Search papers, labs, and topics across Lattice.
HKUST
4
1
5
11
Current multimodal models falter in maintaining consistent motivation reasoning across sequences, exposing a critical gap in their social intelligence capabilities.
Intention-aware tool discovery can boost LLM agent performance by nearly 60% while slashing unnecessary complexity in tool management.
Legal LLMs can be taught to respect the arrow of time, outperforming state-of-the-art models by up to 30% on legal reasoning tasks simply by enforcing temporal consistency via reinforcement learning.
LLMs playing Hanabi reveal that accurately guessing your partner's intentions matters more than predicting what they *think* you're thinking.
