323 articles tagged with Fine-Tuning
FCPRAG adds a lightweight controller for retrieval-conditioned, sample-level adapter fusion in parametric RAG. It improves F1 over baselines on HotpotQA, 2WikiMultiHopQA, PopQA, an...
Macaron-V1: Continual Learning with Self-Improvement and Mixture-of-LoRA Adapters#machinelearning #ai #programming #datascience #software #coding #development #engineering #inclusi...
Fine-tuning NuExtract3 (LoRA) on 624 train / 44 eval books from this pilot corpus markedly improved precision (0.61→0.76), with recall essentially unchanged (0.76→0.75) vs. the zer...
MLX LM gives Apple Silicon a native path for adapting open language models with LoRA or QLoRA....
🐧 PyTorch Lightning – deep learning frameworkPyTorch Lightning is a deep learning framework for pretraining and fine-tuning models with PyTorch. The post PyTorch Lightning – deep l...
Fed-SE (arXiv 2512.08870): aggregating LoRA updates in a shared low-rank subspace beats full-weight averaging - cuts negative transfer across agents, +18% success. Roger Federated ...
With large pretrained models, existing methods have effectively improved instruction-based video editing. However, most of them rely on an in-place editing assumption. They align t...
Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safety tuning may affect model responses to both harmful and benign ...
Every AI headshot product works roughly the same way under the hood, and once you know the shape of...
A 0.6 B interpreter compiled with Program‑as‑Weights matches the accuracy of a 32 B LLM while using...
这是一套围绕 Stanford CS224N: Natural Language Processing with Deep Learning 整理的系统课程笔记。仓库以课程 19 节 Lecture 为主线，从 Word Vectors、RNN、Attention、Transformer 一路延伸到 Pretraining、Post-training、PEF...
📰 Today's AI brief: DeepSeek and GLM slash input prices, llama.cpp ships LoRA bounds fixNew models, notable releases, price moves and emerging projects - measured from our own trac...
Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM PersonalizationSource: arXiv cs.AIhttps://arxiv.org/abs/2608.12389#MachineLearning #Meta
【LoRaを超えて：最も普及している微調整技術を凌駕できるだろうか？】https://huggingface.co/blog/peft-beyond-lora※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
Hugging Face Space: Pepe104/MiniMax-H3-Turbo-Lora-UNCENSORED
SillyTavern extension for selecting Pony Diffusion V6 XL LoRAs in a dedicated ComfyUI workflow.
An adapter layer becomes strategically useful when several teams need one observability contract but...
LoRA fine-tuning of Stable Diffusion v1.5 on Flickr8k for text-to-image generation with a Gradio inference interface.
MERA framework improves small LLM agent performance through iterative skill distillation and LoRA fine-tuning, cutting inference costs to 60.8% of baseline while preserving 88.3% t...
New research proposes Latent Critic, a lightweight LoRA adapter that detects and corrects AI agent hallucinations in real time by restructuring latent uncertainty signals, achievin...
🤖 Outsourced my thinking and cognitive debt gives me anxietyI'm a dev. In my company I am an early adapter of LLMs, it just so happened that i became the "AI guy" in my department....
Anker’s travel charger works in almost any country and is down to $20Anker’s Nano Travel Adapter can power up to five devices at once. | Image: Anker If you’ve got international tr...
Hugging Face model: fal/MiniMax-H3-Realism-People-LoRA
Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized arou...