Search: “latent-space”

arXiv:2608.05806v1 Announce Type: cross Abstract: While standard Next-Token Prediction (NTP) lays the foundation of language model pre- training, its teacher-forced training paradigm may not be optima

arXiv:2608.06125v1 Announce Type: new Abstract: Latent reward models can supervise visual diffusion models without decoding intermediate states into pixel space. This makes alignment with human prefer

arXiv:2608.03701v1 Announce Type: cross Abstract: World-action modeling has emerged as a promising paradigm for robotic control, as it empowers models to go beyond reacting to observations and anticip

arXiv:2608.03165v1 Announce Type: cross Abstract: Invisible image watermarks are increasingly used for deepfake detection and provenance tracking, where they must survive not only incidental distortio

arXiv:2608.00530v1 Announce Type: new Abstract: Infrared-visible image fusion under realistic degradation scenarios is a challenging task, as degradations not only cause a loss of reliable modality-sp

arXiv:2607.28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space. However, the decision boun

arXiv:2607.28760v1 Announce Type: cross Abstract: As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation

arXiv:2607.26639v1 Announce Type: cross Abstract: A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% def

arXiv:2607.26504v1 Announce Type: new Abstract: Many discrete reasoning tasks, such as code generation, are inherently non-causal: programmers move between high-level structure and local details, a pr

Everyone is talking about Kimi K3, but if you jump straight into the technical report, you’ll quickly realize it’s standing on years of research -- just like any breakthrough is! If you want to unders

arXiv:2606.19610v2 Announce Type: replace-cross Abstract: We study causal discovery from observational and interventional regimes when latent variables may affect the measured system. Our first algori

arXiv:2607.22430v1 Announce Type: new Abstract: Learning world models that infer environment dynamics from high-dimensional observations and predict outcomes under candidate actions is central to plan

arXiv:2607.20345v1 Announce Type: cross Abstract: Closing the gap between benchmark performance and reliable real-world operation remains a central challenge for Vision-Language-Action (VLA) humanoid

arXiv:2607.19120v1 Announce Type: new Abstract: Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models

arXiv:2607.11943v1 Announce Type: cross Abstract: Long-horizon physics-based simulations of battery degradation provide mechanistic insight but remain computationally expensive, limiting their use for

arXiv:2607.12922v1 Announce Type: cross Abstract: Stochastic-process models are, as a rule, far easier to simulate than to condition. Non-linear observations, non-Gaussian likelihoods, black-box infor

arXiv:2607.08724v1 Announce Type: new Abstract: Human decision-making is highly flexible -- some actions are taken immediately; others require longer deliberation. Language models have exhibited a sim

arXiv:2607.07720v1 Announce Type: cross Abstract: Sleep physiology arises from the coordinated dynamics of the central nervous system (CNS) and autonomic nervous system (ANS), as reflected by multimod

arXiv:2607.06348v1 Announce Type: new Abstract: We introduce a physics-informed framework for learning finite-dimensional embeddings of solution families of partial differential equations. The method

arXiv:2607.02537v1 Announce Type: cross Abstract: Jamming and spoofing pose significant threats to wireless and satellite navigation by disrupting radio-frequency (RF) signals and compromising availab

arXiv:2607.05373v1 Announce Type: new Abstract: 3D reconstruction and generation are commonly tackled by separate paradigms: pixel-based regression for reconstruction, and latent diffusion for generat

arXiv:2607.01804v1 Announce Type: new Abstract: Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence. To reduce policy-call frequency while pr

arXiv:2607.00461v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens whi

arXiv:2606.32020v1 Announce Type: new Abstract: Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: T

arXiv:2606.30190v1 Announce Type: cross Abstract: Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem

arXiv:2304.11171v5 Announce Type: replace-cross Abstract: To overcome the limitations of point-based inputs, overly fine computation and limited adaptability in existing artificial intelligence method

arXiv:2606.29173v1 Announce Type: new Abstract: Touch resolves the physical-property ambiguity left by vision: exploratory contact recovers shape, texture, compliance, and material, and visuo-haptic o

arXiv:2606.27897v1 Announce Type: new Abstract: We present a design rationale, embedding model, and interactive visual-analysis system for exploring large wristwatch collections through heterogeneous

arXiv:2606.28127v1 Announce Type: cross Abstract: The AI community has framed the relationship between large language models (LLMs) and world models as a dichotomy: LLMs predict tokens; world models s

arXiv:2606.24982v1 Announce Type: new Abstract: Modeling and sampling from the underlying distribution of asynchronous event sequences are crucial in various real-world applications, including social

arXiv:2606.21509v1 Announce Type: new Abstract: End-to-end autonomous driving systems tightly couple perception and decision-making through latent representations. Consequently, updates to perception

arXiv:2606.23079v1 Announce Type: new Abstract: Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs

arXiv:2606.20878v1 Announce Type: new Abstract: Synthetic tabular data enables microdata sharing in regulated domains, yet deploying continuous-time generative models requires balancing analytical uti

arXiv:2507.23534v3 Announce Type: replace-cross Abstract: Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience

arXiv:2603.12261v2 Announce Type: replace-cross Abstract: Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due

arXiv:2606.10572v1 Announce Type: new Abstract: External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal

arXiv:2606.08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation

arXiv:2606.09432v1 Announce Type: new Abstract: Modeling interacting dynamical systems requires capturing spatial interactions alongside long-range temporal dependencies. Graph neural networks (GNNs)

arXiv:2510.06492v2 Announce Type: replace Abstract: Latent world models are a promising approach for learning state representations and dynamics directly from high-dimensional observations, enabling r

arXiv:2602.15287v2 Announce Type: replace Abstract: Text-to-video generation is expensive, so only a few samples are typically produced per prompt. In this low-sample regime, maximizing the value of e

arXiv:2603.21510v3 Announce Type: replace-cross Abstract: This paper addresses the fusion of a pair of spatially unregistered hyperspectral image (HSI) and multispectral image (MSI) covering roughly o

arXiv:2606.07473v1 Announce Type: cross Abstract: Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconne

arXiv:2606.05711v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks

arXiv:2606.05173v1 Announce Type: new Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are st

arXiv:2606.04310v1 Announce Type: new Abstract: Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essenti

arXiv:2606.04092v1 Announce Type: new Abstract: Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution. When prior-data pairs are coupled via o