Search papers, labs, and topics across Lattice.
4
0
6
3
Redirecting failure into actionable corrections boosts robotic manipulation success rates by nearly 32% while using an order of magnitude fewer training samples.
OpenSearch-VL offers a fully transparent recipe for training state-of-the-art multimodal search agents, finally democratizing access to a capability previously locked behind closed doors.
Forget photorealism: the next frontier for 3D generation is creating physically plausible, interactive environments that can train robots.
By tightly coupling reasoning, searching, and generation, Unify-Agent demonstrates that agent-based modeling can substantially improve world knowledge grounding in image synthesis, rivaling closed-source models.
