Search papers, labs, and topics across Lattice.
Chinese Academy of Sciences
2
0
6
0
Continual learning methods for Video-LLMs face a fundamental trade-off: mitigating catastrophic forgetting often comes at the cost of generalization or prohibitive computational overhead.
Context-augmented RL lets smaller MLLMs punch *way* above their weight, rivaling much larger models on reasoning tasks while dodging reward hacking.
