Search papers, labs, and topics across Lattice.
Institute of Information Engineering, Chinese Academy of Sciences
6
0
11
3
Structure-grounded reasoning in generative recommendation can dramatically enhance performance, especially when traditional methods struggle with complex item relationships.
Recommender systems resist steering towards long-tail content, revealing a major flaw in their controllability that could impact user experience and algorithmic fairness.
Over-privileged tool selection is alarmingly common in LLM agents, often triggered by transient failures, raising critical safety concerns in autonomous decision-making.
Pre-load auditing of Agent Skills can achieve >97% accuracy in detecting malicious intent, even against semantics-preserving rewrites, by combining role-aware evidence extraction with semantic verification.
Decoupling fact injection from text generation lets you edit LLMs with greater precision, improving fine-grained question answering without sacrificing overall editing performance.
Escape the flatland of traditional recommender systems: RecBundle uses differential geometry to disentangle user interactions from preferences, opening the door to understanding and mitigating systemic biases.
