1 code implementation • 28 Oct 2024 • Ge Yang, Changyi He, Jinyang Guo, Jianyu Wu, Yifu Ding, Aishan Liu, Haotong Qin, Pengliang Ji, Xianglong Liu
Finally, we perform an in-depth analysis based on the evaluation and provide useful insight for LLM compression design.
no code implementations • 26 Sep 2024 • Quanting Xie, So Yeon Min, Pengliang Ji, Yue Yang, Tianyi Zhang, Kedi Xu, Aarav Bajaj, Ruslan Salakhutdinov, Matthew Johnson-Roberson, Yonatan Bisk
There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable.
1 code implementation • 29 Aug 2024 • Kaijing Ma, Haojian Huang, Jin Chen, Haodong Chen, Pengliang Ji, Xianghao Zang, Han Fang, Chao Ban, Hao Sun, Mulin Chen, Xuelong Li
To the best of our knowledge, this marks the first successful attempt of DER in VTG.
no code implementations • 19 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.
no code implementations • 1 Jul 2024 • Yixiao Wang, Yifei Zhang, Mingxiao Huo, Ran Tian, Xiang Zhang, Yichen Xie, Chenfeng Xu, Pengliang Ji, Wei Zhan, Mingyu Ding, Masayoshi Tomizuka
The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning.
1 code implementation • 7 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.
1 code implementation • 19 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.
no code implementations • 15 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.
1 code implementation • 1 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.
no code implementations • ICCV 2023 • Jiacong Xu, Yi Zhang, Jiawei Peng, Wufei Ma, Artur Jesslen, Pengliang Ji, Qixin Hu, Jiehua Zhang, Qihao Liu, Jiahao Wang, Wei Ji, Chen Wang, Xiaoding Yuan, Prakhar Kaushik, Guofeng Zhang, Jie Liu, Yushan Xie, Yawen Cui, Alan Yuille, Adam Kortylewski
Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 keypoints, and importantly the pose and shape parameters of the SMAL model.
Ranked #1 on
Animal Pose Estimation
on Animal3D
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.
1 code implementation • 17 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.
no code implementations • 9 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.
no code implementations • 1 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.