1 code implementation • 4 Mar 2025 • Yuzhe Gu, Wenwei Zhang, Chengqi Lyu, Dahua Lin, Kai Chen
We further study the generalization property of Mask-DPO using different training sample scaling strategies and find that scaling the number of topics in the dataset is more effective than the number of questions.
1 code implementation • 10 Feb 2025 • Chengqi Lyu, Songyang Gao, Yuzhe Gu, Wenwei Zhang, Jianfei Gao, Kuikun Liu, Ziyi Wang, Shuaibin Li, Qian Zhao, Haian Huang, Weihan Cao, Jiangning Liu, Hongwei Liu, Junnan Liu, Songyang Zhang, Dahua Lin, Kai Chen
To alleviate the long-existing difficulties brought by sparse rewards in RL, which are even exacerbated by the partial correctness of the long chain of thought for reasoning tasks, we further apply a token-level reward model to sample important tokens in reasoning trajectories for learning.
no code implementations • 20 Oct 2024 • Tian Lan, Wenwei Zhang, Chengqi Lyu, Shuaibin Li, Chen Xu, Heyan Huang, Dahua Lin, Xian-Ling Mao, Kai Chen
To overcome these challenges, this paper proposes a novel data generation pipeline, named MultiCritique, that improves the critique ability of LLMs by utilizing multi-agent feedback in both the SFT and reinforcement learning (RL) stages.
1 code implementation • 5 Jul 2024 • Yuzhe Gu, Ziwei Ji, Wenwei Zhang, Chengqi Lyu, Dahua Lin, Kai Chen
Such an annotator can not only evaluate the hallucination levels of various LLMs on the large-scale dataset but also help to mitigate the hallucination of LLMs generations, with the Natural Language Inference (NLI) metric increasing from 25% to 37% on HaluEval.
1 code implementation • 30 May 2024 • Ziwei Ji, Yuzhe Gu, Wenwei Zhang, Chengqi Lyu, Dahua Lin, Kai Chen
Reducing the `$\textit{hallucination}$' problem of Large Language Models (LLMs) is crucial for their wide applications.
2 code implementations • 29 May 2024 • Zifan Song, Yudong Wang, Wenwei Zhang, Kuikun Liu, Chengqi Lyu, Demin Song, Qipeng Guo, Hang Yan, Dahua Lin, Kai Chen, Cairong Zhao
Open-source Large Language Models (LLMs) and their specialized variants, particularly Code LLMs, have recently delivered impressive performance.
1 code implementation • 10 Nov 2023 • Yixu Wang, Yan Teng, Kexin Huang, Chengqi Lyu, Songyang Zhang, Wenwei Zhang, Xingjun Ma, Yu-Gang Jiang, Yu Qiao, Yingchun Wang
The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety.
1 code implementation • 8 May 2023 • Tao Gong, Chengqi Lyu, Shilong Zhang, Yudong Wang, Miao Zheng, Qian Zhao, Kuikun Liu, Wenwei Zhang, Ping Luo, Kai Chen
To further enhance the ability to chat with humans of the MultiModal-GPT, we utilize language-only instruction-following data to train the MultiModal-GPT jointly.
2 code implementations • CVPR 2023 • Shilong Zhang, Xinjiang Wang, Jiaqi Wang, Jiangmiao Pang, Chengqi Lyu, Wenwei Zhang, Ping Luo, Kai Chen
Concretely, we first lay dense queries like traditional detectors and then select distinct ones for one-to-one assignments.
Ranked #4 on
Object Detection
on CrowdHuman (full body)
1 code implementation • 13 Mar 2023 • Tao Jiang, Peng Lu, Li Zhang, Ningsheng Ma, Rui Han, Chengqi Lyu, Yining Li, Kai Chen
Recent studies on 2D pose estimation have achieved excellent performance on public benchmarks, yet its application in the industrial community still suffers from heavy model parameters and high latency.
Ranked #1 on
2D Human Pose Estimation
on Human-Art
(Validation AP metric)
12 code implementations • 14 Dec 2022 • Chengqi Lyu, Wenwei Zhang, Haian Huang, Yue Zhou, Yudong Wang, Yanyi Liu, Shilong Zhang, Kai Chen
In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection.
Ranked #1 on
Object Detection In Aerial Images
on DOTA 1.0
1 code implementation • CVPR 2023 • Xinjiang Wang, Xingyi Yang, Shilong Zhang, Yijiang Li, Litong Feng, Shijie Fang, Chengqi Lyu, Kai Chen, Wayne Zhang
In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD).
1 code implementation • 28 Apr 2022 • Yue Zhou, Xue Yang, Gefan Zhang, Jiabao Wang, Yanyi Liu, Liping Hou, Xue Jiang, Xingzhao Liu, Junchi Yan, Chengqi Lyu, Wenwei Zhang, Kai Chen
We present an open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning.