4988 papers
This paper proposes a novel Variational Learning framework for Gaussian Process Latent Variable Models that utilizes Stochastic Gradient Annealed Importance Sampling to overcome proposal distribution challenges in high-dimensional spaces, achieving tighter variational bounds and superior performance compared to state-of-the-art methods.
This paper introduces the Multimodal Laryngoscopic Video Analyzing System (MLVAS), a novel framework that integrates audio keyword spotting with diffusion-refined video segmentation to automatically extract key metrics and features for the objective assisted diagnosis of Vocal Fold Paralysis.
This paper explores how integrating artificial intelligence into software testing transforms the generation and validation of test cases by enhancing efficiency, accuracy, and scalability while addressing challenges related to data quality, model transparency, and the balance between automation and human oversight.
This paper challenges the prevailing assumption of Spiking Neural Networks' inherent energy superiority by introducing a rigorous, fair-comparison framework that reveals SNNs only outperform Quantized ANNs under specific low-spike-rate conditions, while demonstrating that such optimized SNNs could nearly double the battery life of devices like smartwatches.
This paper introduces a novel Coupled Oscillator Network (CON) model that overcomes key limitations in latent-space control by ensuring Lagrangian structure, global input-to-state stability, and an invertible input-force mapping, thereby enabling efficient closed-form control strategies for complex mechanical systems using only raw visual feedback.
This paper introduces BNEM, a robust diffusion-based sampler that learns from energy functions via bootstrapped noised energy matching to efficiently generate independent samples from Boltzmann distributions, outperforming existing methods on complex molecular dynamics benchmarks.
The paper proposes PiVOT, a visual prompting mechanism that leverages a pretrained CLIP foundation model to automatically generate and refine online visual prompts, thereby enhancing generic object tracking by effectively suppressing distractors through contrastive guidance.
This paper introduces a constant-lag Neural Delay Differential Equations (NDDEs) framework, inspired by the Mori-Zwanzig formalism, to effectively learn non-Markovian dynamics from partially observed data by identifying memory effects through time delays, demonstrating superior performance over existing methods like LSTMs and ANODEs across synthetic, chaotic, and experimental datasets.
The paper introduces Puppet-CNN, a framework that models convolutional layer parameters as states evolving within a learned neural ODE, enabling input-adaptive computation and significant parameter reduction by dynamically determining the effective network depth based on input complexity.
This paper proposes an input-adaptive framework for diffusion models that dynamically adjusts the generative trajectory and sampling steps for each sample based on its complexity, thereby maintaining generation quality while reducing the average number of required steps.
This paper demonstrates that competing algorithmic agents using multi-armed bandit learning can spontaneously develop "naive collusion" through action synchronicity, even without knowledge of competitors, with the likelihood of such outcomes depending critically on whether the agents employ deterministic, greedy-in-the-limit, or persistently random policies.
This paper proposes a joint optimization framework for sensing, communication, and exploration speed in lifelong SLAM systems to minimize energy consumption, validated through simulations and experiments involving LiDAR-equipped robots transmitting data to a deep learning-based cloud reconstruction center.
This paper introduces HarmonicEval, a reference-free, multi-criteria evaluation metric for vision-language models that aggregates criterion-wise scores to better align with human judgments across diverse multi-modal tasks, supported by the newly constructed MMHE benchmark containing 18,000 expert human evaluations.
This paper proposes a method that leverages pretrained vision-language models to learn compact, abstract symbolic world models from limited visual demonstrations, enabling zero-shot generalization and long-horizon planning for complex robotic tasks across novel objects, environments, and goals.
This paper proposes efficient data reduction strategies for semi-supervised adversarial training that utilize latent clustering techniques to select or generate critical boundary-adjacent samples, significantly reducing data requirements and computational costs while maintaining state-of-the-art robustness.
This paper proposes a pivot-based single-model ensemble framework that generates diverse translation candidates through pivot languages and aggregates the best ones to improve translation quality for low-resource language pairs while avoiding the high computational costs of traditional multi-model ensembles.
This paper introduces GRADIEND, a novel encoder-decoder method that utilizes model gradients to identify and rewrite specific neural network weights, effectively debiasing AI systems regarding gender, race, and religion while preserving their other capabilities.
This paper proposes a novel local search algorithm with a balanced optimization objective and provable linear convergence to efficiently identify polarized communities in signed networks, effectively addressing size imbalance and scaling to large datasets while outperforming state-of-the-art methods.
This paper demonstrates that integrating Low-Rank Adaptation (LoRA) into Federated Learning for Large Language Models significantly reduces unintended memorization of sensitive training data across diverse model sizes and domains, while maintaining performance and offering compatibility with other privacy-preserving techniques.
Prompt-SID is a self-supervised single-image denoising framework that leverages a latent diffusion-based structural representation generator and a scale replay training mechanism to preserve detailed structural information without relying on expensive paired datasets.