NeurIPS 2024PastOther
NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability
FITML 2024
- Submission deadline
- Oct 1, 2024, 23:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (88)
Fetched from OpenReview (v2) on 2026-06-10.
A Layer Selection Approach to Test Time Adaptation
A Tensor-based Convolutional Neural Network for Small Dataset Classification
Accelerating Direct Preference Optimization with Prefix Sharing
ActNAS : Generating Efficient YOLO Models using Activation NAS
Adapting Language Models via Token Translation
Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models
An empirical study of CLIP fine-tuning with similarity clusters
Analysing Softmax Entropy Minimization for Adaptating Multitask Models at Test-time
Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs
Best Unpacking DPO and PPO: Disentangling Practices for Learning from Preference Feedback
Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences
Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization
CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation
Deep Reinforcement Learning Without Experience Replay, Target Networks, or Batch Updates
Discrepancy-Guided Parameter Suppression for Robust Fine-tuning
DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent
E-Tamba: Efficient Transformer-Mamba Layer Transplantation
Early Exiting in Deep Neural Networks via Dirichlet-based Uncertainty Quantification
Effective Text-to-Image Alignment with Quality Aware Pair Ranking
Efficient Fine-Tuning of Behavior Cloned Policies with Reinforcement Learning from Limited Demonstrations
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation
Ensembling Finetuned Language Models for Text Classification
Entropic Distribution Matching for Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity
Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering
Exploring Continual Fine-Tuning for Enhancing Language Ability in Large Language Model
Faster, More Efficient RLHF through Off-Policy Asynchronous Learning
FedEx-LoRA: Exact Aggregation for Federated Parameter-Efficient Fine-Tuning of Foundation Models
Fine tuning language models to align fidelity and efficiency of generative retrieval in multi-turn dialogues
Fine-tuning Vision Classifiers On A Budget
Fitness Aware Human Motion Generation with Fine-Tuning
Flat-LoRA: Low-Rank Adaption over a Flat Loss Landscape
Flexora: Flexible Low-Rank Adaptation for Large Language Models
FourierKAN outperforms MLP on Text Classification Head Fine-tuning
FRACTAL: Fine-Grained Scoring from Aggregate Text Labels
GaLore-mini: Low Rank Gradient Learning with Fewer Learning Rates
Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization
Hierarchical Unlearning Framework for Multi-Class Classification
HyperDPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework
ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning
Improving Fine-Tuning with Latent Cluster Correction
Improving LLM Generation with Inverse and Forward Alignment: Reward Modeling, Prompting, Fine-Tuning, and Inference-Time Optimization
Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples
Inducing Semi-Structured Sparsity by Masking for Efficient Model Inference in Convolutional Networks
Instant Transformer Adaption via HyperLoRA
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
Investigating the Role of Fine-Tuning in Addressing the Gap Between Synthetic and Real Data in Generative Foundation Models
Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment
Learning the Regularization Strength for Deep Fine-Tuning via a Data-Emphasized Variational Objective
LLM Alignment Through Successive Policy Re-weighting (SPR)
Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement
Memory retaining finetuning via distillation
Model Soup for Better RLHF: Weight Space Averaging to Improve Alignment in LLMs
MPLoRA: Orthogonal Multi-Path Low-Rank Adaptation for Parameter Efficient Fine-Tuning
Navigating Parameter Space with Geodesic Interpolation: A New Approach to Efficient Fine-Tuning
Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach
On Efficient Distillation from LLMs to SLMs
On the Transferability of Parameter-Efficient Continual Learning for Vision Transformers
One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation
Online Fine-Tuning with Uncertainty Quantification for Offline Pre-Trained Agents
Optimizing Small Language Models for In-Vehicle Function-Calling
PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences
Parameter-Efficient Fine-Tuning of State Space Models
Parasite Networks: Transfer Learning in Resource-Constrained Domains
REACT: Residual-Adaptive Contextual Tuning for Fast Model Adaptation in Cybersecurity
RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates
Scalability of memorization-based machine unlearning
Self-Stitching: Widely Applicable and Efficient Transfer Learning Using Stitching Layer
Semi-Supervised Fine-Tuning of Vision Foundation Models with Content-Style Decomposition
Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
Simultaneous Weight and Architecture Optimization for Neural Networks
Skip Transformers: Efficient Inference through Skip-Routing
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Teaching LLMs How To Learn with Contextual Fine-Tuning
Token Pruning using a Lightweight Background Aware Vision Transformer
TOU: Truncated-factorized reduction for an efficient-parameter model fine-tuning
Towards Long-Context Time Series Foundation Models With A Handful Of Additional Parameters
Towards Natural Machine Unlearning
TreeTop: Topology-Aware Fine-Tuning for LLM Conversation Tree Understanding
Uncertainty-Penalized Direct Preference Optimization
Understanding Visual Concepts Across Models
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
UnoLoRA: Single Low-Rank Adaptation for Efficient Multitask Fine-tuning
Variational Best-of-N Alignment
Variational Low-Rank Adaptation Using IVON
What Causes a Disparate Impact in a Quantized Model?
XoRA: Expander Adapted LoRA Finetuning