Search papers, labs, and topics across Lattice.
5
0
10
3
Achieving synchronized audio-visual generation and trajectory control, EchoWM sets a new standard for immersive media experiences in generative models.
MSEditor achieves unprecedented consistency in multi-shot video editing, outperforming existing methods by effectively managing identity drift and temporal coherence.
Fine-tuning compact open-weight LLMs can outperform proprietary models in coding complex student metaphor responses, revolutionizing educational assessment.
Synthesized egocentric videos can elevate real-robot task success rates by over 10% through enhanced training data.
Achieve significantly more accurate text and formula rendering with a training-free agentic workflow that injects glyph templates into latent spaces and attention maps of text-to-image models.
