[HTML][HTML] Reviewability and supportability: New complementary principles to empower research software practices

H Zhang, A Maillo, SA Khan… - Computational and …, 2024 - Elsevier
In today's scientific landscape, research software has evolved from being a supportive tool to
becoming a fundamental driver of discovery, particularly in life sciences. Beyond its roots in …

Archilles' Heel in Semi-open LLMs: Hiding Bottom against Recovery Attacks

H Huang, Y Li, B Jiang, L Liu, R Sun, Z Liu… - arXiv preprint arXiv …, 2024 - arxiv.org
Closed-source large language models deliver strong performance but have limited
downstream customizability. Semi-open models, combining both closed-source and public …

COMMA: A Communicative Multimodal Multi-Agent Benchmark

T Ossowski, J Chen, D Maqbool, Z Cai… - arXiv preprint arXiv …, 2024 - arxiv.org
The rapid advances of multi-modal agents built on large foundation models have largely
overlooked their potential for language-based communication between agents in …

[PDF][PDF] Exploring the Landscape of Large and Small Language Models: Advancements, Trade-offs, and Future Directions

D Shams, I Salama, I Callixtus - 2025 - preprints.org
Recent advances in natural language processing (NLP) have led to the development of
large language models (LLMs) and small language models (small LMs), which have …