A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Kazuki Nonoyama, Ziang Liu, Tomofumi Fujiwara, et al.
This paper optimizes energy-efficient motion planning for dual-arm industrial robots by fine-tuning PID controllers with Genetic Algorithms and Particle Swarm Optimization.
DM Anisuzzaman, Jeffrey G. Malins, Paul A. Friedman, et al.
This review outlines major methodological approaches and steps for fine-tuning LLMs for specialized use cases, with examples from medical subspecialties.
Zorik Gekhman, G. Yona, Roee Aharoni, et al.
This paper shows that supervised fine-tuning introducing new factual knowledge to LLMs is learned slowly and linearly increases hallucination, supporting that factual knowledge is acquired during pre-training.
Xun Liang, Hanyu Wang, Yezhaohui Wang, et al.
A systematic review of controllable text generation for LLMs, defining core concepts, categorizing tasks, and analyzing methods including model retraining, fine-tuning, and decoding-time intervention.
Siyun Zhao, Yuqing Yang, Zilong Wang, et al.
Proposes a four-level RAG task categorization for data-augmented LLMs and compares context, small model, and fine-tuning integration forms.
Zhengqing Yuan, Weixiang Sun, Yixin Liu, et al.
EfficientLLM is a comprehensive benchmark and empirical study of efficiency techniques for LLMs, evaluating over 100 model-technique pairs across architecture, fine-tuning, and inference axes.
Unknown
Selective Self-to-Supervised Fine-Tuning (S3FT) improves LLM fine-tuning by selectively using the model's own correct predictions or gold responses to reduce overfitting and boost generalization.
Unknown
Critique Fine-Tuning trains models to critique noisy responses, improving reasoning more than imitating correct answers.
Unknown
ReST iteratively aligns LLMs with human preferences by alternating between data generation and offline RL fine-tuning with increasing quality thresholds.
Unknown
STaR bootstraps reasoning in language models by iteratively generating rationales, filtering correct ones, and fine-tuning, with rationalization to learn from failures.
Unknown
LongLoRA enables efficient context extension for large language models via sparse local attention and parameter-efficient fine-tuning.
Unknown
QLoRA enables fine-tuning of large language models on a single GPU by combining 4-bit NormalFloat quantization, double quantization, and paged optimizers, matching 16-bit performance.