Search papers, labs, and topics across Lattice.
Tongji University
3
0
8
Current multimodal humor generation struggles to maintain image relevance, contextual appropriateness, and humor quality when explicitly conditioned on different cultural contexts, but this work offers a way to improve it.
LLMs can evolve surprisingly effective and interpretable traffic signal control policies, outperforming traditional methods in critical event handling while remaining human-understandable.
Instead of discarding noisy pseudo-labels in image restoration, QualiTeacher leverages them by teaching the model to understand and even surpass the quality levels they represent.
