-audio (V2A) models excelled at synthesizing semantically plausible sounds from visual inputs, they do not explicitly model ro

arXiv:2604.27453v1 Announce Type: new Abstract: Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, exi

arXiv:2604.27155v1 Announce Type: new Abstract: Model merging aims to combine multiple models into one without additional training. Naive parameter-space averaging can be fragile under architectural s

arXiv:2604.27889v1 Announce Type: new Abstract: Semantic segmentation and change detection are two fundamental challenges in remote sensing, requiring models to capture either spatial semantics or tem

arXiv:2604.27629v1 Announce Type: new Abstract: We present WaferSAGE, a framework for wafer defect visual question answering using small vision-language models. To address data scarcity in semiconduct

arXiv:2604.26772v1 Announce Type: new Abstract: Recent methods demonstrate that large-scale pretrained models, such as CLIP vision transformers, effectively detect AI-generated images (AIGIs) from uns

arXiv:2604.26934v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that

arXiv:2604.24775v1 Announce Type: cross Abstract: We present a Mixture-of-Experts-based foundation model applied to the GlueX DIRC detector at Jefferson Lab, demonstrating its utility as a unified fra

arXiv:2603.29844v2 Announce Type: replace-cross Abstract: The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). Howeve

arXiv:2512.03043v3 Announce Type: replace Abstract: Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs).

arXiv:2604.22847v1 Announce Type: new Abstract: We introduce Dream-Cubed, a large-scale dataset of Minecraft worlds at voxel resolution, and a family of models using cubes as powerful compositional un

arXiv:2504.18576v2 Announce Type: replace Abstract: This paper presents DriVerse, a generative model for simulating navigation-driven driving scenes from a single image and a future trajectory. Previo

arXiv:2501.02673v4 Announce Type: replace Abstract: Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to effectively determin

arXiv:2603.28258v2 Announce Type: replace-cross Abstract: Categorical perception (CP) -- enhanced discriminability at category boundaries -- is among the most studied phenomena in perceptual psycholog

arXiv:2604.21083v1 Announce Type: cross Abstract: Third-party Large Language Model (LLM) API gateways are rapidly emerging as unified access points to models offered by multiple vendors. However, the

arXiv:2511.17085v3 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) as tool-using agents causes their alignment training to manifest in new ways. Recent work finds

arXiv:2509.26010v2 Announce Type: replace Abstract: Second-order PDE models have been widely used for suppressing multiplicative noise, but they often introduce blocky artifacts in the early stages of

arXiv:2604.17706v1 Announce Type: new Abstract: Visual-Language-Action (VLA) models represent a paradigm shift in embodied AI, yet existing frameworks often struggle with imprecise spatial perception,

arXiv:2510.24235v3 Announce Type: replace Abstract: Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large la

arXiv:2506.01770v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved tremendous success in various tasks, yet concerns about their safety and security have emerged. In

arXiv:2604.18058v1 Announce Type: new Abstract: We introduce Sonata, a compact latent world model for six-axis trunk IMU representation learning under clinical data scarcity. Clinical cohorts typicall

arXiv:2604.16170v1 Announce Type: new Abstract: We introduce neuralCAD-Edit, the first benchmark for editing 3D CAD models collected from expert CAD engineers. Instead of text conditioning as in prior

arXiv:2604.13354v1 Announce Type: cross Abstract: The discovery of inorganic crystal structures with targeted properties is a significant challenge in materials science. Generative models, especially

arXiv:2604.14152v1 Announce Type: cross Abstract: Ambient AI 'scribe' systems promise to reduce clinical documentation burden, but automatic speech recognition (ASR) errors can remain unnoticed withou

arXiv:2602.03295v2 Announce Type: replace Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities. However, their deployment is hindered by s

arXiv:2604.13594v1 Announce Type: cross Abstract: Binary droplet collisions are ubiquitous in dense sprays. Traditional deterministic models cannot adequately represent transitional and stochastic beh

arXiv:2603.28554v2 Announce Type: replace Abstract: Visual document understanding typically requires separate retrieval and generation models, doubling memory and system complexity. We present Hydra,