Search papers, labs, and topics across Lattice.
Institute of Information Engineering, Chinese Academy of Sciences
4
0
6
12
Hallucinations in LVLMs can be cut by over 43% without sacrificing grounded object coverage, thanks to a novel verifier-guided approach.
DocFormFlow boosts document formatting accuracy while slashing token consumption, revealing that target localization is the key to success.
By co-evolving experts through bidirectional policy distillation, CoPD achieves all-in-one integration of text, image, and video reasoning, outperforming domain-specific experts and suggesting a new training paradigm.
Forget external teachers – the best way to boost your RL model's performance is to learn from its future self.
