Related papers: CovMatch: Cross-Covariance Guided Multimodal Datas…

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…

Large machine-learning training datasets can be distilled into small collections of informative synthetic data samples. These synthetic sets support efficient model learning and reduce the communication cost of data sharing. Thus,…

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Efficient Multimodal Large Language Models (MLLMs) compress vision tokens to reduce resource consumption, but the loss of visual information can degrade comprehension capabilities. Although some priors introduce Knowledge Distillation to…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Dataset distillation aims to encapsulate the rich information contained in dataset into a compact distilled dataset but it faces performance degradation as the image-per-class (IPC) setting or image resolution grows larger. Recent…

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…

Image-text matching is gaining a leading role among tasks involving the joint understanding of vision and language. In literature, this task is often used as a pre-training objective to forge architectures able to jointly deal with images…

Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…

State-of-the-art trainable machine translation evaluation metrics like xCOMET achieve high correlation with human judgment but rely on large encoders (up to 10.7B parameters), making them computationally expensive and inaccessible to…

Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even…

Software version migration and program translation are an important and costly part of the lifecycle of large codebases. Traditional machine translation relies on parallel corpora for supervised translation, which is not feasible for…

This paper addresses the limitations of large-scale language models in safety alignment and robustness by proposing a fine-tuning method that combines contrastive distillation with noise-robust training. The method freezes the backbone…

Multimodal fusion leverages information across modalities to learn better feature representations with the goal of improving performance in fusion-based tasks. However, multimodal datasets, especially in medical settings, are typically…

Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use…

Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the…

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…

The deployment of foundation models for medical imaging has demonstrated considerable success. However, their training overheads associated with downstream tasks remain substantial due to the size of the image encoders employed, and the…