Related papers: MoPD: Mixture-of-Prompts Distillation for Vision-L…

On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-policy distillation can improve a student's output quality…

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…

Pre-trained Vision-Language (VL) models such as CLIP have demonstrated their excellent performance across numerous downstream tasks. A recent method, Context Optimization (CoOp), further improves the performance of VL models on downstream…

Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing…

Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the…

Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representations from medical images and texts. Practically, there exist…

Recent advancements in multi-modal pre-training for 3D point clouds have demonstrated promising results by aligning heterogeneous features across 3D shapes and their corresponding 2D images and language descriptions. However, current…

Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges in Knowledge Distillation (KD) are: 1) balancing learning…

Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection is critical in VICL, but current methods assume 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…

High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representation from enormous unlabeled images (e.g., species, brands)…

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…

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

Efficient reasoning distillation for long chain-of-thought (CoT) models is increasingly constrained by the assumption of a single oracle teacher, despite the practical availability of multiple candidate teachers and growing CoT corpora. We…

Vision-language models (VLMs) have demonstrated remarkable zero-shot performance across various classification tasks. Nonetheless, their reliance on hand-crafted text prompts for each task hinders efficient adaptation to new tasks. While…

This work introduces a novel interpretable machine learning method called Mixture of Decision Trees (MoDT). It constitutes a special case of the Mixture of Experts ensemble architecture, which utilizes a linear model as gating function and…

Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear,…

Existing Score Distillation Sampling (SDS)-based methods have driven significant progress in text-to-3D generation. However, 3D models produced by SDS-based methods tend to exhibit over-smoothing and low-quality outputs. These issues arise…

Large pretrained visual models exhibit remarkable generalization across diverse recognition tasks. Yet, real-world applications often demand compact models tailored to specific problems. Variants of knowledge distillation have been devised…