Search Results for author:
Found 13 papers, 7 papers with code
Robust Misinformation Detection by Visiting Potential Commonsense Conflict
In this paper, we propose a novel plug-and-play augmentation method for the MD task, namely Misinformation Detection with Potential Commonsense Conflict (MD-PCC).
Revisiting CLIP for SF-OSDA: Unleashing Zero-Shot Potential with Adaptive Threshold and Training-Free Feature Filtering
Source-Free Unsupervised Open-Set Domain Adaptation (SF-OSDA) methods using CLIP face significant issues: (1) while heavily dependent on domain-specific threshold selection, existing methods employ simple fixed thresholds, underutilizing CLIP's zero-shot potential in SF-OSDA scenarios; and (2) overlook intrinsic class tendencies while employing complex training to enforce feature separation, incurring deployment costs and feature shifts that compromise CLIP's generalization ability.
Collaboration and Controversy Among Experts: Rumor Early Detection by Tuning a Comment Generator
However, these RD methods often fail in the early stages of rumor propagation when only limited user comments are available, leading the community to focus on a more challenging topic named Rumor Early Detection (RED).
Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
Large language models based Multi Agent Systems (MAS) have demonstrated promising performance for enhancing the efficiency and accuracy of code generation tasks.
Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation
Source-free Unsupervised Domain Adaptation (SF-UDA) aims to transfer a model's performance from a labeled source domain to an unlabeled target domain without direct access to source samples, addressing critical data privacy concerns.
Why Misinformation is Created? Detecting them by Integrating Intent Features
Accordingly, we propose to reason the intent of articles and form the corresponding intent features to promote the veracity discrimination of article features.
Harmfully Manipulated Images Matter in Multimodal Misinformation Detection
Accordingly, in this work, we propose to detect misinformation by learning manipulation features that indicate whether the image has been manipulated, as well as intention features regarding the harmful and harmless intentions of the manipulation.
Training-Free Unsupervised Prompt for Vision-Language Models
In light of this, we propose Training-Free Unsupervised Prompts (TFUP), which maximally preserves the inherent representation capabilities and enhances them with a residual connection to similarity-based prediction probabilities in a training-free and labeling-free manner.
Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering
To solve the problems, we fine-tune PLMs by leveraging the frequency information of words and propose a novel USRL framework, namely Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering (SLT-FAI).
Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
A contrastive loss is employed to align such augmented text and image representations on downstream tasks.
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers
In this paper, we emphasize the cruciality of diverse global semantics and propose an efficient token decoupling and merging method that can jointly consider the token importance and diversity for token pruning.
Ranked #4 on
Efficient ViTs
on ImageNet-1K (with DeiT-T)
Next-item Recommendations in Short Sessions
The obtained similar sessions are then utilized to complement and optimize the preference representation learned from the current short session by the local module for more accurate next-item recommendations in this short session.
Hyperbolic Node Embedding for Signed Networks
Signed network embedding methods aim to learn vector representations of nodes in signed networks.
