Search papers, labs, and topics across Lattice.
Tencent
3
0
7
0
LLM agents are alarmingly susceptible to memory poisoning via conversational attacks, achieving 95% success rates even against agents with selective memory mechanisms.
Probability boxes offer a surprisingly robust way to maintain prediction coverage when your model ventures into the unknown, even with limited training data.
MLLMs can learn to reason more faithfully by explicitly anchoring visual attention to relevant image regions and reinforcing the use of that evidence during reasoning via counterfactual interventions.
