Search papers, labs, and topics across Lattice.
Harbin Institute of Technology
6
0
9
Action recognition can thrive even in severely limited visibility, with a framework that boosts performance by up to 68.8% in challenging conditions.
Treating tactile signals as active cues rather than passive inputs leads to a dramatic boost in manipulation success rates and accuracy in contact-rich tasks.
Riemannian self-attention can revolutionize EEG decoding by overcoming the limitations of traditional metrics, leading to more accurate brain-computer interfaces.
Bayesian-Agent transforms how LLM agents evolve skills, achieving up to 100% success on complex benchmarks through a novel posterior-guided optimization approach.
Unlock new magnetic phases: Engineering orbital interactions in 2D materials provides a route to realizing altermagnetism without relying on spin-orbit coupling.
Over 20 teams vied to decode human attention in video, revealing new insights into saliency prediction techniques.
