Search papers, labs, and topics across Lattice.
2
0
6
Forget predefined relationships: SceneAssistant uses visual feedback to let VLMs generate diverse and high-quality 3D scenes from open-vocabulary text prompts.
Tired of LLM judges hallucinating when evaluating long, detailed speech captions? EmoSURA offers a more reliable, audio-grounded alternative by verifying atomic perceptual units.
