Yiming Cui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yiming Cui has a total of 86 co-authors. Here are the top co-authors by number of shared publications:
- Ting Liu
Harbin Institute of Technology, Harbin, China
29 shared publications - Shijin Wang
State Key Laboratory of Cognitive Intelligence, Hefei, China and iFLYTEK AI Research, Hefei, China
26 shared publications - Guoping Hu
Flytek Research China
22 shared publications Wanxiang Che
16 shared publications- Zhipeng Chen
State Key Laboratory of Cognitive Intelligence iFLYTEK Research China
10 shared publications - Ziqing Yang
State Key Laboratory of Cognitive Intelligence iFLYTEK Research China
10 shared publications
Latest Publications
- Open Access
Evaluating Large Language Models on Multimodal Chemistry Olympiad Exams
Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, molecular structures, and structured visual data. Here, we systematically evaluate 40 proprietary and open-source multimodal LLMs, including GPT-5, o3, Gemini-2.5-Pro, and Qwen2.5-VL, on a curated benchmark of Olympiad-style chemistry questions drawn from over two decades of U.S. National Chemistry Olympiad (USNCO) exams. These questions require integrated visual and textual reasoning across diverse modalities. We find that many models struggle with modality fusion, where in some cases, removing the image even improves accuracy, indicating misalignment in vision-language integration. Chain-of-Thought prompting consistently enhances both accuracy and visual grounding, as demonstrated through ablation studies and occlusion-based interpretability. Our results reveal critical limitations in the scientific reasoning abilities of current MLLMs, providing actionable strategies for developing more robust and interpretable multimodal systems in chemistry. This work provides a timely benchmark for measuring progress in domain-specific multimodal AI and underscores the need for further advances at the intersection of artificial intelligence and scientific reasoning.
Open AccessEvaluating Large Language Models on Multimodal Chemistry Olympiad Exams
Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, molecular structures, and structured visual data. Here, we systematically evaluate 40 proprietary and open-source multimodal LLMs, including GPT-5, o3, Gemini-2.5-Pro, and Qwen2.5-VL, on a curated benchmark of Olympiad-style chemistry questions drawn from over two decades of U.S. National Chemistry Olympiad (USNCO) exams. These questions require integrated visual and textual reasoning across diverse modalities. We find that many models struggle with modality fusion, where in some cases, removing the image even improves accuracy, indicating misalignment in vision-language integration. Chain-of-Thought prompting consistently enhances both accuracy and visual grounding, as demonstrated through ablation studies and occlusion-based interpretability. Our results reveal critical limitations in the scientific reasoning abilities of current MLLMs, providing actionable strategies for developing more robust and interpretable multimodal systems in chemistry. This work provides a timely benchmark for measuring progress in domain-specific multimodal AI and underscores the need for further advances at the intersection of artificial intelligence and scientific reasoning.
- Open Access
Large and Small Model Collaboration for Air Interface
Large artificial intelligence models (LAMs) have shown strong capability in wireless communications, yet existing works mainly rely on their generalized knowledge across environments while overlooking the potential gains of environment-specific adaptation. Directly fine-tuning LAMs for adaptation is often impractical due to prohibitive training costs, low inference efficiency in multi-user scenarios, and the risk of catastrophic forgetting, in addition to the limited accessibility of model parameters. To address these limitations, we establish a collaborative framework for air interface. In this framework, unlike prior approaches that either depend solely on LAMs or require direct fine-tuning, LAMs are exploited as a universal channel knowledge base while small artificial intelligence models (SAMs) are employed as lightweight plugins to capture environment-specific knowledge, facilitating efficient environment-specific adaptation of LAMs. Subsequently, we instantiate this framework for CSI feedback tasks, and develop a large and small collaboration framework for CSI feedback, referred to as LASCO. LASCO operates by letting the base LAM produce an initial CSI reconstruction, learning the environment-induced reconstruction shift through a reference SAM and a proxy SAM, and transferring this shift back to the LAM. To further enhance adaptability, we introduce elastic-LASCO (E-LASCO), which augments LASCO with learnable collaboration coefficients that control the contribution of LAMs and SAMs across different environments. Numerical results demonstrate that LASCO and E-LASCO enables LAMs to achieve environment-specific performance gains with significantly reduced training costs, lower data collection requirements, and faster adaptation speed.
Open AccessLarge and Small Model Collaboration for Air Interface
Large artificial intelligence models (LAMs) have shown strong capability in wireless communications, yet existing works mainly rely on their generalized knowledge across environments while overlooking the potential gains of environment-specific adaptation. Directly fine-tuning LAMs for adaptation is often impractical due to prohibitive training costs, low inference efficiency in multi-user scenarios, and the risk of catastrophic forgetting, in addition to the limited accessibility of model parameters. To address these limitations, we establish a collaborative framework for air interface. In this framework, unlike prior approaches that either depend solely on LAMs or require direct fine-tuning, LAMs are exploited as a universal channel knowledge base while small artificial intelligence models (SAMs) are employed as lightweight plugins to capture environment-specific knowledge, facilitating efficient environment-specific adaptation of LAMs. Subsequently, we instantiate this framework for CSI feedback tasks, and develop a large and small collaboration framework for CSI feedback, referred to as LASCO. LASCO operates by letting the base LAM produce an initial CSI reconstruction, learning the environment-induced reconstruction shift through a reference SAM and a proxy SAM, and transferring this shift back to the LAM. To further enhance adaptability, we introduce elastic-LASCO (E-LASCO), which augments LASCO with learnable collaboration coefficients that control the contribution of LAMs and SAMs across different environments. Numerical results demonstrate that LASCO and E-LASCO enables LAMs to achieve environment-specific performance gains with significantly reduced training costs, lower data collection requirements, and faster adaptation speed.
- Open Access
- 13 December 2025
- Published by Springer Nature in Communications Chemistry
- Vol. 8 (1)
Evaluating large language models on multimodal chemistry olympiad exams
Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, molecular structures, and structured visual data. Here, we systematically evaluate 40 proprietary and open-source multimodal LLMs, including GPT-5, o3, Gemini-2.5-Pro, and Qwen2.5-VL, on a curated benchmark of Olympiad-style chemistry questions drawn from over two decades of U.S. National Chemistry Olympiad (USNCO) exams. These questions require integrated visual and textual reasoning across diverse modalities. We find that many models struggle with modality fusion, where, in some cases, removing the image even improves accuracy, indicating misalignment in vision-language integration. Chain-of-Thought prompting consistently enhances both accuracy and visual grounding, as demonstrated through ablation studies and occlusion-based interpretability. Our results reveal critical limitations in the scientific reasoning abilities of current MLLMs, providing actionable strategies for developing more robust and interpretable multimodal systems in chemistry. This work provides a timely benchmark for measuring progress in domain-specific multimodal AI and underscores the need for further advances at the intersection of artificial intelligence and scientific reasoning.
- 13 December 2025
- Published by Springer Nature in Communications Chemistry
- Vol. 8 (1)
Open AccessEvaluating large language models on multimodal chemistry olympiad exams
Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, molecular structures, and structured visual data. Here, we systematically evaluate 40 proprietary and open-source multimodal LLMs, including GPT-5, o3, Gemini-2.5-Pro, and Qwen2.5-VL, on a curated benchmark of Olympiad-style chemistry questions drawn from over two decades of U.S. National Chemistry Olympiad (USNCO) exams. These questions require integrated visual and textual reasoning across diverse modalities. We find that many models struggle with modality fusion, where, in some cases, removing the image even improves accuracy, indicating misalignment in vision-language integration. Chain-of-Thought prompting consistently enhances both accuracy and visual grounding, as demonstrated through ablation studies and occlusion-based interpretability. Our results reveal critical limitations in the scientific reasoning abilities of current MLLMs, providing actionable strategies for developing more robust and interpretable multimodal systems in chemistry. This work provides a timely benchmark for measuring progress in domain-specific multimodal AI and underscores the need for further advances at the intersection of artificial intelligence and scientific reasoning.
- Open Access
ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding
Large Vision-Language Models (LVLMs) have recently demonstrated remarkable progress, yet hallucination remains a critical barrier, particularly in chart understanding, which requires sophisticated perceptual and cognitive abilities as well as rigorous factual accuracy. While prior work has investigated hallucinations and chart comprehension independently, their intersection remains largely unexplored. To address this gap, we present ChartHal, a benchmark that features a fine-grained taxonomy of hallucination scenarios in chart understanding, along with a human-validated dataset of 1,062 samples. Our evaluation shows that state-of-the-art LVLMs suffer from severe hallucinations on ChartHal, including proprietary models such as GPT-5 and o4-mini, which achieve only 34.46% and 22.79% accuracy, respectively. Further analysis reveals that questions involving information absent from or contradictory to charts are especially likely to trigger hallucinations, underscoring the urgent need for more robust mitigation strategies. Code and data are available at https://github.com/ymcui/ChartHal .
Open AccessChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding
Large Vision-Language Models (LVLMs) have recently demonstrated remarkable progress, yet hallucination remains a critical barrier, particularly in chart understanding, which requires sophisticated perceptual and cognitive abilities as well as rigorous factual accuracy. While prior work has investigated hallucinations and chart comprehension independently, their intersection remains largely unexplored. To address this gap, we present ChartHal, a benchmark that features a fine-grained taxonomy of hallucination scenarios in chart understanding, along with a human-validated dataset of 1,062 samples. Our evaluation shows that state-of-the-art LVLMs suffer from severe hallucinations on ChartHal, including proprietary models such as GPT-5 and o4-mini, which achieve only 34.46% and 22.79% accuracy, respectively. Further analysis reveals that questions involving information absent from or contradictory to charts are especially likely to trigger hallucinations, underscoring the urgent need for more robust mitigation strategies. Code and data are available at https://github.com/ymcui/ChartHal .
- Open Access
Exploring the Potential of Large Language Models for Massive MIMO CSI Feedback
Large language models (LLMs) have achieved remarkable success across a wide range of tasks, particularly in natural language processing and computer vision. This success naturally raises an intriguing yet unexplored question: Can LLMs be harnessed to tackle channel state information (CSI) compression and feedback in massive multiple-input multiple-output (MIMO) systems? Efficient CSI feedback is a critical challenge in next-generation wireless communication. In this paper, we pioneer the use of LLMs for CSI compression, introducing a novel framework that leverages the powerful denoising capabilities of LLMs -- capable of error correction in language tasks -- to enhance CSI reconstruction performance. To effectively adapt LLMs to CSI data, we design customized pre-processing, embedding, and post-processing modules tailored to the unique characteristics of wireless signals. Extensive numerical results demonstrate the promising potential of LLMs in CSI feedback, opening up possibilities for this research direction.
Open AccessExploring the Potential of Large Language Models for Massive MIMO CSI Feedback
Large language models (LLMs) have achieved remarkable success across a wide range of tasks, particularly in natural language processing and computer vision. This success naturally raises an intriguing yet unexplored question: Can LLMs be harnessed to tackle channel state information (CSI) compression and feedback in massive multiple-input multiple-output (MIMO) systems? Efficient CSI feedback is a critical challenge in next-generation wireless communication. In this paper, we pioneer the use of LLMs for CSI compression, introducing a novel framework that leverages the powerful denoising capabilities of LLMs -- capable of error correction in language tasks -- to enhance CSI reconstruction performance. To effectively adapt LLMs to CSI data, we design customized pre-processing, embedding, and post-processing modules tailored to the unique characteristics of wireless signals. Extensive numerical results demonstrate the promising potential of LLMs in CSI feedback, opening up possibilities for this research direction.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 15839-15855
Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation
Tianhao Niu, Yiming Cui, Baoxin Wang, Xiao Xu, Xin Yao, Qingfu Zhu, Dayong Wu, Shijin Wang, Wanxiang Che. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 15839-15855
Open AccessChart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation
Tianhao Niu, Yiming Cui, Baoxin Wang, Xiao Xu, Xin Yao, Qingfu Zhu, Dayong Wu, Shijin Wang, Wanxiang Che. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
Efficient Deep Learning-based Cascaded Channel Feedback in RIS-Assisted Communications
In the realm of reconfigurable intelligent surface (RIS)-assisted communication systems, the connection between a base station (BS) and user equipment (UE) is formed by a cascaded channel, merging the BS-RIS and RIS-UE channels. Due to the fixed positioning of the BS and RIS and the mobility of UE, these two channels generally exhibit different time-varying characteristics, which are challenging to identify and exploit for feedback overhead reduction, given the separate channel estimation difficulty. To address this challenge, this letter introduces an innovative deep learning-based framework tailored for cascaded channel feedback, ingeniously capturing the intrinsic time variation in the cascaded channel. When an entire cascaded channel has been sent to the BS, this framework advocates the feedback of an efficient representation of this variation within a subsequent period through an extraction-compression scheme. This scheme involves RIS unit-grained channel variation extraction, followed by autoencoder-based deep compression to enhance compactness. Numerical simulations confirm that this feedback framework significantly reduces both the feedback and computational burdens.
Open AccessEfficient Deep Learning-based Cascaded Channel Feedback in RIS-Assisted Communications
In the realm of reconfigurable intelligent surface (RIS)-assisted communication systems, the connection between a base station (BS) and user equipment (UE) is formed by a cascaded channel, merging the BS-RIS and RIS-UE channels. Due to the fixed positioning of the BS and RIS and the mobility of UE, these two channels generally exhibit different time-varying characteristics, which are challenging to identify and exploit for feedback overhead reduction, given the separate channel estimation difficulty. To address this challenge, this letter introduces an innovative deep learning-based framework tailored for cascaded channel feedback, ingeniously capturing the intrinsic time variation in the cascaded channel. When an entire cascaded channel has been sent to the BS, this framework advocates the feedback of an efficient representation of this variation within a subsequent period through an extraction-compression scheme. This scheme involves RIS unit-grained channel variation extraction, followed by autoencoder-based deep compression to enhance compactness. Numerical simulations confirm that this feedback framework significantly reduces both the feedback and computational burdens.
- Open Access
Self-Evolving GPT: A Lifelong Autonomous Experiential Learner
To improve the performance of large language models (LLMs), researchers have explored providing LLMs with textual task-solving experience via prompts. However, they rely on manual efforts to acquire and apply such experience for each task, which is not feasible for the growing demand for LLMs and the variety of user questions. To address this issue, we design a lifelong autonomous experiential learning framework based on LLMs to explore whether LLMs can imitate human ability for learning and utilizing experience. It autonomously learns and accumulates experience through experience transfer and induction, categorizing the types of input questions to select which accumulated experience to employ for them. Experimental results on six widely used NLP datasets show that our framework performs reliably in each intermediate step and effectively improves the performance of GPT-3.5 and GPT-4. This validates the feasibility of using LLMs to mimic human experiential learning and application capabilities. Additionally, we provide a detailed analysis of the behavior of our framework at each step.
Open AccessSelf-Evolving GPT: A Lifelong Autonomous Experiential Learner
To improve the performance of large language models (LLMs), researchers have explored providing LLMs with textual task-solving experience via prompts. However, they rely on manual efforts to acquire and apply such experience for each task, which is not feasible for the growing demand for LLMs and the variety of user questions. To address this issue, we design a lifelong autonomous experiential learning framework based on LLMs to explore whether LLMs can imitate human ability for learning and utilizing experience. It autonomously learns and accumulates experience through experience transfer and induction, categorizing the types of input questions to select which accumulated experience to employ for them. Experimental results on six widely used NLP datasets show that our framework performs reliably in each intermediate step and effectively improves the performance of GPT-3.5 and GPT-4. This validates the feasibility of using LLMs to mimic human experiential learning and application capabilities. Additionally, we provide a detailed analysis of the behavior of our framework at each step.
- Open Access
Deep Learning-based CSI Feedback in Wi-Fi Systems
In Wi-Fi systems, channel state information (CSI) plays a crucial role in enabling access points to execute beamforming operations. However, the feedback overhead associated with CSI significantly hampers the throughput improvements. Recent advancements in deep learning (DL) have transformed the approach to CSI feedback in cellular systems. Drawing inspiration from the successes witnessed in the realm of mobile communications, this paper introduces a DL-based CSI feedback framework, named EFNet, tailored for Wi-Fi systems. The proposed framework leverages an autoencoder to achieve precise feedback with minimal overhead. The process involves the station utilizing the encoder to compress and quantize a series of matrices into codeword bit streams, which are then fed back to the access point. Subsequently, the decoder installed at the AP reconstructs beamforming matrices from these bit streams. We implement the EFNet system using standard Wi-Fi equipment operating in the 2.4 GHz band. Experimental findings in an office environment reveal a remarkable 80.77% reduction in feedback overhead compared to the 802.11ac standard, alongside a significant boost in net throughput of up to 30.72%.
Open AccessDeep Learning-based CSI Feedback in Wi-Fi Systems
In Wi-Fi systems, channel state information (CSI) plays a crucial role in enabling access points to execute beamforming operations. However, the feedback overhead associated with CSI significantly hampers the throughput improvements. Recent advancements in deep learning (DL) have transformed the approach to CSI feedback in cellular systems. Drawing inspiration from the successes witnessed in the realm of mobile communications, this paper introduces a DL-based CSI feedback framework, named EFNet, tailored for Wi-Fi systems. The proposed framework leverages an autoencoder to achieve precise feedback with minimal overhead. The process involves the station utilizing the encoder to compress and quantize a series of matrices into codeword bit streams, which are then fed back to the access point. Subsequently, the decoder installed at the AP reconstructs beamforming matrices from these bit streams. We implement the EFNet system using standard Wi-Fi equipment operating in the 2.4 GHz band. Experimental findings in an office environment reveal a remarkable 80.77% reduction in feedback overhead compared to the 802.11ac standard, alongside a significant boost in net throughput of up to 30.72%.
- Open Access
Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral
Mixtral, a representative sparse mixture of experts (SMoE) language model, has received significant attention due to its unique model design and superior performance. Based on Mixtral-8x7B-v0.1, in this paper, we propose Chinese-Mixtral and Chinese-Mixtral-Instruct with improved Chinese language abilities by adopting further pre-training and instruction fine-tuning. Experimental results show that our Chinese-Mixtral and Chinese-Mixtral-Instruct successfully improve Chinese understanding and generation performance while retaining the original English abilities. Then, we discuss several key questions when performing language adaptation on large language models, including the necessity of extending the language-specific vocabulary and the choice of the initialization model (foundation model v.s. instruction model), by providing empirical results and analysis. We also present the visualizations of each expert to examine their importance on downstream tasks. Our resources are publicly available through \url{https://github.com/ymcui/Chinese-Mixtral}.
Open AccessRethinking LLM Language Adaptation: A Case Study on Chinese Mixtral
Mixtral, a representative sparse mixture of experts (SMoE) language model, has received significant attention due to its unique model design and superior performance. Based on Mixtral-8x7B-v0.1, in this paper, we propose Chinese-Mixtral and Chinese-Mixtral-Instruct with improved Chinese language abilities by adopting further pre-training and instruction fine-tuning. Experimental results show that our Chinese-Mixtral and Chinese-Mixtral-Instruct successfully improve Chinese understanding and generation performance while retaining the original English abilities. Then, we discuss several key questions when performing language adaptation on large language models, including the necessity of extending the language-specific vocabulary and the choice of the initialization model (foundation model v.s. instruction model), by providing empirical results and analysis. We also present the visualizations of each expert to examine their importance on downstream tasks. Our resources are publicly available through \url{https://github.com/ymcui/Chinese-Mixtral}.