7 accepted papers
Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual \perception to improve \accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a probing experiment, we reveal a severe \confidence miscalibra
Long-video understanding remains challenging due to extreme temporal redundancy, sparse yet decisive events, and the instability of long-horizon reasoning in visual-language models (VLMs). Existing agent-based methods invoke external micro-tools but remain static, repeatedly rebuilding long chains o
In this work, we propose a diffusion-based method for 3D-aware image composition. Previous approaches have focused on 2D-view image composition, which limits their handling of complex 3D spatial relationships. Consequently, they are not well-suited for applications requiring precise 3D object contr
Sarcasm detection is a crucial yet challenging Natural Language Processing task. Existing Large Language Model methods are often limited by single-perspective analysis, static reasoning pathways, and a susceptibility to hallucination when processing complex ironic rhetoric, which impacts their accur
Point cloud registration is a fundamental task in 3D vision, which plays an important role in various fields but faces challenges in geometrically weak or repetitive scenes. Traditional geometric-based methods struggle in these cases, while recent multimodal approaches improve robustness in weak sce
To address the issues of tracking trajectory loss caused by small object size, frequent view angle changes and object occlusion in the multi-object tracking task of Unmanned Aerial Vehicle (UAV), in this paper, we propose a multi-object tracker for UAV based on multi-frame feature fusion. First, in…
Invertible neural networks based on Coupling Flows (CFlows) have various applications such as image synthesis and data compression. The approximation universality for CFlows is of paramount importance to ensure the model expressiveness. In this paper, we prove that CFlows}can approximate any diffeom…