相关论文: When Prompts Interact: Assessing Prompt Arithmetic…

We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models. Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting.…

In safety-critical but computationally resource-constrained applications, deep learning faces two key challenges: lack of robustness against adversarial attacks and large neural network size (often millions of parameters). While the…

Prompt engineering is a challenging yet crucial task for optimizing the performance of large language models on customized tasks. It requires complex reasoning to examine the model's errors, hypothesize what is missing or misleading in the…

Prompt tuning offers a parameter-efficient way to adapt large pre-trained language models to new tasks, but most existing approaches are designed for single-task settings, failing to share knowledge across related tasks. We propose…

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task…

Prompt-tuning is an emerging strategy to adapt large language models (LLM) to downstream tasks by learning a (soft-)prompt parameter from data. Despite its success in LLMs, there is limited theoretical understanding of the power of…

In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Domain-Aware Robust…

Foundation models enable prompt-based classifiers for zero-shot and few-shot learning. Nonetheless, the conventional method of employing fixed prompts suffers from distributional shifts that negatively impact generalizability to unseen…

Collaboration between different data centers is often challenged by heterogeneity across sites. To account for the heterogeneity, the state-of-the-art method is to re-weight the covariate distributions in each site to match the distribution…

Prompt-based methods have been used extensively across NLP to build zero- and few-shot label predictors. Many NLP tasks are naturally structured: that is, their outputs consist of multiple labels which constrain each other. Annotating data…

Distribution shifts, which often occur in the real world, degrade the accuracy of deep learning systems, and thus improving robustness to distribution shifts is essential for practical applications. To improve robustness, we study an image…

Prompting is a common approach for leveraging LMs in zero-shot settings. However, the underlying mechanisms that enable LMs to perform diverse tasks without task-specific supervision remain poorly understood. Studying the relationship…

This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prompts by removing tokens or lexical units according to their…

Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable…

Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on…

The Tactile Internet requires ultra-low latency and high-fidelity haptic feedback to enable immersive teleoperation. A key challenge is to ensure ultra-reliable and low-latency transmission of haptic packets under channel variations and…

The aim is to identify faulty predicates which have strong effect on program failure. Statistical debugging techniques are amongst best methods for pinpointing defects within the program source code. However, they have some drawbacks. They…

Prompt optimization improves language models without updating their weights by searching for a better system prompt, but its effectiveness varies widely across tasks. We study what makes a task amenable to prompt optimization. We show that…

Prompting is a mainstream paradigm for adapting large language models to specific natural language processing tasks without modifying internal parameters. Therefore, detailed supplementary knowledge needs to be integrated into external…

Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the prompt to adapt PTMs to downstream tasks. Although it is…