Search Results for author: Chengqi Lyu

Found 13 papers, 12 papers with code

Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs

1 code implementation4 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.

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

1 code implementation10 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.

Math Mathematical Reasoning +1

Training Language Models to Critique With Multi-agent Feedback

no code implementations20 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.

Reinforcement Learning (RL)

ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models

1 code implementation5 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.

Hallucination Long Form Question Answering +1

ANAH: Analytical Annotation of Hallucinations in Large Language Models

1 code implementation30 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.

Generative Question Answering Hallucination +1

AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data

2 code implementations29 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.

Code Generation Diversity +1

Fake Alignment: Are LLMs Really Aligned Well?

1 code implementation10 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.

Multiple-choice

MultiModal-GPT: A Vision and Language Model for Dialogue with Humans

1 code implementation8 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.

Instruction Following Language Modeling +1

RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose

1 code implementation13 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)

2D Human Pose Estimation 2D Pose Estimation +1

RTMDet: An Empirical Study of Designing Real-Time Object Detectors

12 code implementations14 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.

Object object-detection +7

MMRotate: A Rotated Object Detection Benchmark using PyTorch

1 code implementation28 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.

Object object-detection +1

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