Lei Li
6 papers ยท Latest:
HSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment
HSUGA improves LLM-enhanced recommendations by using hierarchical semantic understanding and group-aware alignment for better user preference modeling.
BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD
BenchCAD is a new industry-standard benchmark for evaluating MLLMs on generating executable parametric CAD programs, revealing current models' limitations.
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
Claw-Eval-Live is a live benchmark for LLM agents, evaluating their performance on evolving real-world workflows with verifiable execution.
SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
SeaEvo improves LLM-guided algorithm discovery by using explicit natural-language strategy descriptions to organize and guide evolutionary search.
Bridging the Gap between User Intent and LLM: A Requirement Alignment Approach for Code Generation
REA-Coder improves LLM code generation by iteratively aligning user requirements, addressing the common issue of LLMs misunderstanding prompts.
AdaSplash-2: Faster Differentiable Sparse Attention
AdaSplash-2 introduces a novel histogram-based initialization for ฮฑ-entmax attention, significantly speeding up sparse transformer training.
๐ฌ Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week โ summarized, scored, and delivered to your inbox every Monday.