Decomposing the Depth Profile of Fine-Tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Billa, Jayadev
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Predicting Where Steering Vectors Succeed
par: Billa, Jayadev
Publié: (2026)

Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs
par: Billa, Jayadev
Publié: (2026)

The Geometric Anatomy of Capability Acquisition in Transformers
par: Billa, Jayadev
Publié: (2026)

The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines?
par: Billa, Jayadev
Publié: (2026)

When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration
par: Billa, Jayadev
Publié: (2026)

Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
par: Ramasubramanian, Shrinivas, et autres
Publié: (2024)

DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
par: Shi, Zhengxiang, et autres
Publié: (2023)

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation
par: Azizi, Seyedarmin, et autres
Publié: (2024)

Interpretable ML Under the Microscope: Performance, Meta-Features, and the Regression-Classification Predictability Gap
par: Billa, Mattia, et autres
Publié: (2026)

Feature Dynamics as Implicit Data Augmentation: A Depth-Decomposed View on Deep Neural Network Generalization
par: Ruan, Tianyu, et autres
Publié: (2025)

Applying Fine-Tuned LLMs for Reducing Data Needs in Load Profile Analysis
par: Hu, Yi, et autres
Publié: (2024)

R-Tuning: Wavelet-Decomposed Replay and Semantic Alignment for Continual Adaptation of Pretrained Time-Series Models
par: Yin, Tianyi, et autres
Publié: (2025)

Iterative Tilting for Diffusion Fine-Tuning
par: Pachebat, Jean, et autres
Publié: (2025)

Transfer Learning in Physics-Informed Neural Networks: Full Fine-Tuning, Lightweight Fine-Tuning, and Low-Rank Adaptation
par: Wang, Yizheng, et autres
Publié: (2025)

X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios
par: Kwak, Namju, et autres
Publié: (2024)

Decomposable Neuro Symbolic Regression
par: Morales, Giorgio, et autres
Publié: (2025)

Decomposable Transformer Point Processes
par: Panos, Aristeidis
Publié: (2024)

Diagnosing Capability Gaps in Fine-Tuning Data
par: Taghanaki, Saeid Asgari, et autres
Publié: (2026)

Gradual Fine-Tuning for Flow Matching Models
par: Thorkelsdottir, Gudrun, et autres
Publié: (2026)

Exploring Fine-Tuning for Tabular Foundation Models
par: Tanna, Aditya, et autres
Publié: (2026)

Tilt Matching for Scalable Sampling and Fine-Tuning
par: Potaptchik, Peter, et autres
Publié: (2025)

Retrieval & Fine-Tuning for In-Context Tabular Models
par: Thomas, Valentin, et autres
Publié: (2024)

Optimizing DDPM Sampling with Shortcut Fine-Tuning
par: Fan, Ying, et autres
Publié: (2023)

Smooth Model Compression without Fine-Tuning
par: Runkel, Christina, et autres
Publié: (2025)

Improving Fine-Tuning with Latent Cluster Correction
par: Thanh, Cédric Ho
Publié: (2025)

Anchored Supervised Fine-Tuning
par: Zhu, He, et autres
Publié: (2025)

A Comparative Study of Model Selection Criteria for Symbolic Regression
par: Soltani, Ali, et autres
Publié: (2026)

Profiling LoRA/QLoRA Fine-Tuning Efficiency on Consumer GPUs: An RTX 4060 Case Study
par: Avinash, MSR
Publié: (2025)

Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
par: Naram, Jayadev, et autres
Publié: (2025)

Decomposing The Dark Matter of Sparse Autoencoders
par: Engels, Joshua, et autres
Publié: (2024)

Decomposing Prediction Mechanisms for In-Context Recall
par: Daniels, Sultan, et autres
Publié: (2025)

Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning
par: Tian, Zichen, et autres
Publié: (2026)

Robust Graph Fine-Tuning with Adversarial Graph Prompting
par: Zhang, Ziyan, et autres
Publié: (2026)

LLM Zeroth-Order Fine-Tuning is an Inference Workload
par: Li, Zelin, et autres
Publié: (2026)

Fine-Tuning Dynamics of In-Context Factual Recall in Transformers
par: Huang, Ruomin, et autres
Publié: (2026)

Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors
par: Ding, Xinyu, et autres
Publié: (2025)

Curvature-Aware Safety Restoration In LLMs Fine-Tuning
par: Bach, Thong, et autres
Publié: (2025)

Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation
par: Wu, Fei, et autres
Publié: (2025)

Iterative Foundation Model Fine-Tuning on Multiple Rewards
par: Ghari, Pouya M., et autres
Publié: (2025)

An Optimization Framework for Differentially Private Sparse Fine-Tuning
par: Makni, Mehdi, et autres
Publié: (2025)