A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Adam Zweiger, Jyothish Pari, Han Guo, et al.
SEAL enables LLMs to self-adapt by generating their own finetuning data and update directives, using reinforcement learning to optimize downstream performance.
Jack Lanchantin, Angelica Chen, Janice Lan, et al.
This paper compares offline, semi-online, and fully online RL finetuning methods for LLMs, finding online and semi-online DPO and GRPO variants perform similarly and outperform offline methods, with multi-tasking across verifiable and non-verifiable
Unknown
This paper investigates the fine-tuning of tabular foundation models, particularly TabPFNv2, and compares their performance against traditional GBDT methods.
Unknown
This paper proposes a multi-scale finetuning approach for encoder-based time series foundation models to improve forecasting performance.
Zheyang Xiong, Vasileios Papageorgiou, Kangwook Lee, et al.
Proposes finetuning LLMs on synthetic key-value retrieval data to improve long-context retrieval and reasoning without harming general benchmarks.
Unknown
Multiagent Finetuning improves LLMs by training specialized generation and critic agents on debate-generated data, enabling iterative self-improvement with diverse reasoning.
Unknown
RAFT iteratively fine-tunes generative models on top-ranked samples to align them with a reward function, improving stability and efficiency over RLHF.
Dwip Dalal, Shivansh Patel, Chahit Jain, et al.
Anchor-Align augments behavior cloning with vision-language anchoring and language-action alignment to prevent representation drift and improve VLA policy generalization.