Related papers: Re-evaluating Position and Velocity Decoding for H…

Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output…

Vision-Language Models (VLMs) have demonstrated strong performance across various multimodal tasks, where position encoding plays a vital role in modeling both the sequential structure of textual information and the spatial structure of…

We study the task of gesture recognition from electromyography (EMG), with the goal of enabling expressive human-computer interaction at high accuracy, while minimizing the time required for new subjects to provide calibration data. To…

In visual depictions of data, position (i.e., the vertical height of a line or a bar) is believed to be the most precise way to encode information compared to other encodings (e.g., hue). Not only are other encodings less precise than…

In general, hand pose estimation aims to improve the robustness of model performance in the real-world scenes. However, it is difficult to enhance the robustness since existing datasets are obtained in restricted environments to annotate 3D…

In this paper, we study the back-end of simultaneous localization and mapping (SLAM) problem in deforming environment, where robot localizes itself and tracks multiple non-rigid soft surface using its onboard sensor measurements. An…

Brain encoding and decoding aims to understand the relationship between external stimuli and brain activities, and is a fundamental problem in neuroscience. In this article, we study latent embedding alignment for brain encoding and…

For certain manipulation tasks, object pose estimation from head-mounted cameras may not be sufficiently accurate. This is at least in part due to our inability to perfectly calibrate the coordinate frames of today's high degree of freedom…

Errors in surface code have typically been decoded by Minimum Weight Perfect Matching (MWPM) based method. Recently, neural-network-based Machine Learning (ML) techniques have been employed for this purpose. Here we propose a two-level (low…

With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-trained models are optimized for next-token prediction and…

This paper presents an approach for Evoked Expressions from Videos (EEV) challenge, which aims to predict evoked facial expressions from video. We take advantage of pre-trained models on large-scale datasets in computer vision and audio…

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses…

Semantic segmentation of satellite imagery is crucial for Earth observation applications, but remains constrained by limited labelled training data. While self-supervised pretraining methods like Masked Autoencoders (MAE) have shown…

Semantic segmentation, which refers to pixel-wise classification of an image, is a fundamental topic in computer vision owing to its growing importance in robot vision and autonomous driving industries. It provides rich information about…

Positional encodings enable Transformers to incorporate sequential information, yet their theoretical understanding remains limited to two properties: distance attenuation and translation invariance. Because natural language lacks purely…

Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood. In encoder-decoder arithmetic models, we…

Decoding visual stimuli from neural recordings is a critical challenge in the development of brain-computer interfaces (BCIs). Although recent EEG-based decoding approaches have made progress in tasks such as visual classification,…

Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods struggle to capture both the stochastic nature of neural…

Vision-language Models (VLMs) have shown remarkable capabilities in advancing general artificial intelligence, yet the irrational encoding of visual positions persists in inhibiting the models' comprehensive perception performance across…

Accurate and responsive myoelectric prosthesis control typically relies on complex, dense multi-sensor arrays, which limits consumer accessibility. This paper presents a novel, data-efficient deep learning framework designed to achieve…