Search papers, labs, and topics across Lattice.
4
0
7
1
Simply adding multi-view videos to latent action models doesn't guarantee 3D awareness; LAWM-3D reveals the critical design choices needed for success.
Grounded language comprehension, rather than free-form reasoning, is the key to unlocking superior performance in Vision-Language-Action models.
Current LLMs can tackle basic proofs, but MathCoPilot reveals their limitations when faced with advanced theorems requiring true mathematical understanding.
Guard models trained with BraveGuard can detect safety threats in computer-use agents with over 82% accuracy, a significant leap from conventional methods.
