Search papers, labs, and topics across Lattice.
Hong Kong University of Science and Technology
5
0
7
Augmenting images from a model's own failures can lead to substantial performance boosts in multimodal tasks, outperforming conventional augmentation techniques.
HOMIE redefines video personalization by seamlessly integrating inter- and intra-subject inputs, achieving unprecedented fidelity and interaction accuracy.
Expressiveness preservation in speech-to-speech translation remains a significant hurdle, with systems scoring poorly on emotional and nonverbal fidelity despite achieving high translation accuracy.
UCE enables LLM agents to evolve their knowledge dynamically, achieving a staggering 96.3% success rate in complex tasks by leveraging a structured experience library.
LLMs can be dissected like never before using Blackbird Language Matrices, a new task revealing if they're truly grasping linguistic structure or just pattern-matching.
