Search: “pretraining”

@__JohnNguyen__ and I are presenting the Beyond Language Modeling paper as an ICML spotlight in 30 minutes at the 10:30 AM poster session! I’ll also be at the AMI Mixer on Thursday and hanging around

arXiv:2607.03715v1 Announce Type: new Abstract: Medical imaging models often degrade when deployed at new clinical sites due to differences in imaging equipment, protocols, and patient populations. Te

arXiv:2607.04139v1 Announce Type: new Abstract: Self-supervised learning (SSL) shows strong potential for cross-dataset transfer by improving feature representation and generalization. However, its ap

arXiv:2601.08828v2 Announce Type: replace-cross Abstract: Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon

arXiv:2607.04033v1 Announce Type: cross Abstract: Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, an

arXiv:2607.03723v1 Announce Type: cross Abstract: Visual policies learned from human videos, teleoperation, and robot demonstrations offer scalable motion priors, but often fail in contact-rich manipu

arXiv:2607.03524v1 Announce Type: new Abstract: We propose Perceptual Flow Matching (PFM), a simple yet effective framework for few-step generation in flow-matching models. Rather than performing velo

arXiv:2607.04557v1 Announce Type: cross Abstract: Accurate prediction of patient-specific therapeutic response from pre-treatment transcriptomes is hindered by the scarcity of matched clinical respons

arXiv:2607.02853v1 Announce Type: new Abstract: Vision Language Models (VLMs) are increasingly applied to software engineering artifacts, especially UML class diagrams whose meaning depends on visual

arXiv:2607.05207v1 Announce Type: new Abstract: Self-supervised learning (SSL) is designed to learn generic, transferable representations rather than representations optimized for a single task. Most

arXiv:2607.03732v1 Announce Type: new Abstract: Precise control over complex dynamics remains challenging for modern video generative models, as text prompts alone often cannot specify physically plau

arXiv:2607.05088v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models have achieved striking progress but still struggle to synthesize rare concepts involving unusual attribute-object p

arXiv:2607.04587v1 Announce Type: new Abstract: Robust 3D object detection in adverse weather conditions is challenging due to sensor limitations. Although combining complementary modalities such as L

arXiv:2607.03148v1 Announce Type: cross Abstract: Activation functions are considered an essential primitive for neural nonlinearity, i.e., they enable neural networks to serve as universal approximat

arXiv:2602.07341v2 Announce Type: replace Abstract: This paper focuses on the scalable robot learning for manipulation in the dexterous robot arm-hand systems, where the remote human-robot interaction

arXiv:2603.19873v2 Announce Type: replace Abstract: Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and d

arXiv:2607.04064v1 Announce Type: cross Abstract: Unsupervised syllabic tokenization aims to learn discrete syllabic tokens that capture latent linguistic content-related structure from raw speech. Re

arXiv:2607.03377v1 Announce Type: cross Abstract: The rapidly growing repository of publicly available large language models (LLMs) presents significant challenges for systematic management and quanti

arXiv:2607.03094v1 Announce Type: new Abstract: Electroencephalography (EEG) decoding for brain-computer interfaces (BCIs) faces a major challenge: substantial inter-subject variability limits effecti

arXiv:2607.03089v1 Announce Type: cross Abstract: HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remain hard to deploy: raw sensor prompts are long, clo

arXiv:2607.02840v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown promising generalization in robotic manipulation, but they still struggle with contact-rich tasks, where

arXiv:2607.03572v1 Announce Type: cross Abstract: Knowledge distillation is usually framed as a choice of what to match in the teacher - its logits, hidden features, or sample relations - which presup

arXiv:2607.03788v1 Announce Type: new Abstract: Discrete diffusion promises orders-of-magnitude faster generation than autoregressive (AR) models for sequential discrete data, yet its full potential o

arXiv:2505.15379v2 Announce Type: replace Abstract: We present the P^3 dataset, a large-scale multimodal benchmark for building vectorization, constructed from aerial LiDAR point clouds, high-resoluti

arXiv:2607.02798v1 Announce Type: new Abstract: Modern image-and-text-to-video diffusion models can synthesize highly realistic videos by iteratively denoising an initial Gaussian noise tensor conditi

arXiv:2607.04510v1 Announce Type: cross Abstract: Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.5 mode

arXiv:2603.14504v2 Announce Type: replace-cross Abstract: Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards at infer

arXiv:2606.14048v2 Announce Type: replace Abstract: World action models (WAMs) have recently shown promise in jointly modeling future observations and executable robot actions. However, most existing

arXiv:2607.02212v1 Announce Type: cross Abstract: Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph i

arXiv:2603.29466v2 Announce Type: replace-cross Abstract: Existing methods for quantifying predictive uncertainty in neural networks are either computationally intractable for large language models or

arXiv:2607.01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims req

arXiv:2607.01275v1 Announce Type: cross Abstract: Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture t

arXiv:2512.10485v2 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiv

arXiv:2607.02092v1 Announce Type: cross Abstract: Flow-matching vision-language-action policies generate robot action chunks through an iterative transport process, creating an opportunity for test-ti

arXiv:2607.02513v1 Announce Type: cross Abstract: LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal met

arXiv:2607.01401v1 Announce Type: cross Abstract: INTRODUCTION: Accurate MRI-based identification of Alzheimer's disease (AD), mild cognitive impairment (MCI), and related dementias remains challengin

arXiv:2607.01759v1 Announce Type: cross Abstract: Open-vocabulary object detection aims to localize and classify objects beyond the fixed set of categories seen dur ing training. Recent open-vocabular

arXiv:2607.01897v1 Announce Type: cross Abstract: We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards. RTA trains a

arXiv:2603.02112v2 Announce Type: replace-cross Abstract: Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We id

arXiv:2607.01823v1 Announce Type: cross Abstract: Packet loss concealment (PLC) reconstructs audio packets that are missing at the receiver, usually with a trained model whose parameters remain fixed

arXiv:2607.01674v1 Announce Type: new Abstract: In multi-source ECG deployment, models may need to incorporate new data sources when earlier raw ECGs cannot be retained or replayed. Freezing a pretrai

arXiv:2607.01455v1 Announce Type: cross Abstract: Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface between them.

arXiv:2511.05150v2 Announce Type: replace-cross Abstract: Molecular biomarker testing in pathology is often costly and tissue-consuming, limiting scalable clinical deployment. Artificial intelligence

arXiv:2506.12009v2 Announce Type: replace Abstract: Affordance grounding aims to localize where to interact with an object, a fundamental capability for embodied agents. Yet progress is bottlenecked b

arXiv:2607.00573v1 Announce Type: new Abstract: Diffusion MRI probes brain microstructure with particular sensitivity to early cerebrovascular and neurodegenerative changes. Neurite Orientation Disper

arXiv:2603.13059v2 Announce Type: replace-cross Abstract: Cost-per-click (CPC) in paid search is an auction-generated outcome shaped by a competitive landscape that is only partially observable from a