Search: “pretraining”

To train better open models, we need predictable scaling. Delphi is Marin’s first step: we pretrained many small models with one recipe, then extrapolated 300× to predict a 25B-param / 600B-token run

arXiv:2601.10931v2 Announce Type: replace Abstract: Tree canopy detection from aerial imagery is an important task for environmental monitoring, urban planning, and ecosystem analysis. Simulating real

arXiv:2604.24474v1 Announce Type: new Abstract: Molecular similarity plays a central role in ligand-based drug discovery, such as virtual screening, analog searching, and goal-directed molecular gener

arXiv:2604.22334v1 Announce Type: new Abstract: Recent advances in pretraining 3D point cloud encoders (e.g., Point-BERT, Point-MAE) have produced powerful models, whose abilities are typically evalua

arXiv:2510.05482v2 Announce Type: replace Abstract: Molecular dynamics (MD) simulations underpin modern computational drug discovery, materials science, and biochemistry. Recent machine learning model

Sapiens2 is the highest quality ViT backbone that now exists in the public domain. It was pretrained on the equivalent of 1/2 of all human images on Flickr. First public release by a large lab that is

🦤 LeWorldModel: Learning Physics from Pixels — Stable World Models with Just Two Losses World models: 1️⃣ DINO-WM: pretrained ViT encoder (from ImageNet) → features → predictor. But encoder is frozen,

arXiv:2602.12370v2 Announce Type: replace Abstract: Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of mode

arXiv:2604.10268v1 Announce Type: new Abstract: We propose EditCrafter, a high-resolution image editing method that operates without tuning, leveraging pretrained text-to-image (T2I) diffusion models

arXiv:2604.08598v1 Announce Type: cross Abstract: Text-based person search faces inherent limitations due to data scarcity, driven by stringent privacy constraints and the high cost of manual annotati

arXiv:2610.19743v1 Announce Type: new Abstract: Discriminative models are trained with task-specific objectives such as classification, detection, or representation learning, yet their practical utili

arXiv:2506.17585v4 Announce Type: replace-cross Abstract: Large language models can answer questions correctly and still hallucinate their citations. Most citation systems address this by retrieving d

arXiv:2609.37116v1 Announce Type: cross Abstract: Accurate perceptual quality assessment is essential for evaluating and optimizing spatial audio, where perceived quality depends on both signal fideli

arXiv:2609.33586v1 Announce Type: new Abstract: On NVIDIA Blackwell B200, tensor-core throughput outpaces special-function exponential throughput by more than two orders of magnitude, exposing exponen

arXiv:2609.23574v1 Announce Type: cross Abstract: In high-dimensional tabular learning, feature screening provides a lightweight, model-agnostic way to remove irrelevant features before model fitting.

arXiv:2609.22607v1 Announce Type: new Abstract: We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas, i

arXiv:2506.08641v3 Announce Type: replace-cross Abstract: Adapting vision models for time series analysis is compelling, yet all existing approaches are falling short of dedicated time series foundati

arXiv:2609.22606v1 Announce Type: new Abstract: Vision-Tactile-Language-Action (VTLA) models have demonstrated clear advantages over Vision-Language-Action (VLA) models in contact-rich manipulation. H

arXiv:2609.14926v1 Announce Type: cross Abstract: We propose a linearized Physics-Informed Neural Network (lPINN), a reduced-order neural basis method for forward and inverse differential equations. I

arXiv:2608.24115v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) can integrate long visual histories, reason under partial observability, and infer behavior from a few exampl

arXiv:2508.21041v4 Announce Type: replace-cross Abstract: Atypical mitotic figures (AMFs) indicate abnormal cell division associated with poor prognosis. Their detection remains difficult due to low p

arXiv:2608.02662v1 Announce Type: cross Abstract: Reliable forecasting of nonlinear physical systems underpins scientific discovery and engineering decision-making. Yet high-fidelity simulations are p

arXiv:2607.27919v1 Announce Type: new Abstract: Decoder-only language models entangle long-term memory and reasoning in a single parameter set, making it difficult to scale memory capacity independent

arXiv:2607.13192v1 Announce Type: new Abstract: Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approa

arXiv:2607.00249v1 Announce Type: new Abstract: New device layouts pose a challenging modeling problem due to the lack of large datasets for each specific layout. Biosignal foundation models offer a p

arXiv:2607.00777v1 Announce Type: cross Abstract: Recognizing jazz standards from audio is a challenging form of tune-level music retrieval: different performances of the same standard may vary in tem

arXiv:2509.18068v2 Announce Type: replace Abstract: Millimeter-wave radar provides robust perception in fog, smoke, dust, and low light, making it attractive for size-, weight-, and power-constrained

arXiv:2510.17700v2 Announce Type: replace Abstract: Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes, forcing sub-optimal deploym

arXiv:2605.31173v1 Announce Type: cross Abstract: Reconstructing continuous speech from non-invasive neural recordings is a fundamental problem for probing human auditory perception and building safe,

arXiv:2605.25352v1 Announce Type: cross Abstract: Deep learning models are vulnerable to adversarial perturbations, raising important concerns for safety-critical deployment. Empirical defenses can ac

arXiv:2605.20267v1 Announce Type: new Abstract: Synthetic PET images are valuable for quantitative imaging workflow development, scalable virtual imaging trials, and deep learning model training, but

arXiv:2605.19568v1 Announce Type: new Abstract: Embedding models are pivotal in industrial information retrieval systems like search and advertising. However, existing pretrained models often exhibit

arXiv:2605.13010v1 Announce Type: cross Abstract: We study image inpainting with generative diffusion models. Existing methods typically either train dedicated task-specific models, or adapt a pretrai

arXiv:2605.08276v1 Announce Type: new Abstract: Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain sh

arXiv:2605.04291v1 Announce Type: new Abstract: We present a discrete diffusion-based language model using Glauber dynamics from statistical physics. Our main insight is that instead of trying to trai

arXiv:2604.10985v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new

arXiv:2604.11576v1 Announce Type: new Abstract: Despite their impressive zero-shot abilities, vision-language models such as CLIP have been shown to be susceptible to adversarial attacks. To enhance i

arXiv:2610.19492v1 Announce Type: new Abstract: Streaming Inverse Text Normalization (ITN) is vital for converting spoken-form outputs from streaming Automatic Speech Recognition into formatted writte

arXiv:2610.11214v1 Announce Type: cross Abstract: KV-cache quantization and linear attention are two representative approaches to tackling the storage and computational costs of Transformers. KV-cache

arXiv:2610.10984v1 Announce Type: new Abstract: We present Fluid-Gen-Zero, a training-free framework for physics-aware fluid-object interaction video generation that decouples physical reasoning from

arXiv:2606.15568v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models perform well in generalist robot manipulation but remain brittle to out-of-distribution perturbations, while ful

arXiv:2610.07028v1 Announce Type: new Abstract: Diffusion-based world models can generate and predict trajectories in high-dimensional dynamical systems, but predictive accuracy does not imply that th

arXiv:2610.05649v1 Announce Type: new Abstract: We investigate the scaling laws and compute-optimal training of physiological waveform foundation models (FMs). We train Aether, a family of over one hu

arXiv:2307.12226v3 Announce Type: replace-cross Abstract: Machine learning models -- including prominent zero-shot models -- are often trained on datasets whose labels are only a small proportion of a

arXiv:2610.01425v1 Announce Type: new Abstract: Train-validation separation is the evolving difference between performance on observed training examples and a finite held-out validation set. We propos

arXiv:2609.39784v1 Announce Type: new Abstract: Can heterogeneous physical degradation systems benefit from joint pretraining and move beyond system-specific prognostics toward reusable cross-system r