Search papers, labs, and topics across Lattice.
6
0
6
Reducing inter-view redundancy, PointSplat achieves superior 3D human representation quality while minimizing computational load.
Event-based eye movements can achieve over 96% accuracy in recognizing cognitive workload, paving the way for smarter rehabilitation technologies.
AI peer reviewers are alarmingly vulnerable to targeted multimodal attacks, with existing defenses falling short in the face of sophisticated adversarial strategies.
Repurposing adversarial perturbations can significantly enhance continual learning, reducing forgetting and improving task transfer in large language models.
Imagine cities teaching cars to see: this work demonstrates a label-free 3D perception pipeline where roadside sensors train autonomous vehicles, achieving impressive detection accuracy without manual annotation.
Multimodal LLMs struggle with math because they *see* poorly, but a multi-agent system focused on visual evidence can dramatically improve their perception and reasoning.
