Search papers, labs, and topics across Lattice.
University of Chinese Academy of Sciences
6
0
9
Dynamic agent collaboration in DAIN leads to a 2.6% accuracy boost on multimodal tasks, redefining efficiency in complex reasoning scenarios.
Achieving new state-of-the-art scores in deep research benchmarks, DuMate-DeepResearch redefines the capabilities of multi-agent systems in tackling complex research tasks.
Novelty-driven interaction enables agents to explore more effectively while using memory efficiently, outperforming traditional methods in open-ended environments.
Long-form video generation struggles with transitions, scoring only 0.256 on transition quality even when prompt fulfillment is high (0.71), revealing a critical bottleneck exposed by the new DirectorBench diagnostic benchmark.
Saturated LLM benchmarks can be revived without creating new datasets: a self-improving LLM judge in an elimination tournament recovers ranking signal and breaks ties.
Alignment-based projection offers a surprisingly effective way to fix broken Chinese word boundaries in noisy text, outperforming direct segmentation and stabilizing annotation pipelines.
