Related papers: MixAtlas: Uncertainty-aware Data Mixture Optimizat…

Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to…

We introduce Mixture-based Feature Space Learning (MixtFSL) for obtaining a rich and robust feature representation in the context of few-shot image classification. Previous works have proposed to model each base class either with a single…

Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model generalization in various…

Large Language Models (LLMs) have achieved impressive performance through Supervised Fine-tuning (SFT) on diverse instructional datasets. When training on multiple capabilities simultaneously, the mixture training dataset, governed by…

Highly imbalanced datasets are ubiquitous in medical image classification problems. In such problems, it is often the case that rare classes associated to less prevalent diseases are severely under-represented in labeled databases,…

Multimodal Large Language Model (MLLM) have demonstrated strong generalization capabilities across diverse distributions and tasks, largely due to extensive pre-training datasets. Fine-tuning MLLM has become a common practice to improve…

Multimodal large language models (MLLMs) require a nuanced interpretation of complex image information, typically leveraging a vision encoder to perceive various visual scenarios. However, relying solely on a single vision encoder to handle…

This paper narrows the performance gap between small, specialized models and significantly larger general-purpose models through domain adaptation via continual pre-training and merging. We address the scarcity of specialized non-English…

We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance. Most existing semi-supervised methods rely on the assumption that…

The mixture proportions of pretraining data domains (e.g., Wikipedia, books, web text) greatly affect language model (LM) performance. In this paper, we propose Domain Reweighting with Minimax Optimization (DoReMi), which first trains a…

The scarcity of high-quality, knowledge-intensive training data hinders the development of large language models (LLMs), as traditional corpora provide limited information. Previous studies have synthesized and integrated corpora-dependent…

Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single-resolution prompt blocks. This creates a tension between relevance and…

We propose MindVL, a multimodal large language model (MLLMs) trained on Ascend NPUs. The training of state-of-the-art MLLMs is often confined to a limited set of hardware platforms and relies heavily on massive, undisclosed data recipes,…

Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency…

Language models (LMs) excel at tasks across diverse domains, yet require substantial computational resources during inference. Compression techniques such as pruning and quantization offer a practical path towards efficient LM deployment,…

The task of video and text sequence alignment is a prerequisite step toward joint understanding of movie videos and screenplays. However, supervised methods face the obstacle of limited realistic training data. With this paper, we attempt…

Quantizing neural networks is one of the most effective methods for achieving efficient inference on mobile and embedded devices. In particular, mixed precision quantized (MPQ) networks, whose layers can be quantized to different bitwidths,…

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack…

How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families.…

Optimizing data mixtures for supervised fine-tuning (SFT) of large language models (LLMs) is critical for developing general-purpose models, yet this area remains underexplored. In this paper, we frame data mixing as an optimization problem…