Related papers: Brain-Inspired Capture: Evidence-Driven Neuromimet…

Our purpose is to improve performance-based animation which can drive believable 3D stylized characters that are truly perceptual. By combining traditional blendshape animation techniques with multiple machine learning models, we present…

Deep learning has achieved transformative performance across diverse domains, largely driven by large-scale and high-quality training data. In contrast, the development of brain-computer interfaces (BCIs) is fundamentally constrained by…

Findings in recent years on the sensitivity of convolutional neural networks to additive noise, light conditions and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the…

Neuromorphic devices represent an attempt to mimic aspects of the brain's architecture and dynamics with the aim of replicating its hallmark functional capabilities in terms of computational power, robust learning and energy efficiency. We…

The growing need for intelligent, adaptive, and energy-efficient autonomous systems across fields such as robotics, mobile agents (e.g., UAVs), and self-driving vehicles is driving interest in neuromorphic computing. By drawing inspiration…

Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention and are being applied to many relevant problems using Machine Learning. Despite a well-established mathematical…

$\textit{BrainForm}$ is a gamified Brain-Computer Interface (BCI) training system designed for scalable data collection using consumer hardware and a minimal setup. We investigated (1) how users develop BCI control skills across repeated…

A brain-computer interface (BCI) facilitates direct interaction between the brain and external devices. To concurrently achieve high decoding accuracy and low energy consumption in invasive BCIs, we propose a novel spiking neural network…

Medical image segmentation (MIS) aims to finely segment various organs. It requires grasping global information from both parts and the entire image for better segmenting, and clinically there are often certain requirements for segmentation…

Decoding visual experience from brain signals offers exciting possibilities for neuroscience and interpretable AI. While EEG is accessible and temporally precise, its limitations in spatial detail hinder image reconstruction. Our model…

Emerging immersive display technologies efficiently utilize resources with perceptual graphics methods such as foveated rendering and denoising. Running multiple perceptual graphics methods challenges devices with limited power and…

This work introduces a neuromorphic compression based neural sensing architecture with address-event representation inspired readout protocol for massively parallel, next-gen wireless iBMI. The architectural trade-offs and implications of…

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces. We extend recently proposed Neuro Symbolic Concept Learning…

In embodied intelligence systems, a key component is 3D perception algorithm, which enables agents to understand their surrounding environments. Previous algorithms primarily rely on point cloud, which, despite offering precise geometric…

As brain-computer interfacing (BCI) systems transition from assistive technology to more diverse applications, their speed, reliability, and user experience become increasingly important. Dynamic stopping methods enhance BCI system speed by…

Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy…

Supervised image captioning approaches have made great progress, but it is challenging to collect high-quality human-annotated image-text data. Recently, large-scale vision and language models (e.g., CLIP) and large-scale generative…

Emotion recognition,as a step toward mind reading,seeks to infer internal states from external cues.Most existing methods rely on explicit signals-such as facial expressions,speech,or gestures-that reflect only bodily responses and overlook…

Contrastive language image pretraining (CLIP) encoders have been shown to be beneficial for a range of visual tasks from classification and detection to captioning and image manipulation. We investigate the effectiveness of CLIP visual…