Search: “pretraining”

arXiv:2604.11757v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for building general-purpose robotic agents. However, the VLA landsc

arXiv:2604.10000v1 Announce Type: new Abstract: Precise medical image segmentation is fundamental for enabling computer aided diagnosis and effective treatment planning. Traditional models that rely s

arXiv:2511.17925v3 Announce Type: replace-cross Abstract: Recent advances in whole-body robot control have enabled humanoid and legged robots to perform increasingly agile and coordinated motions. How

arXiv:2604.09693v1 Announce Type: cross Abstract: Falls are a major cause of injury and mortality among older adults, yet most incidents occur in private indoor environments where monitoring must bala

arXiv:2604.10912v1 Announce Type: new Abstract: Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise,

arXiv:2604.11529v1 Announce Type: new Abstract: Foundation models have transformed natural language processing and computer vision, and a rapidly growing literature on time-series foundation models (T

arXiv:2604.11544v1 Announce Type: cross Abstract: Structured memory representations such as knowledge graphs are central to autonomous agents and other long-lived systems. However, most existing appro

arXiv:2509.26627v2 Announce Type: replace Abstract: Designing dense rewards is crucial for reinforcement learning (RL), yet in robotics it often demands extensive manual effort and lacks scalability.

arXiv:2604.09716v1 Announce Type: cross Abstract: Deep visual recognition models are usually trained and evaluated using metrics such as loss and accuracy. While these measures show whether a model is

arXiv:2604.11564v1 Announce Type: new Abstract: Single-image super-resolution has progressed from deep convolutional baselines to stronger Transformer and state-space architectures, yet the correspond

arXiv:2602.18679v2 Announce Type: replace Abstract: Large-scale foundation models for scientific machine learning adapt to physical settings unseen during training, such as zero-shot transfer between

arXiv:2505.17682v2 Announce Type: replace-cross Abstract: Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behav

arXiv:2604.10721v1 Announce Type: cross Abstract: Natural-language Guided Cross-view Geo-localization (NGCG) aims to retrieve geo-tagged satellite imagery using textual descriptions of ground scenes.

arXiv:2604.10952v1 Announce Type: new Abstract: Selecting prototypical examples from a source distribution to represent a target data distribution is a fundamental problem in machine learning. Existin

arXiv:2604.11250v1 Announce Type: new Abstract: Face recognition embeddings encode identity, but they also encode other factors such as gender and ethnicity. Depending on how these factors are used by

arXiv:2604.08590v1 Announce Type: cross Abstract: We present AlphaLab, an autonomous research harness that leverages frontier LLM agentic capabilities to automate the full experimental cycle in quanti

arXiv:2604.09370v1 Announce Type: cross Abstract: Labelling tissue components in histology whole slide images (WSIs) is prohibitively labour-intensive: a single slide may contain tens of thousands of

arXiv:2604.06161v2 Announce Type: replace-cross Abstract: Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is

arXiv:2604.09240v1 Announce Type: new Abstract: High-Level Synthesis (HLS) compiles C/C++ into RTL, but exploring pragma-driven optimization choices remains expensive because each design point require

arXiv:2604.08837v1 Announce Type: new Abstract: Flow-based image generative models exhibit stable training and produce high quality samples when using multi-step sampling procedures. One-step generati

arXiv:2604.08574v1 Announce Type: cross Abstract: Large Genomic Foundation Models have recently achieved remarkable results and in-vivo translation capabilities. However these models quickly grow to o

arXiv:2602.10603v3 Announce Type: replace Abstract: Genomic foundation models have the potential to decode DNA syntax, yet face a fundamental tradeoff in their input representation. Standard fixed-voc

arXiv:2604.08644v1 Announce Type: new Abstract: This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integr

arXiv:2604.06832v2 Announce Type: replace Abstract: Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference

arXiv:2604.08903v1 Announce Type: new Abstract: Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromati

arXiv:2603.13842v3 Announce Type: replace-cross Abstract: End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demo

arXiv:2604.08762v1 Announce Type: cross Abstract: Understanding instructional videos requires recognizing fine-grained actions and modeling their temporal relations, which remains challenging for curr

arXiv:2604.09059v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently achieved notable progress in end-to-end autonomous driving by integrating perception, reasoning, and

arXiv:2604.08956v1 Announce Type: new Abstract: Adapting vision-language models to remote sensing imagery presents a fundamental challenge: both the visual and linguistic distributions of satellite da

arXiv:2604.09406v1 Announce Type: new Abstract: Training large language models (LLMs) is constrained by memory requirements, with activations accounting for a substantial fraction of the total footpri

arXiv:2602.01997v2 Announce Type: replace-cross Abstract: Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classific

arXiv:2604.09480v1 Announce Type: new Abstract: We present Online3R, a new sequential reconstruction framework that is capable of adapting to new scenes through online learning, effectively resolving

arXiv:2604.09100v1 Announce Type: new Abstract: We propose a multimodal, physically grounded approach for metric-scale amodal object reconstruction and pose estimation under severe hand occlusion. Unl

arXiv:2502.13388v4 Announce Type: replace Abstract: StarCraft II is a complex and dynamic real-time strategy (RTS) game environment, which is very suitable for artificial intelligence and reinforcemen

arXiv:2604.09532v1 Announce Type: cross Abstract: Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual conten

arXiv:2604.09169v1 Announce Type: new Abstract: Semi-supervised semantic segmentation in computational pathology remains challenging due to scarce pixel-level annotations and unreliable pseudo-label s

arXiv:2604.09330v1 Announce Type: cross Abstract: Recent advances in robot foundation models trained on large-scale human teleoperation data have enabled robots to perform increasingly complex real-wo

arXiv:2604.08558v1 Announce Type: cross Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically

arXiv:2604.08045v1 Announce Type: new Abstract: Adnexal mass evaluation via ultrasound is a challenging clinical task, often hindered by subjective interpretation and significant inter-observer variab

arXiv:2601.20524v2 Announce Type: replace Abstract: Zero-shot anomaly detection aims to detect and localise abnormal regions in the image without access to any in-domain training images. While recent

arXiv:2604.07282v1 Announce Type: cross Abstract: Automated face recognition has made rapid strides over the past decade due to the unprecedented rise of deep neural network (DNN) models that can be t

arXiv:2604.08260v1 Announce Type: new Abstract: Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item r

arXiv:2604.08015v1 Announce Type: new Abstract: We propose a unified objective function, termed CATMIL, that augments the base segmentation loss with two auxiliary supervision terms operating at diffe

arXiv:2604.07786v1 Announce Type: new Abstract: Talking face generation has gained significant attention as a core application of generative models. To enhance the expressiveness and realism of synthe

arXiv:2511.19365v2 Announce Type: replace-cross Abstract: Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the t

arXiv:2604.06491v1 Announce Type: cross Abstract: We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matchi