Search papers, labs, and topics across Lattice.
6
0
8
3
ILLUME-X achieves unprecedented quality in free-form interleaved text-image generation, setting a new benchmark for multimodal models.
Evolving hardware-aware compression techniques can outperform human designs, achieving unprecedented efficiency in deploying massive AI models.
Retrieval-augmented context boosts commit message quality, outperforming traditional LLM approaches by leveraging historical examples and user feedback.
Capturing structured relationships in images can boost open-vocabulary object detection performance by over 10% on novel categories.
Forget expensive human feedback loops: a VLM-powered reward function can efficiently align image editing diffusion models with human preferences.
Current image editing models, even closed-source ones, still fall short on complex and creative instruction-based tasks, as revealed by a new interpretable QA-based evaluation framework.
