Tag
This paper proposes Self-Recognition Finetuning as an intervention to prevent and reverse emergent misalignment in LLMs, showing it stabilizes the model's aligned character rather than adopting a misaligned persona.
Proposes a finetuning-based hardware-aware training algorithm to mitigate I-V non-linearity and retention errors in ReRAM crossbar arrays, enabling robust DNN deployment with minimal overhead. Evaluated on image classification and QA tasks, achieving near-baseline accuracy.
Cleo is a finetuned version of Qwen3.5-2B-Base designed for text-to-SQL tasks, using a unified harness for training and inference that supports live execution evidence and safety checks. All code, model, and datasets are open-source.
This paper introduces Muon^p, a novel optimizer that uses fractional spectral-power updates to interpolate between Muon and gradient descent, providing theoretical justification and empirical gains on billion-scale fine-tuning tasks.
This paper proposes a modular approach for adapting pretrained language models to low-resource languages by freezing embeddings and tuning the rest, showing improvements on NLU tasks for Scottish Gaelic, Irish, and Quechua.
TRL now supports fine-tuning models on agent traces from various sources like Claude Code, Codex, OpenClaw, and Pi, moving towards a standardized stack for training agentic models.
This paper introduces GGT-100K, a dataset of 103,707 image pairs for real-world image restoration, generated by using multimodal foundation models like Nano-Banana-2 to produce high-quality targets from low-quality inputs. Experiments show the dataset improves the generalization of various image restoration models.
This article discusses making LLM finetuning accessible to non-coders, highlighting a video demonstration of how anyone can customize LLMs without coding.