Search papers, labs, and topics across Lattice.
Affiliation:
11
0
8
3
Static 3D worlds now possess vivid, looping motion, seamlessly transitioning from any viewpoint without explicit motion capture.
LLM/VLM agents significantly outperform non-agentic methods in preserving unedited parts during iterative 3D asset modification, but current agentic edits are prohibitively slow.
Most video generation models fail to accurately render fine-grained, program-specified world events, with PROWBench revealing significant discrepancies between intended logic and visual output.
KaiNinja, a part-level extension of TRELLIS.2 built on a dual-volume form of its O-Voxel representation, is the first 3D generative model trained on agent-authored part data and finds that whole-object fidelity improves over the same backbone fine-tuned on the same dataset.
Monolithic 3D scenes with hundreds of heavily occluded objects can be cleanly parsed into individual editable meshes without ever training on multi-object data.
Conditioning signals now match generated content more closely, leading to unprecedented realism in long-horizon video generation.
AlayaRenderer-Flash achieves real-time generative rendering at 30 FPS without sacrificing scene fidelity or control.
AlayaWorld achieves unprecedented long-horizon video generation with just four sampling steps, revolutionizing how we create interactive virtual environments.
AlayaWorld transforms game development by enabling real-time, interactive world generation that adapts to user actions without the need for extensive manual design.
VDMs can tell time is running backward, but still fail at basic causal reasoning, revealing a significant gap between statistical pattern matching and true world model understanding.
