Search papers, labs, and topics across Lattice.
Beihang University
4
0
7
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.
Achieve SOTA zero-shot anomaly detection by dynamically routing image patches based on structural entropy, adapting to heterogeneous anomaly patterns without target-domain fine-tuning.
RLHF can be made more stable and effective by explicitly verifying and reinforcing policy improvements against a historical baseline, rather than relying solely on instantaneous reward signals.
