12 accepted papers
Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces highly heterogeneous trajectory distributions that undermine intent recognition stability. We present Adaptor, a few-shot framework for robust cross-ope…
We introduce FrontierCS, a benchmark of 240 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competitive programming participants and problem setters. Unlike existing benchmarks that focus on tasks with known optimal solut…
Perception systems in robotic vehicles are crucial for safe and efficient operation, providing key state estimates necessary for planning and control. However, these systems are increasingly vulnerable to perception-based attacks, such as odometry spoofing, position spoofing, obstacle hiding, and ob
This work addresses the challenge of personalizing trajectories generated in automated decision-making systems by introducing a resource-efficient approach that enables rapid adaptation to individual users' preferences. Our method leverages a pretrained conditional diffusion model with Preference La
In Federated Learning (FL), model aggregation is pivotal. It involves a global server iteratively aggregating client local trained models in successive rounds without accessing private data. Traditional methods typically aggregate the local models from the current round alone. However, due to the st…
Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. A natural concern is that during multimodal interaction, the generated hallucinations could influence the LVLMs’ subsequent generation. Thus, we…
Emotion recognition in conversation (ERC) has received extensive attention for its wide applications in recent years. Considering the actual situation, we focus on the real-time conversation scenarios, in which how to model the conversation emotion with only the historical contextual information and…
Infrared and visible image fusion aims to generate a fused image by integrating and distinguishing complementary information from multiple sources. While the cross-attention mechanism with global spatial interactions appears promising it only capture second-order spatial interactions neglecting high…
Monocular 3D human mesh estimation is an ill-posed problem characterized by inherent ambiguity and occlusion. While recent probabilistic methods propose generating multiple solutions little attention is paid to obtaining high-quality estimates from them. To address this limitation we introduce Score…
Spatial down-sampling techniques, such as strided convolution, Gaussian, and Nearest down-sampling, are essential in deep neural networks. In this study, we revisit the working mechanism of the spatial down-sampling family and analyze the biased effects caused by the static weighting strategy employ…
The blooming progress made in deep learning-based image restoration has been largely attributed to the availability of high-quality, large-scale datasets and advanced network structures. However, optimization functions such as L_1 and L_2 are still de facto. In this study, we propose to investigate…
GelSight optical tactile sensors have high-resolution and low-cost advantages and have witnessed growing adoption in various contact-rich robotic applications. Sim2Real for GelSight sensors can reduce the time cost and sensor damage during data collection and is crucial for learning-based tactile pe