Search papers, labs, and topics across Lattice.
The Chinese University of Hong Kong, Shenzhen
2
0
5
SIVA-RL reveals that outcome-conditioned supervision can dramatically enhance multimodal reasoning performance, outperforming traditional methods across diverse benchmarks.
LLMs trained with ScaleBox, a new high-fidelity code verification system, substantially outperform those trained with heuristic matching, suggesting current RLHF methods are bottlenecked by verification quality.
