Search papers, labs, and topics across Lattice.
4
0
6
8
Realistic anomalies can be generated for unseen products without needing any target-product samples, revolutionizing how we approach anomaly detection in industrial settings.
MLLMs struggle to grasp deeply interleaved text-image contexts, with performance gaps of over 40% compared to human experts on TIC-Bench.
Generative supervision can transform the landscape of moiré removal, yielding substantial performance gains even in the most challenging real-world scenarios.
An off-the-shelf coding agent can uncover hundreds of buggy submissions that official test suites miss, reshaping how we evaluate code correctness.
