LLM-Based Edge Intelligence: A Comprehensive Survey on Architectures, Applications, Security and Trustworthiness
The integration of Large Language Models (LLMs) and Edge Intelligence (EI) introduces a
groundbreaking paradigm for intelligent edge devices. With their capacity for human-like …
groundbreaking paradigm for intelligent edge devices. With their capacity for human-like …
Promptmm: Multi-modal knowledge distillation for recommendation with prompt-tuning
Multimedia online platforms (eg, Amazon, TikTok) have greatly benefited from the
incorporation of multimedia (eg, visual, textual, and acoustic) content into their personal …
incorporation of multimedia (eg, visual, textual, and acoustic) content into their personal …
Enhancing federated semi-supervised learning with out-of-distribution filtering amidst class mismatches
Federated Learning (FL) has gained prominence as a method for training models on edge
computing devices, enabling the preservation of data privacy by eliminating the need to …
computing devices, enabling the preservation of data privacy by eliminating the need to …
Can we soft prompt LLMs for graph learning tasks?
Graph plays an important role in representing complex relationships in real-world
applications such as social networks, biological data and citation networks. In recent years …
applications such as social networks, biological data and citation networks. In recent years …
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
Integrating and processing information from various sources or modalities are critical for
obtaining a comprehensive and accurate perception of the real world in autonomous …
obtaining a comprehensive and accurate perception of the real world in autonomous …
MinPrompt: Graph-based minimal prompt data augmentation for few-shot question answering
Few-shot question answering (QA) aims at achieving satisfactory results on machine
question answering when only a few training samples are available. Recent advances …
question answering when only a few training samples are available. Recent advances …
EIVEN: Efficient implicit attribute value extraction using multimodal LLM
In e-commerce, accurately extracting product attribute values from multimodal data is crucial
for improving user experience and operational efficiency of retailers. However, previous …
for improving user experience and operational efficiency of retailers. However, previous …
LeMon: Automating Portrait Generation for Zero-Shot Story Visualization with Multi-Character Interactions
Zero-Shot Story Visualization (ZSV) seeks to depict textual narratives through a sequence of
images without relying on pre-existing text-image pairs for training. In this paper, we address …
images without relying on pre-existing text-image pairs for training. In this paper, we address …
How rationals boost textual entailment modeling: Insights from large language models
DH Pham, T Le, HT Nguyen - Computers and Electrical Engineering, 2024 - Elsevier
This study introduces an innovative methodology for rationale-based distillation in textual
entailment. Central to our methodology is the use of diverse and deep rationale types …
entailment. Central to our methodology is the use of diverse and deep rationale types …
Beyond Clouds: Locally Runnable LLMs as a Secure Solution for AI Applications
Imagine a world where your smartphone can diagnose diseases, your laptop can predict
market crashes, and your smartwatch can draft legal contracts—all without sending your …
market crashes, and your smartwatch can draft legal contracts—all without sending your …