Siu-Ming Yiu
6 papers · Latest:
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
QD-LLM uses neuroevolution to evolve prompt embeddings, enabling diverse and high-quality LLM outputs without fine-tuning.
EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent
EvoPref, a multi-objective evolutionary algorithm, discovers diverse LLM alignments, overcoming preference collapse in gradient-based methods.
When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
ReaLM-Retrieve adaptively injects evidence during reasoning, improving large model performance and efficiency by detecting knowledge gaps.
FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification
FinGround is a new pipeline that significantly reduces financial AI hallucination by verifying atomic claims against regulatory filings, crucial for compliance.
ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection
ComplianceNLP is a knowledge-graph-augmented RAG system for automated regulatory gap detection, outperforming GPT-4o and improving analyst efficiency.
A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era
This paper surveys and benchmarks deep learning for molecular property prediction, covering paradigms from quantum to foundation models.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.