Aijun An — accepted AI-conference papers

2026

Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models

Mehran Tamjidi, Hamidreza Dastmalchi, Mohammadreza Alimoradijazi, Ali Cheraghian, Aijun An, Morteza Saberi

AAAI 2026technical

3D Vision-Language Foundation Models (VLFMs) have demonstrated strong generalization and zero-shot recognition capabilities in open-world point cloud processing tasks. However, their performance often degrades in practical scenarios where data are noisy, incomplete, or drawn from distributions that

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression

Hamidreza Dastmalchi, Aijun An, Ali Cheraghian, Hamed Barzamini

CVPR 2026

While large vision-language models (LVLMs) achieve strong performance on multimodal tasks, they frequently generate hallucinations--unfaithful outputs misaligned with the visual input. To address this issue, we introduce CIPHER (Counterfactual Image Perturbations for Hallucination Extraction and Rem

Cited by 0 Source ↗Scholar ↗

2025

Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders

Saeed Abbasi, Aijun An, Heidar Davoudi, Ron Di Carlantonio, Gary Farmaner

COLING 2025industry

We introduce a novel Transformer-based method for document segmentation, tailored for practical, real-world applications. This method utilizes overlapping text sequences with a unique position-aware weighting mechanism to enhance segmentation accuracy. Through comprehensive experiments on both publi…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Generating Vehicular Icon Descriptions and Indications Using Large Vision-Language Models

James Fletcher, Nicholas Dehnen, Seyed Nima Tayarani Bathaie, Aijun An, Heidar Davoudi, Ron DiCarlantonio +1

EMNLP 2024industry

To enhance a question-answering system for automotive drivers, we tackle the problem of automatic generation of icon image descriptions. The descriptions can match the driver’s query about the icon appearing on the dashboard and tell the driver what is happening so that they may take an appropriate…

Cited by 0 Source ↗PDF ↗Scholar ↗

2020

Affective and Contextual Embedding for Sarcasm Detection

Nastaran Babanejad, Heidar Davoudi, Aijun An, Manos Papagelis

COLING 2020main

Automatic sarcasm detection from text is an important classification task that can help identify the actual sentiment in user-generated data, such as reviews or tweets. Despite its usefulness, sarcasm detection remains a challenging task, due to a lack of any vocal intonation or facial gestures in t…

Cited by 127 Source ↗PDF ↗code ↗Scholar ↗

2018

Decoupling the Layers in Residual Networks

Ricky Fok, Aijun An, Zana Rashidi, Xiaogang Wang

ICLR 2018poster

We propose a Warped Residual Network (WarpNet) using a parallelizable warp operator for forward and backward propagation to distant layers that trains faster than the original residual neural network. We apply a perturbation theory on residual networks and decouple the interactions between residual…

Cited by 2 Source ↗PDF ↗Scholar ↗