Search: “latent-space”

arXiv:2605.11846v1 Announce Type: new Abstract: Self-supervised learning (SSL) is often deployed under changing information, such as shorter histories, missing features, or partially observed images.

arXiv:2605.10840v1 Announce Type: cross Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architec

arXiv:2601.23087v3 Announce Type: replace Abstract: Learning long-horizon robotic manipulation requires jointly achieving expressive behavior modeling, real-time inference, and stable execution, which

arXiv:2605.08218v1 Announce Type: cross Abstract: This paper proposes latent visualization by optimization (LVO), a mechanistic interpretability technique that extends feature visualization by optimiz

arXiv:2605.09949v1 Announce Type: new Abstract: Understanding how chemical language models (CLMs) learn chemical meaning from molecular string representations, rather than only surface-level string pa

arXiv:2605.08250v1 Announce Type: cross Abstract: Recent advances in diffusion transformers (DiTs) have enabled promising single-turn image editing capabilities. However, multi-turn editing often lead

arXiv:2605.07554v1 Announce Type: cross Abstract: Protein language models are trained primarily with masked language modeling (MLM), which predicts amino-acid identities at masked positions. We ask wh

arXiv:2605.04474v1 Announce Type: new Abstract: Geometry is central to PDE-governed systems, motivating shape optimization and inversion. Classical pipelines conduct costly forward simulation with geo

arXiv:2605.03964v1 Announce Type: new Abstract: Training machine learning interatomic potentials (MLIPs) for reactive chemistry is often bottlenecked by the high cost of quantum chemical labels and th

arXiv:2605.00874v1 Announce Type: new Abstract: The rapid proliferation of AI-powered video generation systems has introduced significant challenges in content moderation, particularly with respect to

arXiv:2605.00972v1 Announce Type: cross Abstract: Earth system science is producing increasingly large, high-dimensional datasets from physics based Earth system models to AI-based weather and climate

arXiv:2505.13007v2 Announce Type: replace Abstract: The ability to accurately model random fields plays a critical role in science and engineering for problems involving uncertain, spatially-varying q

arXiv:2604.27775v1 Announce Type: cross Abstract: Shallow nanoindentation enables mechanical characterization of thin films, individual phases and other volume-constrained materials, but measured hard

arXiv:2604.26762v1 Announce Type: cross Abstract: The Probabilistic Transformer (PT) establishes that the Transformer's self-attention plus its feed-forward block is mathematically equivalent to Mean-

arXiv:2603.06752v2 Announce Type: replace Abstract: The ensemble Kalman filter (EnKF) is widely used for data assimilation in high-dimensional systems, but its performance often deteriorates for stron

arXiv:2604.25241v1 Announce Type: new Abstract: Categorical structural optimization under aleatoric uncertainty is challenging because each design variable must be selected from a finite catalog of ad

arXiv:2604.25917v1 Announce Type: cross Abstract: Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states

arXiv:2604.23016v1 Announce Type: cross Abstract: AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly,

arXiv:2604.24662v1 Announce Type: cross Abstract: Identifying the dynamical state variables of a system from high-dimensional observations is a central problem across physical sciences. The challenge

arXiv:2505.12009v2 Announce Type: replace Abstract: Expressive human pose and shape estimation (EHPS) plays a central role in digital human generation, particularly in live-streaming applications. How

arXiv:2604.23886v1 Announce Type: cross Abstract: We present a data-driven approach for physics-based, muscle-driven dexterous control that enables musculoskeletal hands to perform precise piano playi

arXiv:2604.24763v1 Announce Type: new Abstract: Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creatin

arXiv:2602.06974v2 Announce Type: replace-cross Abstract: Visual navigation for robotics is inspired by the human ability to navigate environments using visual cues and memory, eliminating the need fo

arXiv:2510.04823v2 Announce Type: replace Abstract: Generating synthetic CT (sCT) from MRI or CBCT plays a crucial role in enabling MRI-only and CBCT-based adaptive radiotherapy, improving treatment p

arXiv:2604.20902v1 Announce Type: cross Abstract: While standard flow-matching models transport noise to data uniformly, incorporating an explicit generation order - specifically, establishing coarse,

arXiv:2604.21046v1 Announce Type: new Abstract: Semi-supervised learning has emerged as a powerful paradigm for leveraging large amounts of unlabeled data to improve the performance of machine learnin

arXiv:2604.21489v1 Announce Type: cross Abstract: Multi-modal trajectory generation is essential for safe autonomous driving, yet existing diffusion-based planners suffer from high inference latency d

arXiv:2510.10417v2 Announce Type: replace-cross Abstract: Gait recognition is an important biometric for human identification at a distance, particularly under low-resolution or unconstrained environm

arXiv:2604.19087v1 Announce Type: new Abstract: We introduce Options LLM (OLLM), a simple, general method that replaces the single next-token prediction of standard LLMs with a extit{set of learned op

arXiv:2603.11024v2 Announce Type: replace Abstract: VLMs have become increasingly proficient at a range of computer vision tasks, such as visual question answering and object detection. This includes

arXiv:2604.15679v1 Announce Type: cross Abstract: Active inference, a neurally-inspired model for inferring actions based on the free energy principle (FEP), has been proposed as a unifying framework

arXiv:2604.15854v1 Announce Type: new Abstract: Lamarckian inheritance has been shown to be a powerful accelerator in systems where the joint evolution of robot morphologies and controllers is enhance

arXiv:2604.15783v1 Announce Type: new Abstract: Urban bike-sharing systems require strategic station expansion to meet growing demand. Traditional allocation approaches rely on explicit demand modelli

arXiv:2604.15153v1 Announce Type: new Abstract: Large Language Models (LLMs) incur significant computational and memory costs when processing long prompts, as full self-attention scales quadratically

arXiv:2604.14733v1 Announce Type: new Abstract: Regrasp planning is often required when one pick-and-place cannot transfer an object from an initial pose to a goal pose while maintaining grasp feasibi

arXiv:2604.14732v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for building embodied agents that ground perception and language into action.

arXiv:2604.13924v1 Announce Type: cross Abstract: Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging d

arXiv:2510.13849v3 Announce Type: replace Abstract: Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks.

arXiv:2604.13015v1 Announce Type: new Abstract: Humanoid robots promise general-purpose assistance, yet real-world humanoid loco-manipulation remains challenging because it requires whole-body stabili

arXiv:2604.12482v1 Announce Type: cross Abstract: Optimizing the body and brain of a robot is a coupled challenge: the morphology determines what control strategies are effective, while the control pa

arXiv:2604.11521v1 Announce Type: cross Abstract: We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which

arXiv:2604.09769v1 Announce Type: cross Abstract: Rare events are central to the evolution of complex many-body systems, characterized as key transitional configurations on the free energy surface (FE

arXiv:2512.06849v2 Announce Type: replace Abstract: Accurate segmentation of vertebral metastasis in CT is clinically important yet difficult to scale, as voxel-level annotations are scarce and both l

arXiv:2604.09692v1 Announce Type: new Abstract: Synthesizing realistic piano hand motions requires both precision and naturalness. Physics-based methods achieve precision but produce stiff motions; da

arXiv:2604.09527v1 Announce Type: cross Abstract: Accurately anticipating how complex, diverse scenes will evolve requires models that represent uncertainty, simulate along extended interaction chains

arXiv:2512.20033v2 Announce Type: replace Abstract: We present FlashLips, a two-stage, mask-free lip-sync system that decouples lips control from rendering and achieves real-time performance, with our