Related papers: Supervised Fine-Tuning Needs to Unlock the Potenti…
Feature Transformation is crucial for classic machine learning that aims to generate feature combinations to enhance the performance of downstream tasks from a data-centric perspective. Current methodologies, such as manual expert-driven…
Graph Neural Networks frequently exhibit significant performance degradation in the out-of-distribution test scenario. While test-time training (TTT) offers a promising solution, existing Parameter Finetuning (PaFT) paradigm suffer from…
As supervised learning still dominates most AI applications, test-time performance is often unexpected. Specifically, a shift of the input covariates, caused by typical nuisances like background-noise, illumination variations or…
Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and…
Recent theoretical studies (Kou et al., 2023; Cao et al., 2022) have revealed a sharp phase transition from benign to harmful overfitting when the noise-to-feature ratio exceeds a threshold-a situation common in long-tailed data…
Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate annotated responses for given instructions. In this paper, we propose Critique Fine-Tuning (CFT), a method more effective than SFT for reasoning tasks.…
Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…
Large language model fine-tuning techniques typically depend on extensive labeled data, external guidance, and feedback, such as human alignment, scalar rewards, and demonstration. However, in practical application, the scarcity of specific…
Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of…
Token filtering to reduce irrelevant tokens prior to self-attention is a straightforward way to enable efficient vision Transformer. This is the first work to view token filtering from a feature selection perspective, where we weigh the…
Fine-tuning pre-trained foundation models has gained significant popularity in various research fields. Existing methods for fine-tuning can be roughly divided into two categories, namely Parameter-Efficient Fine-Tuning and High-Performance…
Revealing novel insights from the relationship between molecular measurements and pathology remains a very impactful application of machine learning in biomedicine. Data in this domain typically contain only a few observations but thousands…
Advancements in prompt tuning of vision-language models have underscored their potential in enhancing open-world visual concept comprehension. However, prior works only primarily focus on single-mode (only one prompt for each modality) and…
Learning robust representations from data often requires scale, which has led to the success of recent zero-shot models such as CLIP. However, the obtained robustness can easily be deteriorated when these models are fine-tuned on other…
In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on…
Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…
A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the new task. This paper shows that in such settings, selectively…
Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This…
Clustering is a core task in machine learning with wide-ranging applications in data mining and pattern recognition. However, its unsupervised nature makes it inherently challenging. Many existing clustering algorithms suffer from critical…
A prevailing view holds that supervised fine-tuning (SFT) memorizes training data and fails to generalize, whereas reinforcement learning (RL) attains broader robustness. We revisit this claim through a systematic evaluation on two…