Search papers, labs, and topics across Lattice.
College of Systems Engineering, National University of Defense Technology
6
0
9
AutoSND uncovers more effective and interpretable network dismantling heuristics by transforming execution evidence into actionable structural policies.
Physically aligned video models can boost robotic manipulation success rates by over 50% compared to traditional methods.
Egocentric human video can outperform traditional teleoperated robot data, achieving superior performance in embodied model pretraining with lower costs and greater diversity.
Training on Syn4D could unlock breakthroughs in dynamic scene understanding, where current datasets fall short in providing dense, complete, and accurate geometric annotations.
Multi-event video generation gets a 33% quality boost with TS-Attn, a training-free attention mechanism that dynamically aligns video content with complex temporal prompts.
A reward model trained on spatial relationship preferences beats proprietary models at spatial understanding in text-to-image generation, and unlocks better RL-based image generation.
