Frontier Research Intelligence
Preparing the latest research view.
Browse
Search and filter the research library by collection and research area. Results are URL-driven for shareable views.
Controlling the Lipschitz constant of a neural network is a standard way to promote robustness and stability. Most existing constraining strategies are designed for Euclidean spaces. In this work, we construct and analyze a class of 1 Lipschitz neural networks on Hadamard manifolds. Our layers are of gradient descent type, $1$ Lipschitz, and quasi $α$ firmly nonexpansive. The core building blocks of the proposed a...
Diffusion based methods have achieved remarkable empirical success in solving inverse problems. However, many existing posterior samplers either lack rigorous theoretical guarantees or incur substantial computational overhead. We propose a simple and efficient algorithm, called \pddim, for solving linear inverse problems with diffusion priors via a DDIM type sampler. Our method requires only lightweight, coordinat...
Associative emotional learning enables organisms to adaptively link pleasant or unpleasant outcomes to the presence of predictive stimuli. Whereas computational models such as the Rescorla Wagner model have shed light on this important function, the limitations of these models are also known, especially when they are applied to neural data. The advent of deep neural networks has opened another avenue for modeling ...
In the primate visual system, center preferring cortical populations have higher spatial resolution and overlap face and word selective regions while periphery preferring populations have lower spatial resolution and overlap scene selective regions. This "eccentricity bias" may reflect differential task relevance: central vision may better support fine grained tasks like face recognition and reading, while periphe...
Detecting staypoints from raw trajectory data is fundamental to numerous spatial computing applications. This process transforms raw numeric sequences of geolocations into semantically meaningful locations, such as homes, workplaces, or restaurants. Despite its importance for semantic trajectory analysis, staypoint detection lacks standard benchmarks, and existing algorithms have never been systematically evaluate...
Controlling dynamical systems in real time across multiple scenarios is critical to enabling adaptive control strategies, ensuring stability and efficiency. However, to tailor control actions in response to varying scenarios, traditional optimal control problems typically require several system simulations, which are often computationally demanding due to the high dimensionality of the underlying spatio temporal d...
Motor imagery (MI) based brain computer interfaces (BCIs) rely on accurate decoding of electroencephalography (EEG) signals. However, the non stationary nature of EEG signals and the complex relationships among discriminative patterns make MI classification a challenging task. To address these issues, this paper proposes a Multi Scale Convolutional Attention Guided Capsule Network (MSC AG CapsNet) for MI EEG class...
This paper addresses multi objective kinodynamic planning in environments with stochastic hybrid adversaries that probabilistically transition to adversarial modes based on the ego state. The goal is to construct the Pareto front of paths that trade off execution cost and the probability of safety constraint violation (risk). Existing chance constrained planners evaluate risk over open loop trajectories, yielding ...
Video models absorb rich priors over how the visual world moves, interacts, and responds to contact, making them promising substrates for robotic world modeling. The central challenge is how to communicate action to such models in a form aligned with the visual space in which they learned these interaction priors, yet still grounded in physical manipulation. We introduce Masked Visual Actions, a pixel space contro...
Supervised learning models in the predictive maintenance field are regularly trained on highly imbalanced industrial datasets: machine failures occur rarely but have a disproportionate effect on operations. In addition to the clear class disparity, failure data are typically non homogeneous, with different failure modes arising from distinct physical processes and exhibiting a multimodal distribution across minori...
Introduction/Objective Reliable identification of individuals from physiological signals is an active research direction in biometrics. Electroencephalography (EEG) is one such modality because brain signals carry individual specific patterns. This study investigates whether a deep learning–based EEG identification framework can achieve reliable closed set individual identification on a 109 subject benchmark under...
INTRODUCTION AND AIMS: Primary burning mouth syndrome (pBMS) is a chronic orofacial pain disorder characterized by persistent oral burning sensations with clinically normal oral mucosa, frequently accompanied by comorbid psychological distress and impaired quality of life. The underlying neurobiological mechanisms of pBMS remain poorly elucidated, and existing structural neuroimaging studies have yielded inconsist...
This paper considers a multi environment factor model in which high dimensional covariates are collected from heterogeneous environments, with auxiliary labels available in a subset of these environments. The joint distribution of the covariates may vary across environments, whereas the latent structure is decomposed into invariant factors with shared loadings and heterogeneous factors with environment specific lo...
PPO and the GRPO baseline studied here use clipped surrogate objectives whose favorable direction saturation introduces an abrupt change in the scalar objective's derivative. We ask whether Output Reset (OR), a smooth one sided saturation rule, offers a useful alternative for large language model post training. PPO OR and GRPO OR replace the clipped policy term with an OR squared margin loss in rollout relative to...
Vision language action (VLA) models have achieved impressive generalization in robotic manipulation, and recent memory augmented VLAs have relaxed the Markovian assumption by conditioning on past images or language summaries. Vision based memory approaches address this by conditioning on sampled past image frames, but they are computationally expensive and fundamentally limited when temporal events are visually am...
Massive cosmological correlators exhibit a rich hypergeometric structure already at tree level, reflecting the distorted propagation of particles in de Sitter spacetime. In this paper, we reveal that this apparent complexity conceals a remarkably simple underlying mathematical structure. Using the spectral representation, we compute arbitrary tree level correlators of scalar fields with generic masses and show tha...
<p>Qualia – the vivid hues of subjective experience – emerge from an irreversible neural alchemy. Objective sensory data streams into the brain, where amygdala and hippocampus forge it into private phenomenology through profound process dualism. Brain computer interfaces capture upstream signals with stunning precision yet hit an »epistemic firewall«: the downstream qualia remain sealed, their essence lost i...
Modern generative models typically rely on an adversarial critic, a prescribed noise to data path, or an autoregressive factorization. Instead, we show that a proper distributional energy can induce sample level motion and provide direct regression supervision for a one step generator. Three Body Scattering Modeling (TBSM) for generation turns the energy distance into a constant size per projectile interaction: ea...
Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning. Modern robot policies either compress each observation into a single global token, or rely on visual backbones trained from scratch, sacrificing both fine grained spatial detail and the benefits of large scale visual pre training. While there exist policies that do operate on dense patch fea...
Seamless human robot interaction (HRI) requires a number of perceptual and motor abilities from the robot, one of them being the imitation of human gestures. Humanoid robots have an advantage in HRI thanks to their anthropomorphic features. In this work, we develop a system for imitation of human arm gestures by the semi humanoid robot NICO based on analytical geometry and a pretrained MediaPipe pose estimation mo...
