Search papers, labs, and topics across Lattice.
2
0
5
53
Forget adversarial training: a closed-form solution can make multi-agent RL for drone collision avoidance surprisingly robust to GPS spoofing.
Ditch BLEU and ROUGE: ViSIL offers a unified metric for multimodal video captioning that actually correlates with VQA performance and human judgment by measuring information loss via VLM inference.
