Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
0
ParticleSplat is presented, a self-supervised object-centric learning method that decomposes scenes into a set of latent particles representing semantic entities through feedforward 3D Gaussian Splatting, and it is established that the learned 3D representation improves downstream performance on robotic manipulation tasks.
Context-Fractured Decomposition attacks expose a critical vulnerability in LLM agents, where harmless actions can lead to harmful outcomes through fragmented artifact interactions.