Related papers: Variational Information Bottleneck for Effective L…
Collaborative edge sensing systems, particularly in collaborative perception systems in autonomous driving, can significantly enhance tracking accuracy and reduce blind spots with multi-view sensing capabilities. However, their limited…
Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning…
Modern applications require lightweight neural network models. Most existing neural network pruning methods focus on removing unimportant filters; however, these may result in the loss of statistical information after pruning due to failing…
Task-oriented communication aims to extract and transmit task-relevant information to significantly reduce the communication overhead and transmission latency. However, the unpredictable distribution shifts between training and test data,…
LLM-brained web agents offer powerful capabilities for web automation but face a critical cost-performance trade-off. The challenge is amplified by web agents' inherently complex prompts that include goals, action histories, and…
Large-scale visual language models are widely used as pre-trained models and then adapted for various downstream tasks. While humans are known to efficiently learn new tasks from a few examples, deep learning models struggle with adaptation…
The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other,…
Finetuning a pretrained vision model (PVM) is a common technique for learning downstream vision tasks. However, the conventional finetuning process with randomly sampled data points results in diminished training efficiency. To address this…
Large-scale pre-trained Vision-Language Models (VLMs) have exhibited impressive zero-shot performance and transferability, allowing them to adapt to downstream tasks in a data-efficient manner. However, when only a few labeled samples are…
In recent years, personalized recommendation technology has flourished and become one of the hot research directions. The matrix factorization model and the metric learning model which proposed successively have been widely studied and…
Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is…
Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…
Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in complex tasks poses a significant barrier to their wider…
We consider an information theoretic approach to address the problem of identifying fake digital images. We propose an innovative method to formulate the issue of localizing manipulated regions in an image as a deep representation learning…
Large Language Models (LLMs) have become indispensable tools in science, technology, and society, enabling transformative advances across diverse fields. However, errors or outdated information within these models can undermine their…
Recently, 3D scenes parsing with deep learning approaches has been a heating topic. However, current methods with fully-supervised models require manually annotated point-wise supervision which is extremely user-unfriendly and…
In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Information Bottleneck (LIB) method for LE. For the recovery…
Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the…
We propose a unified information-geometric framework that formalizes understanding in learning as a trade-off between informativeness and geometric simplicity. An encoder phi is evaluated by U(phi) = I(phi(X); Y) - beta * C(phi), where…
Recent advances in vision-language models (VLMs) have shown remarkable performance across multimodal tasks, yet their ever-growing scale poses severe challenges for deployment and efficiency. Existing compression methods often rely on…