Search papers, labs, and topics across Lattice.
5
0
8
Experimental results demonstrate that the KuaiRP models not only match the current state-of-the-art proprietary models in role-playing fidelity within the authors' target domains, but also successfully recover general agent capabilities, maintaining extremely low deployment costs.
HiGram cuts through irrelevant memory noise, boosting answer quality and efficiency in long-term reasoning tasks by leveraging a hierarchical structure and path-level localization.
Isolating global reasoning from local evidence in multimodal retrieval can dramatically boost QA accuracy and evidence recall.
GTAlign achieves superior performance in graph classification tasks without the need for textual data, challenging the reliance on traditional graph neural networks and LLMs.
RAG systems get a boost: CRITIC-R1 learns to diagnose and fix errors with structured feedback, outperforming strong baselines on knowledge-intensive QA.
