Search Results for author: Pengliang Ji

Found 14 papers, 7 papers with code

NeuroBind: Towards Unified Multimodal Representations for Neural Signals

no code implementations19 Jul 2024 Fengyu Yang, Chao Feng, Daniel Wang, Tianye Wang, Ziyao Zeng, Zhiyang Xu, Hyoungseob Park, Pengliang Ji, Hanbin Zhao, Yuanning Li, Alex Wong

Understanding neural activity and information representation is crucial for advancing knowledge of brain function and cognition.

EEG

Composition Vision-Language Understanding via Segment and Depth Anything Model

1 code implementation7 Jun 2024 Mingxiao Huo, Pengliang Ji, Haotian Lin, Junchen Liu, Yixiao Wang, Yijun Chen

We introduce a pioneering unified library that leverages depth anything, segment anything models to augment neural comprehension in language-vision model zero-shot understanding.

Question Answering Visual Question Answering (VQA)

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts

1 code implementation19 May 2024 Baolong Bi, Shenghua Liu, Lingrui Mei, Yiwei Wang, Pengliang Ji, Xueqi Cheng

We observe that despite a significant boost in logits of the new knowledge, the performance of is still hindered by stubborn knowledge.

knowledge editing

Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs

no code implementations15 Apr 2024 Ruoxi Cheng, Haoxuan Ma, Shuirong Cao, Jiaqi Li, Aihua Pei, Zhiqiang Wang, Pengliang Ji, Haoyu Wang, Jiaqi Huo

Based on this, we propose Reinforcement Learning from Multi-role Debates as Feedback (RLDF), a novel approach for bias mitigation replacing human feedback in traditional RLHF.

Bias Detection Logical Reasoning +2

Make Continual Learning Stronger via C-Flat

1 code implementation1 Apr 2024 Ang Bian, Wei Li, Hangjie Yuan, Chengrong Yu, Mang Wang, Zixiang Zhao, Aojun Lu, Pengliang Ji, Tao Feng

A general framework of C-Flat applied to all CL categories and a thorough comparison with loss minima optimizer and flat minima based CL approaches is presented in this paper, showing that our method can boost CL performance in almost all cases.

Continual Learning

3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation

1 code implementation ICCV 2023 Yi Zhang, Pengliang Ji, Angtian Wang, Jieru Mei, Adam Kortylewski, Alan Yuille

Motivated by the recent success of generative models in rigid object pose estimation, we propose 3D-aware Neural Body Fitting (3DNBF) - an approximate analysis-by-synthesis approach to 3D human pose estimation with SOTA performance and occlusion robustness.

3D Human Pose Estimation Contrastive Learning

Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network

1 code implementation17 Dec 2021 An Tao, Yueqi Duan, He Wang, Ziyi Wu, Pengliang Ji, Haowen Sun, Jie zhou, Jiwen Lu

It results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward.

3D Classification 3D Semantic Segmentation +2

PREMA: Part-based REcurrent Multi-view Aggregation Network for 3D Shape Retrieval

no code implementations9 Nov 2021 Jiongchao Jin, Huanqiang Xu, Pengliang Ji, Zehao Tang, Zhang Xiong

We propose the Part-based Recurrent Multi-view Aggregation network(PREMA) to eliminate the detrimental effects of the practical view defects, such as insufficient view numbers, occlusions or background clutters, and also enhance the discriminative ability of shape representations.

3D Shape Retrieval Retrieval

Perspective, Survey and Trends: Public Driving Datasets and Toolsets for Autonomous Driving Virtual Test

no code implementations1 Apr 2021 Pengliang Ji, Li Ruan, Yunzhi Xue, Limin Xiao, Qian Dong

To the best of our knowledge, we are the first to perform such recent empirical survey on both the datasets and toolsets using a SLA based survey approach.

Autonomous Driving Survey +1

Cannot find the paper you are looking for? You can Submit a new open access paper.