Big models pretrain and fine-tune for semi-supervised learning on ImageNet.
problem Learning from few labeled examples with a large amount of unlabeled data.
method Unsupervised pretraining of a big ResNet model followed by supervised fine-tuning and distillation.
result 73.9% ImageNet top-1 accuracy with just 1% of labels (≤13 labeled images per class). Two methods for model adaptation compared; fine-tuning outperforms Best-of-N in realizable settings.
problem Comparing methods for adapting large language models to new tasks.
method Supervised fine-tuning vs. Best-of-N approach.
result Supervised fine-tuning outperforms Best-of-N in realizable settings.
Self-play fine-tuning improves diffusion models for text-to-image generation.
problem Plateauing performance of diffusion models after data saturation.
method Self-play fine-tuning (SPIN-Diffusion) using competition among model versions.
result Significantly improved model performance and human preference alignment.
FisherSFT selects informative examples to fine-tune LLMs efficiently.
problem Adapting large language models to new domains efficiently.
method Selects examples maximizing information gain using Hessian of log-likelihood.
result Empirically demonstrates improved performance with reduced computational cost.
Framework fine-tunes foundation models with semi-supervised learning for downstream tasks and latent spaces.
problem Training foundation models with limited labelled data.
method Mutual information decomposition for downstream and latent spaces, semi-supervised fine-tuning.
result Significant improvements in classification tasks under low-labelled conditions.
Self-supervised fine-tuning corrects SR CNNs for unseen models and artifacts.
problem SR CNNs' lack of robustness to unseen image formation models and generation of artifacts.
method Iterative fine-tuning using a data fidelity loss at test time.
result Successfully corrects SR solutions for unseen models and GAN artifacts.
New approach uses PDE learning for faster RL fine-tuning.
problem Learning optimal control policy for diffusion process.
method Solves variational inequality based on HJB equations.
result Shows fine-tuning can be done via supervised regression.
Novel unsupervised relation extraction framework using BERT.
problem Relation extraction without supervision.
method Syntactic parsing, pre-trained embeddings, distant supervision, fine-tuning BERT.
result Significantly outperforms baselines and matches state-of-the-art in three out of four data sets.
Paper fine-tunes LLMs using user edits, unifying preference, supervision, and reward feedback.
problem Adapting LLMs to user preferences and feedback types.
method Derives bounds for learning algorithms from user edits, proposes an ensembling procedure.
result Ensembling procedure outperforms individual feedback methods and robustly adapts to different user-edit distributions.
SimCLR pre-training improves CNN performance with fewer labels.
problem Learning with fewer labeled data.
method SimCLR contrastive learning method combined with supervised fine-tuning.
result SimCLR pre-training with supervised fine-tuning achieves almost optimal test loss with fewer labeled data.
Fine-tunes LLMs to correct bias in predictions.
problem LLMs exhibit bias in predictions from data.
method Supervised fine-tuning with Low-Rank Adaptation (LoRA).
result Fine-tuning corrects bias in both controlled and real-world settings.
SPIN converts weak LLMs to strong ones using self-play.
problem Growing strong LLMs without human-annotated data.
method Self-play fine-tuning (SPIN) starting from a supervised fine-tuned model.
result SPIN significantly improves LLM performance across benchmarks.
Interactive machine learning with weak supervision and pre-trained embeddings.
problem Training machine learning models with limited labeled data.
method Use pre-trained embeddings to define a distance function and extend source votes to nearby points.
result Significantly outperforms traditional weakly-supervised and fully-supervised methods.
SelMix fine-tunes pre-trained models to optimize non-decomposable objectives.
problem Optimizing non-decomposable performance measures for practical applications.
method Selective mixup fine-tuning of pre-trained models.
result SelMix significantly improves performance for various non-decomposable objectives.
Paper fine-tunes a simulation-driven estimator to reduce out-of-distribution errors.
problem Out-of-distribution errors in simulation-driven parameter estimators.
method Fine-tuning a Two-Stage estimator to improve accuracy for true parameters outside the sampled range.
result The fine-tuning approach reduces out-of-distribution errors and improves accuracy.
Deep Convolutional features extracted from a comprehensive labeled dataset, contain substantial representations which could be effectively used in a new domain. Despite the fact that generic features achieved good results in many visual tasks, fine-tuning is required for pretrained deep CNN models to be more effective …
New method uses limited labeled data and multiple starts to adapt models across domains.
problem Accurate predictions in target domain with few labeled data.
method Fine-tuning from multiple adaptive starts, extending UDA methods.
result Minimax-optimal target performance with limited labeled target data.
We propose a new image denoising algorithm, dubbed as Fully Convolutional Adaptive Image DEnoiser (FC-AIDE), that can learn from an offline supervised training set with a fully convolutional neural network as well as adaptively fine-tune the supervised model for each given noisy image. We significantly extend the frame…
Curriculum learning improves model training efficiency and performance.
problem Expensive training of reasoning models using human or synthetic data.
method Autocurriculum, where models use their own performance to decide training problems.
result Autocurriculum reduces training costs and improves model performance.
Open-FinLLMs tackle financial tasks with multimodal capabilities.
problem Financial LLMs lack multimodal capabilities and real-world applicability.
method Developed Open-FinLLMs, an open-source multimodal financial LLM suite.
result Open-FinLLMs outperform advanced financial and general LLMs in diverse tasks.
This paper improves anomaly detection in lane rendering images for safer navigation.
problem Anomalies in lane rendering images can mislead drivers, posing safety risks.
method Proposes a four-phase pipeline using Transformer models, self-supervised pre-training, and fine-tuning.
result The pipeline enhances detection accuracy and reduces training time.
Fine-tuning large language models requires minimal data, making them efficient.
problem Achieving state-of-the-art performance with large language models.
method Using BERT as an example, fine-tuning only the most critical layers of the pre-trained model.
result Fine-tuned models are close in parameter space to the pre-trained model, with many good solutions found in sparsified versions.
New approach uses inverse reinforcement learning to improve language model training.
problem Training large language models using imitation learning methods.
method Developed a new method of inverse reinforcement learning to optimize sequences directly.
result IRL-based fine-tuning leads to better performance and diversity in language generation.
L3Ms fine-tune LLMs with constraints for tailored applications.
problem Inadequate alignment of LLMs for diverse applications.
method Formulate SFT and alignment as constrained optimization, using logarithmic barriers.
result Versatile and effective in achieving tailored alignments for various applications.
Improved financial VA intent classification accuracy.
problem Determining user intents for unseen open intents.
method Supervised pre-training of intent representations using prefix-tuning and fine-tuning.
result 1.63% - 2.07% higher accuracy on banking77 benchmark.
This paper tackles few-shot classification by improving GAN-based data augmentation.
problem Improving few-shot classification performance using GANs with limited data.
method Fine-tuning GANs for few-shot classification, addressing training and evaluation challenges.
result Semi-supervised fine-tuning is a more effective approach for few-shot classification with limited data.
Generative Adapter adapts LMs with a single forward pass, reducing inference overhead.
problem Efficient adaptation of large language models for new contexts.
method Generative Adapter directly maps new contexts to low-rank LM adapters via self-supervised learning.
result Significant reduction in inference overhead with no need for fine-tuning.
This paper simplifies fine-tuning for small LLMs, reducing barriers for developers.
problem Limited resources for fine-tuning large language models (LLMs) by individual developers and small organizations.
method Instruction-tuning datasets, small-sized LLMs (3B to 7B parameters), various training configurations and strategies.
result Improved model performance on benchmarks with specific training configurations, and insights into early termination and hyperparameter simplifications.
We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by supervised fine tuning, our method takes advantage of both unlabelled and labelled data…
New framework improves LLM performance by avoiding forgetting during sequential training stages.
problem Forgetting during sequential training stages of LLMs.
method Proposes a joint post-training framework with theoretical convergence guarantees.
result Empirically outperforms sequential post-training framework by up to 23%.
New mechanism protects neural network weights from privacy attacks during self-supervised learning.
problem Privacy risks during fine-tuning stage of self-supervised learning.
method Proposes a novel differential privacy mechanism using additive logistic noise.
result Reduces membership inference attack accuracy to 50% while maintaining below 5% performance loss.
New framework analyzes LLM personalization trade-offs under congestion.
problem Tension between personalization and resource sharing in LLMs.
method Developed a statistical-economic framework to model user incentives.
result Congestion can flip rankings of SFT and ICL, and offers both methods never hurt profits.
Transformers learn sparse Boolean functions through RL and SFT, revealing distinct learning behaviors.
problem Learning sparse Boolean functions with Transformers.
method Reinforcement Learning (RL) with process rewards and Supervised Fine-Tuning (SFT).
result RL learns the whole CoT chain simultaneously, while SFT learns step by step.
AaSP improves audio self-supervised learning by addressing aliasing issues.
problem Alias issues in audio spectrogram transformers.
method AaSP combines aliasing-aware patch representation, teacher-student masked modeling, cross-attention predictor, and contrastive regularization.
result AaSP learns more stable representations that integrate high-frequency cues.
The paper develops an asymptotic theory of self-supervised pre-training.
problem Sharpness of current rates in self-supervised pre-training and their accuracy.
method Two-stage M-estimation and tools from Riemannian geometry.
result Characterization of the limiting distribution of the downstream test risk.
Novel approach trains ASR models with less supervision using bilevel optimization.
problem Training acoustic models for ASR with minimal supervision.
method Bilevel optimization with unsupervised and supervised losses.
result Achieves superior performance compared to existing methods.
Improved robustness of BERT through orthogonal classifier heads.
problem Improving robustness of language models for smaller datasets.
method Enforces orthogonal classifier heads and adaptively eliminates weaker ones.
result Improves accuracy by +9% on average across datasets.
GRASP removes spurious correlations in fine-tuned models, improving task performance and reducing bias.
problem Fine-tuned models can latch onto spurious correlations, leading to bias and reduced generalization.
method GRASP identifies and removes spurious correlations from model weights without removing latent factors.
result GRASP significantly reduces bias and improves task performance in various fine-tuning tasks.
SuNCEt accelerates contrastive learning with minimal labeled data.
problem Efficiently learning visual representations with limited labeled data.
method Noise-contrastive estimation and neighbourhood component analysis-based semi-supervised loss.
result SuNCEt achieves semi-supervised learning accuracy with less than half the labeled data.
Study shows how a strong model can learn a task's feature while retaining other capabilities.
problem How to align superhuman AI systems using weak-to-strong generalization.
method Two-layer neural networks, reward-model learning, multi-step SGD, feature learning.
result The strong model efficiently learns task features while retaining general capabilities.
In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks. Our system leverages a large amount of unlabeled data to pre-train word embeddings. We then use a subset of the unlabeled data to fin…
Paper presents a method for efficient robot adaptation using fine-tuning.
problem Continuous adaptation of robot learning systems in real-world scenarios.
method Fine-tuning previously learned policies using off-policy reinforcement learning.
result Fine-tuning leads to substantial performance gains and adaptation to new conditions.
Current state of the art methods in Domain Adaptation follow adversarial approaches, making training a challenge. Existing non-adversarial methods learn mappings between the source and target domains, to achieve reasonable performance. However, even these methods do not focus on a key aspect: maintaining performance on…
VAE improves semi-supervised learning in small data.
problem Limited data in biological samples.
method Applied VAE to capture features in a lower-dimension.
result Improved performance in semi-supervised learning.
In this study, we propose the integration of competitive learning into convolutional neural networks (CNNs) to improve the representation learning and efficiency of fine-tuning. Conventional CNNs use back propagation learning, and it enables powerful representation learning by a discrimination task. However, it require…
Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insuf…
Behavior Transfer improves reinforcement learning by leveraging pre-trained policies.
problem Efficient transfer of knowledge in reinforcement learning.
method Behavior Transfer (BT) that uses pre-trained policies for exploration.
result BT combined with pre-training leads to better solutions than without pre-training.
Fine-tuning LLMs with observational data can lead to spurious correlations, but DeconfoundLM can mitigate this.
problem Aligning LLMs with human preferences and business objectives using observational data.
method DeconfoundLM, a method that removes confounders from reward signals.
result DeconfoundLM improves recovery of causal relationships and mitigates spurious correlations.