{"work":{"id":"7f3bac41-a0a5-4a7a-bfd2-526b616db745","openalex_id":null,"doi":null,"arxiv_id":"2308.02490","raw_key":null,"title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","authors":null,"authors_text":"Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu","year":2023,"venue":"cs.AI","abstract":"We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give model insights beyond a simple performance ranking. To this end, we present MM-Vet, designed based on the insight that the intriguing ability to solve complicated tasks is often achieved by a generalist model being able to integrate different core vision-language (VL) capabilities. MM-Vet defines 6 core VL capabilities and examines the 16 integrations of interest derived from the capability combination. For evaluation metrics, we propose an LLM-based evaluator for open-ended outputs. The evaluator enables the evaluation across different question types and answer styles, resulting in a unified scoring metric. We evaluate representative LMMs on MM-Vet, providing insights into the capabilities of different LMM system paradigms and models.","external_url":"https://arxiv.org/abs/2308.02490","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-10T09:37:00.827227+00:00","pith_arxiv_id":"2308.02490","created_at":"2026-05-10T05:25:54.856348+00:00","updated_at":"2026-07-10T09:37:00.827227+00:00","title_quality_ok":true,"display_title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","render_title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities"},"hub":{"state":{"work_id":"7f3bac41-a0a5-4a7a-bfd2-526b616db745","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":115,"external_cited_by_count":null,"distinct_field_count":8,"first_pith_cited_at":"2023-05-05T17:59:46+00:00","last_pith_cited_at":"2026-07-09T09:56:50+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T17:59:25.093185+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"dataset","n":18},{"context_role":"background","n":13},{"context_role":"baseline","n":3}],"polarity_counts":[{"context_polarity":"use_dataset","n":16},{"context_polarity":"background","n":14},{"context_polarity":"baseline","n":3},{"context_polarity":"unclear","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","claims":[{"claim_text":"We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give ","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"For baseline comparison, we include the following unified models: EMU2 Chat [31], Chameleon [32], Seed-X [7], VILA -U [36], LMfusion [ 28], Show-o [38], EMU3 [ 34], MetaMorph [ 33], Token- Flow [25], Janus [35], and Janus-Pro [4]. Image Understanding In the image understanding task, we evaluate the benchmark perfor- mance on VQAv2 [ 9], MMBench [ 20], SeedBench [ 14], MM -Vet [41], MME -Perception and MME-Cognition [6], MMMU [42], TextVQA [29], and RealWorldQA [37]. As shown in Table 1, our BLIP","claim_type":"dataset","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"This work is primarily aimed at MLLM pre-training teams. The computational cost is highly dependent on the scale of proprietary training data and the size of the model. 4.2. Evaluation & Benchmarks Fine-grained Image BenchmarksWe follow Opencom- pass [14] image leaderboard, evaluating on MMBench [50], MathVista [57], HallusionBench [25], OCRBench [52], AI2D [35], MMVet [108], MMStar [9], MMMU [109]. Video BenchmarksWe evaluate on a wide range of video benchmarks, including Opencompass video 5 Ta","claim_type":"dataset","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"0 - 56.8/55.749.9 - 517.1475.867.3/69.1- - 67.6 T able 4:Comparison with SOTA models on MLLM benchmarks. VQAv2 [38]; VQAT: TextVQA [104]; SQAI: ScienceQA-IMG [81]; MMMU [128]; MathV: MathVista [80]; MMEP/C: the Perception/Cognition split of MME [33]; MMB: MMBench [78]; SEED: SEED-Bench [62]; POPE [68]; LLaVA W: LLaVA-Bench (In-the-Wild) [76]; MM- Vet [127]. The two numbers reported in MMMU denote the performance on the val and test split, respectively. The two numbers reported in SEED denote the","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"the start of responses also improves the quality of the nega- tive responses generated by DropoutNTP, preventing a sig- nificant quality gap between positive and negative samples that could reduce training effectiveness. 5. Experiments 5.1. Main Results In this section, we compare our models with leading MLLMs on multimodal reasoning [16, 62, 78, 98, 107, 113, 114], complex Visual Question Answering (VQA) [112], and hallucination evaluation [88] tasks. Benchmarks. We evaluate the reasoning abili","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"tuned performance on ScienceQA [116]. LLaVA-Med [35] reports results on biomedical VQA [120], [121], [122]. The above evaluation methods are usually limited to a small range of selected tasks or datasets, lacking a compre- hensive quantitative comparison. To this end, some efforts have endeavored to develop new benchmarks specially designed for MLLMs [123], [124], [125], [126], [127], [128], [129]. For example, Fu et al . [123] construct a comprehen- sive evaluation benchmark MME that includes a","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"an Expert AGI to achieve strong performance on MMMU to demonstrate their broad and deep subject knowledge as well as expert-level understanding and reasoning capabilities. 2. Related Work Multimodal Pre-Training. In recent years, rapid progress has been made in multimodal pre-training, which aims to jointly encode vision and language in a fusion model. LXMERT [71], UNITER [10], VinVL [87], Oscar [37], VilBert [49], and VLP [93] are among the earliest work to train universal vision-language model","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities because it crossed a citation-hub threshold. Current citing contexts most often use it as dataset evidence (18 contexts).","role_counts":[{"n":18,"context_role":"dataset"},{"n":13,"context_role":"background"},{"n":3,"context_role":"baseline"}]},"error":null,"updated_at":"2026-07-02T02:52:16.722062+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"c61dd50a-94ed-4879-9f76-698a81073b01","orcid":null,"display_name":"Weihao Yu"},{"id":"18d9cdaf-45dc-4fe0-bbc4-3fa20cde428c","orcid":null,"display_name":"Zhengyuan Yang"},{"id":"ff9568fc-eeef-432e-8a39-03fe9431c1aa","orcid":null,"display_name":"Linjie Li"},{"id":"d567b51f-78fe-4051-a341-153bfc4adfdd","orcid":null,"display_name":"Jianfeng Wang"},{"id":"c1516ee6-d7c8-4910-97e1-a4a6b4244e6b","orcid":null,"display_name":"Kevin Lin"},{"id":"f8d8bf47-0aa8-45f5-b5ca-b0c9bc8aa4b2","orcid":null,"display_name":"Zicheng Liu"}]},"error":null,"updated_at":"2026-07-02T02:52:16.714246+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T17:48:42.869539+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","work_id":"806d2e73-71b3-4d56-87e0-39d571cc15d6","shared_citers":15},{"title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","work_id":"8abcfe4f-e0fb-44b7-9123-448fac95f90a","shared_citers":15},{"title":"LLaVA-OneVision: Easy Visual Task Transfer","work_id":"f5f2452b-f2a9-49ac-b38d-c76e18cdfe49","shared_citers":14},{"title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","work_id":"e22c3789-9e71-4242-b6ea-3e60e06e2b66","shared_citers":14},{"title":"MMBench: Is Your Multi-modal Model an All-around Player?","work_id":"3b44943d-0f15-4228-9ac3-0e376f4f9ada","shared_citers":14},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":12},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":11},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":11},{"title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","work_id":"23881ff0-b851-474c-8712-90744cc07a3a","shared_citers":11},{"title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","work_id":"0d0b977c-a42e-49b1-869e-b7360dca5282","shared_citers":10},{"title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","work_id":"a7e3a737-e007-42bc-be89-c4d34c5ee071","shared_citers":10},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":9},{"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","shared_citers":9},{"title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","work_id":"b8f5e260-fff5-444e-bcf5-2c42cfefd83d","shared_citers":8},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":8},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":8},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":7},{"title":"Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi","work_id":"da087b16-ea05-4064-980e-ce1d6e281d49","shared_citers":7},{"title":"Qwen Technical Report","work_id":"bb1fd52f-6b2f-437c-9516-37bdf6eb9be8","shared_citers":7},{"title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","work_id":"44525076-312a-4259-b79c-134cd7eeb297","shared_citers":7},{"title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","work_id":"2661b9a6-25cc-41a1-8100-612d2b801289","shared_citers":6},{"title":"Evaluating Object Hallucination in Large Vision-Language Models","work_id":"66d8ac3e-c134-4995-b528-550afa17586f","shared_citers":6},{"title":"Improved Baselines with Visual Instruction Tuning","work_id":"5baeaa33-5986-44a3-85a4-fcabd6fc1e8d","shared_citers":6},{"title":"Kimi-VL Technical Report","work_id":"c876520f-8a20-44f3-b92a-bf7d35bd430f","shared_citers":6}],"time_series":[{"n":2,"year":2023},{"n":5,"year":2024},{"n":7,"year":2025},{"n":25,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T17:48:46.125527+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T17:49:02.335343+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","claims":[{"claim_text":"We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give ","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"For baseline comparison, we include the following unified models: EMU2 Chat [31], Chameleon [32], Seed-X [7], VILA -U [36], LMfusion [ 28], Show-o [38], EMU3 [ 34], MetaMorph [ 33], Token- Flow [25], Janus [35], and Janus-Pro [4]. Image Understanding In the image understanding task, we evaluate the benchmark perfor- mance on VQAv2 [ 9], MMBench [ 20], SeedBench [ 14], MM -Vet [41], MME -Perception and MME-Cognition [6], MMMU [42], TextVQA [29], and RealWorldQA [37]. As shown in Table 1, our BLIP","claim_type":"dataset","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"This work is primarily aimed at MLLM pre-training teams. The computational cost is highly dependent on the scale of proprietary training data and the size of the model. 4.2. Evaluation & Benchmarks Fine-grained Image BenchmarksWe follow Opencom- pass [14] image leaderboard, evaluating on MMBench [50], MathVista [57], HallusionBench [25], OCRBench [52], AI2D [35], MMVet [108], MMStar [9], MMMU [109]. Video BenchmarksWe evaluate on a wide range of video benchmarks, including Opencompass video 5 Ta","claim_type":"dataset","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"0 - 56.8/55.749.9 - 517.1475.867.3/69.1- - 67.6 T able 4:Comparison with SOTA models on MLLM benchmarks. VQAv2 [38]; VQAT: TextVQA [104]; SQAI: ScienceQA-IMG [81]; MMMU [128]; MathV: MathVista [80]; MMEP/C: the Perception/Cognition split of MME [33]; MMB: MMBench [78]; SEED: SEED-Bench [62]; POPE [68]; LLaVA W: LLaVA-Bench (In-the-Wild) [76]; MM- Vet [127]. The two numbers reported in MMMU denote the performance on the val and test split, respectively. The two numbers reported in SEED denote the","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"the start of responses also improves the quality of the nega- tive responses generated by DropoutNTP, preventing a sig- nificant quality gap between positive and negative samples that could reduce training effectiveness. 5. Experiments 5.1. Main Results In this section, we compare our models with leading MLLMs on multimodal reasoning [16, 62, 78, 98, 107, 113, 114], complex Visual Question Answering (VQA) [112], and hallucination evaluation [88] tasks. Benchmarks. We evaluate the reasoning abili","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"tuned performance on ScienceQA [116]. LLaVA-Med [35] reports results on biomedical VQA [120], [121], [122]. The above evaluation methods are usually limited to a small range of selected tasks or datasets, lacking a compre- hensive quantitative comparison. To this end, some efforts have endeavored to develop new benchmarks specially designed for MLLMs [123], [124], [125], [126], [127], [128], [129]. For example, Fu et al . [123] construct a comprehen- sive evaluation benchmark MME that includes a","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"an Expert AGI to achieve strong performance on MMMU to demonstrate their broad and deep subject knowledge as well as expert-level understanding and reasoning capabilities. 2. Related Work Multimodal Pre-Training. In recent years, rapid progress has been made in multimodal pre-training, which aims to jointly encode vision and language in a fusion model. LXMERT [71], UNITER [10], VinVL [87], Oscar [37], VilBert [49], and VLP [93] are among the earliest work to train universal vision-language model","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities because it crossed a citation-hub threshold. Current citing contexts most often use it as dataset evidence (18 contexts).","role_counts":[{"n":18,"context_role":"dataset"},{"n":13,"context_role":"background"},{"n":3,"context_role":"baseline"}]},"error":null,"updated_at":"2026-07-02T02:52:16.718719+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","claims":[{"claim_text":"We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give ","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T17:49:11.980967+00:00"}},"summary":{"title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","claims":[{"claim_text":"We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give ","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","work_id":"806d2e73-71b3-4d56-87e0-39d571cc15d6","shared_citers":15},{"title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","work_id":"8abcfe4f-e0fb-44b7-9123-448fac95f90a","shared_citers":15},{"title":"LLaVA-OneVision: Easy Visual Task Transfer","work_id":"f5f2452b-f2a9-49ac-b38d-c76e18cdfe49","shared_citers":14},{"title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","work_id":"e22c3789-9e71-4242-b6ea-3e60e06e2b66","shared_citers":14},{"title":"MMBench: Is Your Multi-modal Model an All-around Player?","work_id":"3b44943d-0f15-4228-9ac3-0e376f4f9ada","shared_citers":14},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":12},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":11},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":11},{"title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","work_id":"23881ff0-b851-474c-8712-90744cc07a3a","shared_citers":11},{"title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","work_id":"0d0b977c-a42e-49b1-869e-b7360dca5282","shared_citers":10},{"title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","work_id":"a7e3a737-e007-42bc-be89-c4d34c5ee071","shared_citers":10},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":9},{"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","shared_citers":9},{"title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","work_id":"b8f5e260-fff5-444e-bcf5-2c42cfefd83d","shared_citers":8},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":8},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":8},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":7},{"title":"Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi","work_id":"da087b16-ea05-4064-980e-ce1d6e281d49","shared_citers":7},{"title":"Qwen Technical Report","work_id":"bb1fd52f-6b2f-437c-9516-37bdf6eb9be8","shared_citers":7},{"title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","work_id":"44525076-312a-4259-b79c-134cd7eeb297","shared_citers":7},{"title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","work_id":"2661b9a6-25cc-41a1-8100-612d2b801289","shared_citers":6},{"title":"Evaluating Object Hallucination in Large Vision-Language Models","work_id":"66d8ac3e-c134-4995-b528-550afa17586f","shared_citers":6},{"title":"Improved Baselines with Visual Instruction Tuning","work_id":"5baeaa33-5986-44a3-85a4-fcabd6fc1e8d","shared_citers":6},{"title":"Kimi-VL Technical Report","work_id":"c876520f-8a20-44f3-b92a-bf7d35bd430f","shared_citers":6}],"time_series":[{"n":2,"year":2023},{"n":5,"year":2024},{"n":7,"year":2025},{"n":25,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"d567b51f-78fe-4051-a341-153bfc4adfdd","orcid":null,"display_name":"Jianfeng Wang","source":"manual","import_confidence":0.72},{"id":"c1516ee6-d7c8-4910-97e1-a4a6b4244e6b","orcid":null,"display_name":"Kevin Lin","source":"manual","import_confidence":0.72},{"id":"ff9568fc-eeef-432e-8a39-03fe9431c1aa","orcid":null,"display_name":"Linjie Li","source":"manual","import_confidence":0.72},{"id":"c61dd50a-94ed-4879-9f76-698a81073b01","orcid":null,"display_name":"Weihao Yu","source":"manual","import_confidence":0.72},{"id":"18d9cdaf-45dc-4fe0-bbc4-3fa20cde428c","orcid":null,"display_name":"Zhengyuan Yang","source":"manual","import_confidence":0.72},{"id":"f8d8bf47-0aa8-45f5-b5ca-b0c9bc8aa4b2","orcid":null,"display_name":"Zicheng Liu","source":"manual","import_confidence":0.72}]}}