19 accepted papers
Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly inject numerical camera parameters into the diffusion backbone often fail to bridge the gap between abstract coordinates and visual content, leading …
Distilling knowledge from human demonstrations is a promising way for robots to learn and act. Existing methods, which often rely on coarsely-aligned video pairs, are typically constrained to learning global or task-level features. As a result, they tend to neglect the fine-grained frame-level dynam
Spatial multi-modal omics technologies have transformed biological research by enabling the simultaneous profiling of gene expression, protein abundance, and chromatin accessibility within their native spatial contexts. Despite these advances, accurately clustering rare cell types remains a major ch
Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based agents to accumulate semantic drift and correlation-driven errors. We argue that long-video reasoning should begin not with reactive retr
Expressive motion planning for Aerial Manipulators (AMs) is essential for tackling complex manipulation tasks, yet achieving coupled trajectory planning adaptive to various tasks remains challenging, especially for those requiring aggressive maneuvers. In this work, we propose a novel whole-body int…
Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with many approaches building upon the framework that maintains a p…
Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer’s bias towards the most recent task. Traditionally, methods have rel…
Workspace limitations restrict the operational capabilities and range of motion for systems with robotic arms. Maximizing workspace utilization has the potential to provide better solutions for aerial manipulation tasks, increasing the system’s flexibility and operational efficiency. In this paper,
Handling complex or nonlinear motion patterns has long posed challenges for video frame interpolation. Although recent advances in diffusion-based methods offer improvements over traditional optical flow-based approaches, they still struggle to generate sharp, temporally consistent frames in scenari…
Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When directly applied to the IMD task, M-LLMs often produce reasoning texts that suffer from hallucinations and overthinking. To…
Multimodal Large Language Models (MLLMs) have made significant advancements in recent years, with visual features playing an increasingly critical role in enhancing model performance. However, the integration of multi-layer visual features in MLLMs remains underexplored, particularly with regard to…
Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however, is largely driven by empirical convention rather than principled analysis. While prior studies suggest that different V
Large Language Models (LLMs) have achieved notable success in commonsense reasoning tasks, benefiting from their extensive world knowledge acquired through extensive pretraining. While approaches like Chain-of-Thought (CoT) have shown promise in enhancing LLMs’ reasoning capabilities, mitigating the…
Recently, methods have been proposed for 3D <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">open-vocabulary</i> semantic segmentation. Such methods are able to segment scenes into arbitrary classes based on text descriptions provided during runtime.
"Current research on continual learning mainly focuses on relieving catastrophic forgetting, and most of their success is at the cost of limiting the performance of newly incoming tasks. Such a trade-off is referred to as the stability-plasticity dilemma and is a more general and challenging problem…
In recent years, multimodal large language models (MLLMs) have attracted widespread attention from both industry and academia. Based on the integration position, MLLMs can be categorized into external and internal fusion architectures, with the former being more predominant. However, there remains c…
Bioprinting is a promising fabrication technique to create medical devices for the human body in vivo or in vitro. However, the existing in-vivo bioprinting methods impose various prerequisites, such as a large incision on the human skin, to make the printing nozzle close to internal organs. Herein,
Most existing methods for unsupervised domain adaptation (UDA) rely on a shared network to extract domain-invariant features. However, when facing multiple source domains, optimizing such a network involves updating the parameters of the entire network, making it both computationally expensive and c…
Vision-Language Pre-training (VLP) has been shown to be an efficient method to improve the performance of models on different vision-and-language downstream tasks. Substantial studies have shown that neural networks may be able to learn some general rules about language and visual concepts from a la…