Search papers, labs, and topics across Lattice.
The University of Texas at Dallas
7
0
13
Correctness checks can miss kernels that are functionally valid but over 300 times slower than optimized versions, highlighting a critical evaluation gap in GPU DSLs.
SubdivAR achieves unprecedented accuracy in mesh subdivision, outperforming traditional methods by significantly enhancing detail retention and topology preservation.
ReM-MoA reveals that structured cross-layer reasoning memory can dramatically enhance the scalability of multi-agent systems, outperforming traditional methods as complexity increases.
No single exploration strategy outperforms others in automated web GUI testing; instead, their strengths are complementary, revealing critical insights for optimizing testing effectiveness.
Stop hand-engineering your multi-agent LLM systems: UnityMAS-O lets you train them end-to-end with RL, unlocking surprisingly large gains, especially for smaller models.
Stop relying on absolute LLM scores for RLHF: relative comparisons via tournaments yield significantly better rewards for long-form generation.
Forget static graphs: TimeMM dynamically reweights user-item interactions based on recency and modality, adapting to evolving user preferences in multimodal recommendations.
