Search papers, labs, and topics across Lattice.
3
0
7
17
City-scale audio-visual reasoning is currently dominated by expensive agentic pipelines, not standalone multimodal models.
Answer logits in large language models act as reliable indicators of a latent decision variable, challenging the notion that they merely reflect heuristic preferences.
LLMs don't just regurgitate token probabilities when expressing confidence; they perform a more sophisticated, cached self-evaluation of answer quality.
