AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process.

Shilin Yan

Xintong Zhang Xiaowen Zhang Jongrong Wu Zhi Gao 0002 Shilin Yan Zhenxin Diao Kunpeng Gao Xuanyan Chen Yuwei Wu 0001 Yunde Jia Qing Li 0003 AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process. 2026 February abs/2602.02676 CoRR https://doi.org/10.48550/arXiv.2602.02676 db/journals/corr/corr2602.html#abs-2602-02676 streams/journals/corr

Jintao Tong Shilin Yan Hongwei Xue Xiaojun Tang Kunyu Shi Guannan Zhang Ruixuan Li 0001 Yixiong Zou SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs. 2026 February abs/2602.06040 CoRR https://doi.org/10.48550/arXiv.2602.06040 db/journals/corr/corr2602.html#abs-2602-06040 streams/journals/corr

Pengxiang Li Joey Tsai Hongwei Xue Kunyu Shi Shilin Yan Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes. 2026 March abs/2603.05454 CoRR https://doi.org/10.48550/arXiv.2603.05454 db/journals/corr/corr2603.html#abs-2603-05454 streams/journals/corr

Mingyue Li Xin Yang Shilin Yan Jinye Ran Morui Zhu Zirui Peng Huanqing Peng Wei Peng Guanghua Zhang Shuo Li Hao Zhang Phase-Interface Instance Segmentation as a Visual Sensor for Laboratory Process Monitoring. 2026 March abs/2603.10782 CoRR https://doi.org/10.48550/arXiv.2603.10782 db/journals/corr/corr2603.html#abs-2603-10782 streams/journals/corr

Haozhan Shen Shilin Yan Hongwei Xue Shuaiqi Lu Xiaojun Tang Guannan Zhang Tiancheng Zhao Jianwei Yin MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning. 2026 March abs/2603.12266 CoRR https://doi.org/10.48550/arXiv.2603.12266 db/journals/corr/corr2603.html#abs-2603-12266 streams/journals/corr

Shilin Yan Jintao Tong Hongwei Xue Xiaojun Tang Yangyang Wang Kunyu Shi Guannan Zhang Ruixuan Li 0001 Yixiong Zou Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models. 2026 April abs/2604.08545 CoRR https://doi.org/10.48550/arXiv.2604.08545 db/journals/corr/corr2604.html#abs-2604-08545 streams/journals/corr

Yuqi Tang Yang Shi 0009 Zhuoran Zhang 0003 Qixun Wang 0002 Xuehai Bai Yue Ding 0009 Ruizhe Chen Bohan Zeng Xinlong Chen Xuanyu Zhu 0001 Bozhou Li Yuran Wang 0003 Yifan Dai Chengzhuo Tong Xinyu Liu Yiyan Ji Yujie Wei Yuhao Dong Shilin Yan Fengxiang Wang 0004 Yifan Zhang 0004 Haotian Wang 0001 Yuanxing Zhang Pengfei Wan 0001 Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos. 2026 May abs/2605.18984 CoRR https://doi.org/10.48550/arXiv.2605.18984 db/journals/corr/corr2605.html#abs-2605-18984 streams/journals/corr

Lingyi Hong Jinglun Li Xinyu Zhou 0006 Shilin Yan Pinxue Guo Kaixun Jiang Zhaoyu Chen 0001 Shuyong Gao Runze Li Xingdong Sheng Wei Zhang 0016 Hong Lu 0001 Wenqiang Zhang General Compression Framework for Efficient Transformer Object Tracking. 2025 ICCV 13427-13437 conf/iccv/2025 https://doi.org/10.1109/ICCV51701.2025.01247 db/conf/iccv/iccv2025.html#HongLZYGJCGLSZLZ25 streams/conf/iccv Zehao Xiao Shilin Yan Jack Hong Jiayin Cai Xiaolong Jiang Yao Hu 0002 Jiayi Shen Qi Wang 0005 Cees G. M. Snoek DynaPrompt: Dynamic Test-Time Prompt Tuning. 2025 ICLR https://openreview.net/forum?id=EFZEdHB3Mp conf/iclr/2025 db/conf/iclr/iclr2025.html#XiaoYHCJHSWS25 Shilin Yan Ouxiang Li Jiayin Cai Yanbin Hao Xiaolong Jiang Yao Hu 0002 Weidi Xie A Sanity Check for AI-generated Image Detection. 2025 ICLR https://openreview.net/forum?id=ODRHZrkOQM conf/iclr/2025 db/conf/iclr/iclr2025.html#YanLCHJ0X25 Ruichuan An Sihan Yang Renrui Zhang Zijun Shen Ming Lu 0002 Gaole Dai Hao Liang 0017 Ziyu Guo Shilin Yan Yulin Luo Bocheng Zou Chaoqun Yang Wentao Zhang 0001 UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens. 2025 NeurIPS http://papers.nips.cc/paper_files/paper/2025/hash/d531364f1771e0972c1d11c334a0efb4-Abstract-Conference.html conf/nips/2025 db/conf/nips/neurips2025.html#AnYZSLDLGYLZYZ25

Zehao Xiao Shilin Yan Jack Hong Jiayin Cai Xiaolong Jiang Yao Hu 0002 Jiayi Shen Qi Wang 0005 Cees G. M. Snoek DynaPrompt: Dynamic Test-Time Prompt Tuning. 2025 January abs/2501.16404 CoRR https://doi.org/10.48550/arXiv.2501.16404 db/journals/corr/corr2501.html#abs-2501-16404 streams/journals/corr

Jack Hong Shilin Yan Jiayin Cai Xiaolong Jiang Yao Hu 0002 Weidi Xie WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs. 2025 February abs/2502.04326 CoRR https://doi.org/10.48550/arXiv.2502.04326 db/journals/corr/corr2502.html#abs-2502-04326 streams/journals/corr

Rongyao Fang Chengqi Duan Kun Wang 0056 Linjiang Huang Hao Li 0069 Shilin Yan Hao Tian 0006 Xingyu Zeng Rui Zhao 0001 Jifeng Dai Xihui Liu Hongsheng Li 0001 GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing. 2025 March abs/2503.10639 CoRR https://doi.org/10.48550/arXiv.2503.10639 db/journals/corr/corr2503.html#abs-2503-10639 streams/journals/corr

Dongzhi Jiang Ziyu Guo Renrui Zhang Zhuofan Zong Hao Li 0069 Le Zhuo Shilin Yan Pheng-Ann Heng Hongsheng Li 0001 T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT. 2025 May abs/2505.00703 CoRR https://doi.org/10.48550/arXiv.2505.00703 db/journals/corr/corr2505.html#abs-2505-00703 streams/journals/corr

Ruichuan An Sihan Yang Renrui Zhang Zijun Shen Ming Lu 0002 Gaole Dai Hao Liang 0017 Ziyu Guo Shilin Yan Yulin Luo Bocheng Zou Chaoqun Yang Wentao Zhang 0001 UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens. 2025 May abs/2505.14671 CoRR https://doi.org/10.48550/arXiv.2505.14671 db/journals/corr/corr2505.html#abs-2505-14671 streams/journals/corr

Shilin Yan Jiaming Han Joey Tsai Hongwei Xue Rongyao Fang Lingyi Hong Ziyu Guo Ray Zhang 0002 CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms. 2025 May abs/2505.17020 CoRR https://doi.org/10.48550/arXiv.2505.17020 db/journals/corr/corr2505.html#abs-2505-17020 streams/journals/corr

Jack Hong Shilin Yan Zehao Xiao Jiayin Cai Xiaolong Jiang Yao Hu 0002 Henghui Ding Progressive Scaling Visual Object Tracking. 2025 May abs/2505.19990 CoRR https://doi.org/10.48550/arXiv.2505.19990 db/journals/corr/corr2505.html#abs-2505-19990 streams/journals/corr

Pengxiang Li Shilin Yan Joey Tsai Renrui Zhang Ruichuan An Ziyu Guo Xiaowei Gao Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking. 2025 May abs/2505.20199 CoRR https://doi.org/10.48550/arXiv.2505.20199 db/journals/corr/corr2505.html#abs-2505-20199 streams/journals/corr

Xinyan Chen 0001 Renrui Zhang Dongzhi Jiang Aojun Zhou Shilin Yan Weifeng Lin Hongsheng Li 0001 MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning. 2025 June abs/2506.05331 CoRR https://doi.org/10.48550/arXiv.2506.05331 db/journals/corr/corr2506.html#abs-2506-05331 streams/journals/corr

Pengxiang Li Yefan Zhou Dilxat Muhtar Lu Yin 0006 Shilin Yan Li Shen 0008 Yi Liang Soroush Vosoughi Shiwei Liu 0003 Diffusion Language Models Know the Answer Before Decoding. 2025 August abs/2508.19982 CoRR https://doi.org/10.48550/arXiv.2508.19982 db/journals/corr/corr2508.html#abs-2508-19982 streams/journals/corr

Binxiao Xu Junyu Feng Ruichuan An Yulin Luo Shilin Yan Hao Liang 0017 Ming Lu 0002 Wentao Zhang 0001 Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval. 2025 October abs/2510.22765 CoRR https://doi.org/10.48550/arXiv.2510.22765 db/journals/corr/corr2510.html#abs-2510-22765 streams/journals/corr

Tianlong Zhang Hongwei Xue Shilin Yan Di Wu Chen Xu Yunyun Yang You Only Forward Once: An Efficient Compositional Judging Paradigm. 2025 November abs/2511.16600 CoRR https://doi.org/10.48550/arXiv.2511.16600 db/journals/corr/corr2511.html#abs-2511-16600 streams/journals/corr

Shilin Yan Renrui Zhang Ziyu Guo Wenchao Chen Wei Zhang 0016 Hongyang Li 0001 Yu Qiao 0001 Hao Dong 0003 Zhongjiang He Peng Gao 0007 Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation. 6449-6457 2024 AAAI https://doi.org/10.1609/aaai.v38i6.28465 conf/aaai/2024 db/conf/aaai/aaai2024.html#YanZGCZ0Q0H024 Lingyi Hong Shilin Yan Renrui Zhang Wanyun Li Xinyu Zhou 0006 Pinxue Guo Kaixun Jiang Yiting Chen Jinglun Li Zhaoyu Chen 0001 Wenqiang Zhang OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning. 19079-19091 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.01805 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#HongYZLZGJCLCZ24 Cilin Yan Haochen Wang Shilin Yan Xiaolong Jiang Yao Hu 0002 Guoliang Kang Weidi Xie Efstratios Gavves VISA: Reasoning Video Object Segmentation via Large Language Models. 98-115 2024 ECCV (15) https://doi.org/10.1007/978-3-031-72633-0_6 conf/eccv/2024-15 db/conf/eccv/eccv2024-15.html#YanWYJHKXG24 streams/conf/eccv Shilin Yan Xiaohao Xu Renrui Zhang Lingyi Hong Wenchao Chen Wenqiang Zhang Wei Zhang 0016 PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation. 346-365 2024 ECCV (9) https://doi.org/10.1007/978-3-031-72673-6_19 conf/eccv/2024-9 db/conf/eccv/eccv2024-9.html#YanXZHCZZ24 streams/conf/eccv Renrui Zhang Zhengkai Jiang 0001 Ziyu Guo Shilin Yan Junting Pan Hao Dong 0003 Yu Qiao 0001 Peng Gao 0007 Hongsheng Li 0001 Personalize Segment Anything Model with One Shot. 2024 ICLR https://openreview.net/forum?id=6Gzkhoc6YS conf/iclr/2024 db/conf/iclr/iclr2024.html#Zhang0GYP000024 Feipeng Ma Hongwei Xue Yizhou Zhou Guangting Wang Fengyun Rao Shilin Yan Yueyi Zhang Siying Wu Mike Zheng Shou Xiaoyan Sun 0001 Visual Perception by Large Language Model's Weights. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/322e4a595afd9442a89f0bfaa441871e-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#MaXZWRYZWS024

Lingyi Hong Shilin Yan Renrui Zhang Wanyun Li Xinyu Zhou 0006 Pinxue Guo Kaixun Jiang Yiting Chen Jinglun Li Zhaoyu Chen 0001 Wenqiang Zhang OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning. 2024 abs/2403.09634 CoRR https://doi.org/10.48550/arXiv.2403.09634 db/journals/corr/corr2403.html#abs-2403-09634

Feipeng Ma Hongwei Xue Guangting Wang Yizhou Zhou Fengyun Rao Shilin Yan Yueyi Zhang Siying Wu Mike Zheng Shou Xiaoyan Sun 0001 Multi-Modal Generative Embedding Model. 2024 abs/2405.19333 CoRR https://doi.org/10.48550/arXiv.2405.19333 db/journals/corr/corr2405.html#abs-2405-19333

Feipeng Ma Hongwei Xue Guangting Wang Yizhou Zhou Fengyun Rao Shilin Yan Yueyi Zhang Siying Wu Mike Zheng Shou Xiaoyan Sun 0001 Visual Perception by Large Language Model's Weights. 2024 abs/2405.20339 CoRR https://doi.org/10.48550/arXiv.2405.20339 db/journals/corr/corr2405.html#abs-2405-20339

Shilin Yan Ouxiang Li Jiayin Cai Yanbin Hao Xiaolong Jiang Yao Hu 0002 Weidi Xie A Sanity Check for AI-generated Image Detection. 2024 abs/2406.19435 CoRR https://doi.org/10.48550/arXiv.2406.19435 db/journals/corr/corr2406.html#abs-2406-19435 streams/journals/corr

Cilin Yan Haochen Wang Shilin Yan Xiaolong Jiang Yao Hu 0002 Guoliang Kang Weidi Xie Efstratios Gavves VISA: Reasoning Video Object Segmentation via Large Language Models. 2024 abs/2407.11325 CoRR https://doi.org/10.48550/arXiv.2407.11325 db/journals/corr/corr2407.html#abs-2407-11325 streams/journals/corr

Lingyi Hong Jinglun Li Xinyu Zhou 0006 Shilin Yan Pinxue Guo Kaixun Jiang Zhaoyu Chen 0001 Shuyong Gao Wei Zhang 0016 Hong Lu 0001 Wenqiang Zhang General Compression Framework for Efficient Transformer Object Tracking. 2024 abs/2409.17564 CoRR https://doi.org/10.48550/arXiv.2409.17564 db/journals/corr/corr2409.html#abs-2409-17564 streams/journals/corr

Renrui Zhang Jiaming Han Aojun Zhou Xiangfei Hu Shilin Yan Pan Lu Hongsheng Li 0001 Peng Gao 0007 Yu Qiao 0001 LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention. 2023 abs/2303.16199 CoRR https://doi.org/10.48550/arXiv.2303.16199 db/journals/corr/corr2303.html#abs-2303-16199

Renrui Zhang Zhengkai Jiang 0001 Ziyu Guo Shilin Yan Junting Pan Hao Dong 0003 Peng Gao 0007 Hongsheng Li 0001 Personalize Segment Anything Model with One Shot. 2023 abs/2305.03048 CoRR https://doi.org/10.48550/arXiv.2305.03048 db/journals/corr/corr2305.html#abs-2305-03048

Shilin Yan Renrui Zhang Ziyu Guo Wenchao Chen Wei Zhang 0016 Hongyang Li 0001 Yu Qiao 0001 Zhongjiang He Peng Gao 0007 Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation. 2023 abs/2305.16318 CoRR https://doi.org/10.48550/arXiv.2305.16318 db/journals/corr/corr2305.html#abs-2305-16318

Shilin Yan Xiaohao Xu Lingyi Hong Wenchao Chen Wenqiang Zhang Wei Zhang 0016 PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation. 2023 abs/2309.12303 CoRR https://doi.org/10.48550/arXiv.2309.12303 db/journals/corr/corr2309.html#abs-2309-12303

Rongyao Fang Shilin Yan Zhaoyang Huang Jingqiu Zhou Hao Tian 0006 Jifeng Dai Hongsheng Li 0001 InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation. 2023 abs/2311.18835 CoRR https://doi.org/10.48550/arXiv.2311.18835 db/journals/corr/corr2311.html#abs-2311-18835

Shaobo Lin Xingyu Zeng Shilin Yan Rui Zhao Three-stage Training Pipeline with Patch Random Drop for Few-shot Object Detection. 286-302 2022 ACCV (6) https://doi.org/10.1007/978-3-031-26351-4_18 conf/accv/2022-6 db/conf/accv/accv2022-6.html#LinZYZ22 Shilin Yan Shan Chang Jiacheng Wang Shanila Azhar Using Pupil Light Reflex for Fast Biometric Authentication. 139-143 2020 ACM TUR-C https://doi.org/10.1145/3393527.3393551 conf/acmturc/2020 db/conf/acmturc/acmturc2020.html#YanCWA20

Bin Li Jian Li Shilin Yan Linfeng Ju Xu He Impacts of porous material fluid bulk properties on noise attenuation performance of cylinder shell structure based on finite element model. 2019 31 Concurr. Comput. Pract. Exp. 10 https://doi.org/10.1002/cpe.4714 db/journals/concurrency/concurrency31.html#LiLYJH19

Kun Li Shilin Yan Yucheng Zhong Wenfeng Pan Gang Zhao Multi-objective optimization of the fiber-reinforced composite injection molding process using Taguchi method, RSM, and NSGA-II. 69-82 2019 91 Simul. Model. Pract. Theory https://doi.org/10.1016/j.simpat.2018.09.003 https://www.wikidata.org/entity/Q129133255 db/journals/simpra/simpra91.html#LiYZPZ19

Danqing Wu Shilin Yan Haodi Tang Yu Wang Jiayun Feng Xianwu Hu Jiaxin Cao Yufeng Xie 0001 A digitalized RRAM-based Spiking Neuron Network system with 3-bit weight and unsupervised online learning scheme. 1-4 2019 ASICON https://doi.org/10.1109/ASICON47005.2019.8983603 conf/asicon/2019 db/conf/asicon/asicon2019.html#WuYTWFHCX19

Song Jia Ziyi Wang Shilin Yan Yuan Wang 0001 A true single-phase clock dual-modulus prescaler with enhanced robustness against leakage currents. 1895-1900 2016 44 Int. J. Circuit Theory Appl. 10 https://doi.org/10.1002/cta.2196 db/journals/ijcta/ijcta44.html#JiaWYW16

Song Jia Shilin Yan Yuan Wang 0001 Ganggang Zhang A low-power high-speed 32/33 prescaler based on novel divide-by-4/5 unit with improved true single-phase clock logic. 890-893 2015 ISCAS https://doi.org/10.1109/ISCAS.2015.7168777 conf/iscas/2015 db/conf/iscas/iscas2015.html#JiaYWZ15 Ruichuan An Shanila Azhar Xuehai Bai Jiayin Cai Jiaxin Cao Shan Chang Ruizhe Chen Wenchao Chen Xinlong Chen Xinyan Chen 0001 Xuanyan Chen Yi-Ting ChenYiting Chen Zhaoyu Chen 0001 Gaole Dai Jifeng Dai Yifan Dai Zhenxin Diao Henghui Ding Yue Ding 0009 Hao Dong 0003 Yuhao Dong Chengqi Duan Rongyao Fang Jiayun Feng Junyu Feng Kunpeng Gao Peng Gao 0007 Shuyong Gao Xiaowei Gao Zhi Gao 0002 Efstratios Gavves Pinxue Guo Ziyu Guo Jiaming Han Yanbin Hao Xu He Zhongjiang He Pheng-Ann Heng Jack Hong Lingyi Hong Xiangfei Hu Xianwu Hu Yao Hu 0002 Linjiang Huang Zhaoyang Huang Yiyan Ji Song Jia Yunde Jia Dongzhi Jiang Kaixun Jiang Xiaolong Jiang Zhengkai Jiang 0001 Linfeng Ju Guoliang Kang Bin Li Bozhou Li Hao Li 0069 Hongsheng Li 0001 Hongyang Li 0001 Jian Li Jinglun Li Kun Li Mingyue Li Ouxiang Li Pengxiang Li Qing Li 0003 Ruixuan Li 0001 Runze Li Shuo Li Wanyun Li Hao Liang 0017 Yi Liang Shaobo Lin Weifeng Lin Shiwei Liu 0003 Xihui Liu Xinyu Liu Hong Lu 0001 Ming Lu 0002 Pan Lu Shuaiqi Lu Yulin Luo Feipeng Ma Dilxat Muhtar Junting Pan Wenfeng Pan Huanqing Peng Wei Peng Zirui Peng Yu Qiao 0001 Jinye Ran Fengyun Rao Haozhan Shen Jiayi Shen Li Shen 0008 Zijun Shen Xingdong Sheng Kunyu Shi Yang Shi 0009 Zheng Shou 0001Mike Zheng Shou Cees SnoekCees G. M. Snoek Xiaoyan Sun 0001 Haodi Tang Xiaojun Tang Yuqi Tang Hao Tian 0006 Chengzhuo Tong Jintao Tong Joey Tsai Soroush Vosoughi Pengfei Wan 0001 Cheems WangQi Wang 0005 Fengxiang Wang 0004 Guangting Wang Haochen Wang Haotian Wang 0001 Jiacheng Wang Kun Wang 0056 Qixun Wang 0002 Yangyang Wang Yu Wang Yuan Wang 0001 Yuran Wang 0003 Ziyi Wang Yujie Wei Danqing Wu Di Wu Jongrong Wu Siying Wu Yuwei Wu 0001 Zehao Xiao Weidi Xie Yufeng Xie 0001 Binxiao Xu Chen Xu Xiaohao Xu Hongwei Xue Cilin Yan Chaoqun Yang Sihan Yang Xin Yang Yunyun Yang Jianwei Yin Lu Yin 0006 Bohan Zeng Xingyu Zeng Ganggang Zhang Guanghua Zhang Guannan Zhang Hao Zhang Ray Zhang 0002 Renrui Zhang Tianlong Zhang Wei Zhang 0016 Wenqiang Zhang Wentao Zhang 0001 Xiaowen Zhang Xintong Zhang Yifan Zhang 0004 Yuanxing Zhang Yueyi Zhang Zhuoran Zhang 0003 Gang Zhao Rui Zhao Rui Zhao 0001 Tiancheng Zhao Yucheng Zhong Aojun Zhou Jingqiu Zhou Xinyu Zhou 0006 Yefan Zhou Yizhou Zhou Morui Zhu Xuanyu Zhu 0001 Le Zhuo Zhuofan Zong Bocheng Zou Yixiong Zou