Search papers, labs, and topics across Lattice.
SKLCCSE, School of Computer Science and Engineering
5
0
7
10
Isolating global reasoning from local evidence in multimodal retrieval can dramatically boost QA accuracy and evidence recall.
Forget short-sighted compression: Future Forcing anticipates future query needs in autoregressive video generation, boosting long-horizon consistency by up to 1.49 on VBench-Long without any training.
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.
Ditch the training: SVOO achieves up to 1.93x speedup in video generation with sparse attention by exploiting the intrinsic, layer-specific sparsity patterns of attention without any fine-tuning.
By aligning LLM-generated student behaviors with real-world data in hyperbolic space, L-HAKT achieves state-of-the-art knowledge tracing, capturing nuanced hierarchical relationships between concepts.
