Search papers, labs, and topics across Lattice.
Northwestern University
7
0
8
Current VLMs miss crucial transition-level physics, but APT-Tune teaches them to learn causal transitions without forgetting event-level context.
Achieving superior annotation efficiency and task success rates, AnnotateAnything revolutionizes how 3D assets are prepared for robot manipulation.
MagicSim revolutionizes robot learning by merging diverse world construction and execution into a single, efficient framework that enhances both evaluation and interaction capabilities.
Securing UAV swarms demands a holistic approach: game theory thwarts GPS spoofing, behavior analysis spots insiders, and multi-agent forensics traces complex attacks.
VLMs struggle to meaningfully ground numerical outputs in spatial contexts, often performing at chance levels in critical tasks.
Adversarial perturbations in LLMs have an exploitable low-rank structure, enabling more efficient and effective black-box attacks.
Achieve near-lossless 4-bit quantization for LLMs in under a minute, without full fine-tuning, by correcting for non-uniform activation distributions.
