Tagged articles

parameter-efficient fine-tuning

11 articles · Page 1 of 1

Machine Learning Algorithms & Natural Language Processing

Jul 9, 2026 · Artificial Intelligence

One Layer Is Enough: Single‑Layer RL Beats Full‑Parameter Training Across Models, Tasks, and Algorithms

A systematic study of reinforcement‑learning fine‑tuning for large language models reveals that RL gains are highly concentrated in a few middle Transformer layers, and training just one such layer can match or even exceed full‑parameter RL performance across multiple models, tasks, and algorithms.

layer contributionmodel trainingparameter-efficient fine-tuning

0 likes · 17 min read

One Layer Is Enough: Single‑Layer RL Beats Full‑Parameter Training Across Models, Tasks, and Algorithms

AI Engineering

May 26, 2026 · Artificial Intelligence

Training Only the Skill Document While Keeping Model Weights Frozen (SkillOpt)

Microsoft Research introduces SkillOpt, a method that freezes large‑model weights and instead trains a natural‑language skill document as the sole learnable parameter, using a rollout‑reflect‑edit‑gate loop, achieving optimal results across 52 benchmark‑model‑environment combinations and demonstrating strong transferability.

LLM agentsSkillOptTransfer Learning

0 likes · 9 min read

Training Only the Skill Document While Keeping Model Weights Frozen (SkillOpt)

Machine Learning Algorithms & Natural Language Processing

Mar 24, 2026 · Artificial Intelligence

Convert Any Text to LLM LoRA in a Single Forward Pass with SHINE

The SHINE hypernetwork can turn arbitrary text into LoRA parameters for a large language model with just one forward pass, internalizing the knowledge for multi‑turn dialogue, achieving efficiency and scaling comparable to in‑context methods while outperforming traditional fine‑tuning baselines.

LoRAhypernetworkparameter-efficient fine-tuning

0 likes · 17 min read

Convert Any Text to LLM LoRA in a Single Forward Pass with SHINE

Alibaba International Intelligent Technology

Feb 27, 2026 · Artificial Intelligence

A New Dual‑Tower Multi‑Objective Recall Framework (CSMF) Boosts Efficiency Without Extra Parameters

The paper introduces CSMF, a cascaded selective‑mask fine‑tuning framework for dual‑tower embedding‑based retrieval that sequentially optimizes exposure, click and conversion goals, incorporates cumulative percentile pruning and adaptive margin loss, and achieves measurable gains in ad revenue and CTR without increasing model size or latency.

Recommendation Systemscascaded selective maskdual-tower

0 likes · 15 min read

A New Dual‑Tower Multi‑Objective Recall Framework (CSMF) Boosts Efficiency Without Extra Parameters

PaperAgent

Feb 7, 2026 · Artificial Intelligence

Can 13 Parameters Match Full‑Scale Fine‑Tuning? TinyLoRA’s RL Breakthrough

TinyLoRA, a Meta‑proposed method that fine‑tunes Qwen2.5‑7B with only 13 trainable parameters (26 bytes), achieves 91% accuracy on GSM8K under reinforcement learning, revealing that ultra‑low‑parameter RL can rival full‑scale supervised fine‑tuning.

GSM8KQwen2.5TinyLoRA

0 likes · 7 min read

Can 13 Parameters Match Full‑Scale Fine‑Tuning? TinyLoRA’s RL Breakthrough

AI Frontier Lectures

Jan 27, 2026 · Artificial Intelligence

A Unified Framework for Neural Network Reprogrammability: From Model Reprogramming to Prompt Tuning

This article surveys recent advances in neural network reprogrammability, presenting a unified framework that categorizes model reprogramming, prompt tuning, prompt instruction, and in‑context learning, highlights the shift from parameter‑centric to reprogrammability‑centric adaptation, and provides efficiency analyses, taxonomy, and practical case studies.

Model AdaptationNeural Network ReprogrammabilityPrompt Tuning

0 likes · 16 min read

A Unified Framework for Neural Network Reprogrammability: From Model Reprogramming to Prompt Tuning

PMTalk Product Manager Community

Jan 8, 2026 · Artificial Intelligence

Understanding Fine‑Tuning: A Primer for AI Product Managers

This article explains how large language models are first pre‑trained on massive text corpora and then fine‑tuned with smaller, task‑specific datasets, covering the fine‑tuning process, types such as full‑parameter and PEFT, practical benefits, real‑world analogies, and key challenges like data quality and catastrophic forgetting.

AI product managementFine-tuningLarge Language Models

0 likes · 6 min read

Understanding Fine‑Tuning: A Primer for AI Product Managers

Wu Shixiong's Large Model Academy

Aug 23, 2025 · Artificial Intelligence

Why LoRA, QLoRA, Prompt & Prefix Tuning Are Changing Large‑Model Fine‑Tuning

This article explains the mathematical basis of LoRA, compares it with QLoRA, Prompt Tuning, Prefix Tuning and P‑tuning, shows practical PyTorch implementations, and provides mixed‑precision training tips so readers can choose the most memory‑efficient fine‑tuning method for their large language models.

Large Language ModelsLoRAPrompt Tuning

0 likes · 17 min read

Why LoRA, QLoRA, Prompt & Prefix Tuning Are Changing Large‑Model Fine‑Tuning

Ops Development & AI Practice

Mar 19, 2025 · Artificial Intelligence

How to Fine‑Tune Large Language Models: From PEFT to Knowledge Injection

This article provides a comprehensive guide to customizing pre‑trained large language models through fine‑tuning techniques—including parameter‑efficient methods, data preparation, knowledge injection, and robust evaluation—offering practical steps, best practices, and domain‑specific considerations for achieving superior task performance.

Data PreparationLLM fine-tuningknowledge injection

0 likes · 18 min read

How to Fine‑Tune Large Language Models: From PEFT to Knowledge Injection

AntTech

Oct 29, 2024 · Artificial Intelligence

Three Ant Group Papers Featured at EMNLP 2024: Dynamic Transformers, Plug‑and‑Play Visual Reasoner, and Efficient Fine‑Tuning of Large Language Models

This announcement introduces three Ant Group papers accepted at EMNLP 2024—Mixture‑of‑Modules for dynamic Transformer assembly, a plug‑and‑play visual reasoning framework built via data synthesis, and a layer‑wise importance‑aware efficient fine‑tuning method for large language models—highlighting their innovations and upcoming live presentations.

AI researchEMNLP 2024Large Language Models

0 likes · 6 min read

Three Ant Group Papers Featured at EMNLP 2024: Dynamic Transformers, Plug‑and‑Play Visual Reasoner, and Efficient Fine‑Tuning of Large Language Models

UCloud Tech

Oct 13, 2023 · Artificial Intelligence

How PEFT Transforms Large Model Fine‑Tuning: Additive, Prompt & LoRA Methods Explained

This article introduces parameter‑efficient fine‑tuning (PEFT) techniques—including additive adapters, soft‑prompt methods, selection‑based BitFit, and re‑parameterization approaches like LoRA and AdaLoRA—explains their architectures, experimental results, and provides end‑to‑end code for fine‑tuning ChatGLM2‑6B on a Chinese medical QA dataset.

AdaLoRALoRAPEFT

0 likes · 22 min read

How PEFT Transforms Large Model Fine‑Tuning: Additive, Prompt & LoRA Methods Explained