Ladder Up, Memory Down: Low-Cost Fine-Tuning With Side Nets

arXiv:2512.14237 · cs.CL, cs.LG · Submitted 2025-12-16 · Read on arXiv

cs.CL, cs.LG

Submitted: 2025-12-16

Updated: 2026-08-25

Comments: 24 pages, 20 figures

Code: https://github.com/Mega4alik/ollm

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fine-Tuning — 45× in this paper · explained in 5 episodes
• Scaling Laws — 20× in this paper · explained in 4 episodes
• Accuracy — 19× in this paper · explained in 1 episode
• Transformer — 18× in this paper · explained in 2 episodes
• Benchmark — 17× in this paper · explained in 2 episodes
• Downstream Tasks — 10× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Quantization — 7× in this paper · explained in 12 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Ladder Side Tuning — 4× in this paper
• Parameter-Efficient Fine-Tuning — 4× in this paper · explained in 2 episodes
• Pruning — 4× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Quantized Side Tuning — 3× in this paper
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Transfer Learning — 3× in this paper · explained in 10 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Chain-of-Thought (CoT) — 2× in this paper · explained in 4 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Parameter-Efficient Fine-Tuning (PEFT) — 2× in this paper · explained in 4 episodes
• Supervised Fine-Tuning — 2× in this paper
• Transformer Models — 2× in this paper · explained in 2 episodes
• Activation Checkpointing — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Corpus of Linguistic Acceptability — 1× in this paper
• Distribution Shift — 1× in this paper · explained in 5 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• Grouped Query Attention — 1× in this paper
• In-Context Learning — 1× in this paper · explained in 4 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Latent Reasoning — 1× in this paper · explained in 2 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Mathews Correlation Coefficient — 1× in this paper
• Parameter Efficiency — 1× in this paper · explained in 3 episodes
• Quora Question Pairs — 1× in this paper
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• Establishing Task Scaling Laws via Compute-Efficient Model Ladders
• CST: Calibration Side-Tuning for Parameter and Memory Efficient Transfer Learning
• Training Deep Nets with Sublinear Memory Cost
• Language models scale reliably with over-training and on downstream tasks
• Training Verifiers to Solve Math Word Problems
• OpenThoughts: Data Recipes for Reasoning Models
• Flex Attention: A Programming Model for Generating Optimized Attention Kernels
• Measuring Mathematical Problem Solving With the MATH Dataset
• Distilling the Knowledge in a Neural Network
• A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
• Scaling Laws for Neural Language Models
• CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation
• Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
• Reducing Activation Recomputation in Large Transformer Models
• s1: Simple test-time scaling
• EvoLM: In Search of Lost Language Model Training Dynamics
• Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
• When More is Less: Understanding Chain-of-Thought Length in LLMs
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering