16 accepted papers
Human-defined creativity is highly abstract, posing a challenge for multimodal large language models (MLLMs) to comprehend and assess creativity that aligns with human judgments. The absence of an existing benchmark further exacerbates this dilemma. To this end, we propose CreBench, which consists o
Multimodal large language models (MLLMs) have shown strong potential for building embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluation. We introduce ERGeoBench, a large-scale benchmark for vision-driven embodied geo-localization. ERGeoBench …
Embodied artificial intelligence requires a wide variety of large-scale simulated environments for development. Previous scene reconstruction approaches based on multiview images can produce high-fidelity 3D scenes but lack diversity. In contrast, existing prompt-based scene generation approaches ca
This paper introduces LAMM, an open-source framework for large-scale multi-session 3D LiDAR point cloud map merging. LAMM can automatically integrate sub-maps from multiple agents carrying LiDARs with different scanning patterns, facilitating place feature extraction, data association, and global op
Emotion recognition from EEG signals is crucial for understanding complex brain dynamics. Existing methods typically rely on static frequency bands and graph convolutional networks (GCNs) to model brain connectivity. However, EEG signals are inherently non-stationary and exhibit substantial individu
Discrete diffusion models with absorbing processes have shown promise in language modeling. The key quantities to be estimated are the ratios between the marginal probabilities of two transitive states at all timesteps, called the concrete score. In this paper, we reveal that the concrete score in a…
"Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have greatly advanced novel view synthesis, which is capable of photo-realistic rendering. However, these methods require the foundational assumption of the static scene (, consistent lighting condition and persistent object positions),…
Estimating disparities in challenging areas is difficult and limits the performance of stereo matching models. In this paper we exploit local structure information (LSI) to enhance stereo matching. Specifically our LSI comprises a series of key elements including the slant plane (parameterised by di…
Although visual navigation has been extensively studied using deep reinforcement learning, online learning for real-world robots remains a challenging task. Recent work directly learned from offline dataset to achieve broader generalization in the real-world tasks, which, however, faces the out-of-d…
Bayesian flow networks (BFNs) iteratively refine the parameters, instead of the samples in diffusion models (DMs), of distributions at various noise levels through Bayesian inference. Owing to its differentiable nature, BFNs are promising in modeling both continuous and discrete data, while simultan…
In this work, we introduce a novel multimodal descriptor, the image-assisting binary and triangle combined (iBTC) descriptor, which fuses LiDAR (Light Detection and Ranging) and camera measurements for 3D place recognition. The inherent invariance of a triangle to rigid transformations inspires us t
Ensuring safety of unmanned surface vehicles (USVs) during nearshore field operations is challenging as they face unknown risks of collision with surface and underwater obstacles. To address this problem, we propose a bio-inspired collision risk-assessment method for ensuring safe USVs operation in
Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based on a convolutional neural network (CNN) remains dominant in diffusion models. We design a simple and general ViT-based architecture (named U-ViT) for image generation with diffusion models. U-ViT is characteri…
This letter proposes a novel projectile-based mechanism to realize unmanned surface vehicle (USV) charging at berths, which is a challenging task. The proposed mechanism involves two key parts: a projectile-based launcher mechanism, and a bowl-like magnetic charger socket. The proposed mechanism pro
This paper proposes a unified diffusion framework (dubbed UniDiffuser) to fit all distributions relevant to a set of multi-modal data in one model. Our key insight is -- learning diffusion models for marginal, conditional, and joint distributions can be unified as predicting the noise in the perturb…
Automatic latching for charging in a disturbed environment for Unmanned Surface Vehicle (USVs) is always a challenging problem. In this paper, we propose a two-stage automatic latching system for USVs charging in berth. In Stage I, a vision-guided algorithm is developed to calculate an optimal latch…