Search papers, labs, and topics across Lattice.
2
0
5
28
Multimodal LLMs suffer a major performance hit when asked to switch from text-based to image-based tasks mid-conversation, revealing a surprising asymmetry in their ability to handle task interference.
Forget fine-tuning: Prompting MLLMs with a dynamic interval-based decoding strategy lets them generate surprisingly human-like, pause-aware real-time game commentary.
