6 accepted papers
Classifier-Free Guidance (CFG) is a cornerstone of flow-matching models, significantly enhancing visual quality and prompt adherence. However, high guidance scales inherently violate the optimal transport dynamics, leading to visual artifacts and mode collapse. In this paper, we investigate the mech…
Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tu
Localization for autonomous vehicles on highways remains under-explored compared to urban roads, and state-of-the-art methods for urban scenes degrade when directly applied to highways. We identify key challenges including environment change under information homogeneity, heavy occlusion, degraded G…
Recent vision-language models (VLMs) show strong reasoning capabilities through training with reinforcement learning from verifiable rewards (RLVR). Despite their impressive capabilities, current VLMs focus on a limited range of reasoning tasks, such as mathematical and logical reasoning, due to the
Graph classification in medical imaging and drug discovery requires accuracy and robust uncertainty quantification. To address this need, we introduce Conditional Prediction ROC (CP-ROC) bands, offering uncertainty quantification for ROC curves and robustness to distributional shifts in test data. A…
The twisted and coiled polymer actuator (TCPA), promisingly used in wearable robots, soft exoskeletons and prosthesis, retains the advantages of convenience, high energy density, scalable stroke and hysteresis-free. However, as a thermal actuator, its dynamic response is still rather low, not only b