Related papers: Understanding multi-fidelity training of machine-l…

We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pretrained…

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing…

This paper investigates the critical problem of representation similarity evolution during cross-domain transfer learning, with particular focus on understanding why pre-trained models maintain effectiveness when adapted to medical imaging…

Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt (multimodal) large language models to downstream tasks. While effective at task adaptation, their impact on retaining…

Control of legged robots is a challenging problem that has been investigated by different approaches, such as model-based control and learning algorithms. This work proposes a novel Imitating and Finetuning Model Predictive Control (IFM)…

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

In recent years, the use of Machine Learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising…

Masked Language Modeling (MLM) pre-training is one of the primary ways to initialize Neural Information Retrieval (IR) models prior to retrieval fine-tuning. However, studies show that MLM pre-trained models have limited readiness and…

In recent years, deep neural networks (DNNs) have been found very successful for multi-label classification (MLC) of remote sensing (RS) images. Self-supervised pre-training combined with fine-tuning on a randomly selected small training…

The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it right. Existing multimodal instruction following training data…

Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…

The process of meta-learning algorithms from data, instead of relying on manual design, is growing in popularity as a paradigm for improving the performance of machine learning systems. Meta-learning shows particular promise for…

Recent works have shown the promise of learning pre-trained models for 3D molecular representation. However, existing pre-training models focus predominantly on equilibrium data and largely overlook off-equilibrium conformations. It is…

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

Overfitting is a phenomenon that occurs when a machine learning model is trained for too long and focused too much on the exact fitness of the training samples to the provided training labels and cannot keep track of the predictive rules…

Reinforcement fine-tuning (RFT) has become a core paradigm for post-training large language models, yet its training process remains highly fragile. Existing efforts mainly improve reliability at the system level or address specific issues…

Initializing with pre-trained models when learning on downstream tasks is becoming standard practice in machine learning. Several recent works explore the benefits of pre-trained initialization in a federated learning (FL) setting, where…

Language model pre-training and derived methods are incredibly impactful in machine learning. However, there remains considerable uncertainty on exactly why pre-training helps improve performance for fine-tuning tasks. This is especially…

The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and…

Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…