Search papers, labs, and topics across Lattice.
6
0
7
Autoregressive video pretraining unlocks the full potential of long contexts for real-time robot control, boosting success rates by 15% and enabling complex manipulation previously impossible.
Treating all latent tokens identically bottlenecks multimodal test-time compute鈥攄isentangling hidden-state updates into visual-grounding and high-entropy reasoning channels beats standard output-space search under matched sample budgets.
JoyAI-Video-Edit achieves real-time video editing at 30 FPS while maintaining high fidelity and temporal consistency, outperforming traditional streaming editors.
IV-CoT reveals that separating structural planning from appearance rendering can dramatically enhance the fidelity of text-to-image generation.
Bidirectional interaction between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables a unified multimodal model to achieve spatial intelligence beyond general visual competence.
Existing image editing models fall short when it comes to precise spatial manipulations, but a new benchmark and dataset reveal the path to closing the gap.
