A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Dan Gusfield
A comprehensive textbook on string algorithms, suffix trees, and sequence alignment with applications in computational biology.
Franz Josef Och, Hermann Ney
This paper systematically compares statistical and heuristic word alignment models, showing refined models with first-order dependence and fertility significantly outperform simple heuristics.
A. Sheshadri, John Hughes, Julian Michael, et al.
This paper analyzes 25 language models to understand why only 5 exhibit alignment faking, finding that post-training variations in refusal behavior largely explain differences.
Unknown
mmE5 is a multimodal multilingual embedding model trained on synthetic data via a framework that ensures broad task/language coverage, robust cross-modal alignment, and high fidelity through self-evaluation and refinement.
Unknown
Jina Reranker is a neural reranking model that improves search and RAG systems by reordering retrieved documents for better query alignment.
Xiusi Chen, Gaotang Li, Ziqi Wang, et al.
RM-R1 introduces reasoning reward models that improve LLM alignment by formulating reward modeling as a structured reasoning task.
Unknown
GPT-4.5 scales unsupervised learning with new alignment techniques to reduce hallucinations and improve natural conversation, while GPT-4.1 family excels in coding, instruction following, and long-context tasks at lower cost.
Unknown
Nvidia's Nemotron-4 340B models and reward model enable synthetic data generation for training smaller language models, with over 98% of alignment data being synthetic.
Unknown
Zephyr 7B uses distilled direct preference optimization (dDPO) and AI feedback data to improve intent alignment in chat-based language models.
Yufei Wang, Wanjun Zhong, Liangyou Li, et al.
A comprehensive survey of alignment technologies for large language models, summarizing methods for effective high-quality alignment.
Unknown
This paper proposes reward reasoning models to improve the alignment of large language models with human expectations by effectively utilizing test-time computation.
Unknown
This survey systematically reviews threats and countermeasures for trustworthy LLM agents, organizing defense approaches into three paradigms: alignment, monitoring, and control.