20 accepted papers
Recent Video-to-Audio (V2A) methods have achieved remarkable progress, enabling the synthesis of realistic, high-quality audio. However, they struggle with fine-grained temporal control in multi-event scenarios or when visual cues are insufficient, such as small regions, off-screen sounds, or occlud
Latent visual reasoning aims to mimic human's *imagination* process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm for visual reasoning, the underlying mechanisms driving its effectiveness remain unclear. Motivated to demystify the t…
We introduce LLA, an effective intellectual property (IP) protection scheme for generative AI models. LLA leverages the synergy between hardware and software to defend against various supply chain threats, including model theft, model corruption, and information leakage. On the software side, it emb
Multi-agent 3D reconstruction, as a key technology for large-scale VR/AR, robot swarms, and digital twins, has attracted growing attention. Recent end-to-end 3D reconstruction methods achieve strong performance in single-agent scenarios, but they are difficult to directly extend to multi-agent colla
The Zero-shot Composed Image Retrieval (ZSCIR) requires retrieving images that match the query image and the relative captions.Current methods focus on projecting the query image into the text feature space, subsequently combining them with features of query texts for retrieval. However, retrieving…
The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in achieving precise grounding in complex multi-image scenarios…
In recent years, large language models (LLMs) have made significant progress in knowledge-intensive applications. However, when adapting them to specific domains, we may encounter a multi-stage continuous learning scenario, especially in cases where domain knowledge evolves rapidly.This issue severe…
Anomaly detection and localization in automated industrial manufacturing can significantly enhance production efficiency and product quality. Existing methods are capable of detecting surface defects in pre-defined or controlled imaging environments. However, accurately detecting workpiece defects i
The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct a comprehensive and systematic safety evaluation of 13 MLRMs
LiDAR-Inertial Odometry (LIO) demonstrates outstanding accuracy and stability in general low-speed and smooth motion scenarios. However, in high-speed and intense motion scenarios, such as sharp turns, two primary challenges arise: firstly, due to the limitations of IMU frequency, the error in estim…
Multimodal Sentiment Analysis (MSA) utilizes multimodal data to infer the users’ sentiment. Previous methods focus on equally treating the contribution of each modality or statically using text as the dominant modality to conduct interaction, which neglects the situation where each modality may beco…
We present a Multi-Instance Generation (MIG) task simultaneously generating multiple instances with diverse controls in one image. Given a set of predefined coordinates and their corresponding descriptions the task is to ensure that generated instances are accurately at the designated locations and…
"Implicit Neural Representation (INR) has become a popular method for representing visual signals (, 2D images and 3D scenes), demonstrating promising results in various downstream applications. Given its potential as a medium for visual signals, exploring the development of a neural blending method…
Modeling multi-variate time-series (MVTS) data is a long-standing research subject and has found wide applications. Recently, there is a surge of interest in modeling spatial relations between variables as graphs, i.e., first learning one static graph for each dataset and then exploiting the graph s…
Curriculum design is a fundamental component of education. For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication. These and other concepts must be mastered before our first algebra lesson, which also reinforces our addition and multiplicati…
The emergence of Neural Radiance Fields (NeRF) has promoted the development of synthesized high-fidelity views of the intricate real world. However, it is still a very demanding task to repaint the content in NeRF. In this paper, we propose a novel framework that can take RGB images as input and alt…
Pretrained language models are expected to effectively map input text to a set of vectors while preserving the inherent relationships within the text. Consequently, designing a white-box model to compute metrics that reflect the presence of specific internal relations in these vectors has become a c…
Event-based sensors (e.g., DVS cameras) are capable of higher dynamic range, higher temporal resolution, lower time latency, and better power efficiency compared to conventional devices (e.g., RGB cameras). However, learning from these sensors remains challenging; event-based sensors output a stream
Cable-driven continuum robots exhibit accessing and manipulation capabilities in constrained and cluttered environments that are unachievable for traditional robots composing of discrete links and joints. However, the existing continuum robots structured by non-scalable backbones are monofunctional,
As a critical sensor for high-level autonomous vehicles, LiDAR's limitations in adverse weather (e.g. rain, fog, snow, etc.) impede the deployment of self-driving cars in all weather conditions. In this paper, we model the performance of a popular 903nm ToF LiDAR under various fog conditions based o…