Search papers, labs, and topics across Lattice.
New York University
2
0
6
A unified framework reveals how different 3D data representations and learning paradigms interact, paving the way for more efficient and effective applications in 3D vision.
Don't fully retrain your draft model after fine-tuning your LLM: EDA restores speculative decoding performance with significantly less compute by adapting only a small, private component and regenerating training data.
