https://yuxuan.world/research/papers/catalog.xml Yuxuan Zhang — Research works 2026-09-14T00:00:00Z Research questions, source records, and citation context. Each entry links to its original paper or project source. https://yuxuan.world/research/papers/dilran/ An Attention-based Multi-Scale Feature Learning Network for Multimodal Medical Image Fusion 2022-12-09T00:00:00Z Zhou, Meng Xu, Xiaolan Zhang, Yuxuan Research focus: Multiscale feature learning for multimodal medical image fusion. Citation context: Use this source for its attention-based multiscale fusion method; distinguish it from the later edge-enhanced extension. Research image-fusion results do not establish clinical benefit. https://yuxuan.world/research/papers/plaicraft/ PLAICraft: Large-Scale Time-Aligned Vision-Speech-Action Dataset for Embodied AI 2025-05-19T00:00:00Z He, Yingchen Weilbach, Christian D. Wojciechowska, Martyna E. Zhang, Yuxuan Wood, Frank Research focus: Time-aligned vision, speech and action data for embodied AI. Citation context: Cite this dataset when using or comparing time-aligned multimodal embodied-agent data. Consult the source for collection protocol, synchronization and permitted use. https://yuxuan.world/research/papers/deep-research-bench/ Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports 2025-10-02T00:00:00Z Yao, Yang Wang, Yixu Zhang, Yuxuan Lu, Yi Gu, Tianle Li, Lingyu Zhao, Dingyi Wu, Keming Wang, Haozhe Nie, Ping Teng, Yan Wang, Yingchun Research focus: Evaluating deep-research agents from answers to reports. Citation context: Use this benchmark when discussing evaluation of deep-research reports and their semantic quality, topical focus and retrieval trustworthiness. https://yuxuan.world/research/papers/wikigap/ WikiGap: Promoting Epistemic Equity by Surfacing Knowledge Gaps Between English Wikipedia and other Language Editions 2025-05-30T00:00:00Z Wang, Zining Zhang, Yuxuan Yoon, Dongwook Vincent, Nicholas Samir, Farhan Shwartz, Vered Research focus: Finding knowledge gaps across Wikipedia language editions. Citation context: Cite this work for the problem and approach of surfacing knowledge gaps between English Wikipedia and other language editions, with its defined scope of epistemic equity. https://yuxuan.world/research/papers/structeval/ StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs 2025-05-26T00:00:00Z Yang, Jialin Jiang, Dongfu He, Lipeng Siu, Sherman Zhang, Yuxuan Liao, Disen Li, Zhuofeng Zeng, Huaye Jia, Yiming Wang, Haozhe Schneider, Benjamin Ruan, Chi Ma, Wentao Lyu, Zhiheng Wang, Yifei Lu, Yi Do, Quy Duc Jiang, Ziyan Nie, Ping Chen, Wenhu Research focus: Evaluating structured output generation and format conversion. Citation context: Use this benchmark when evaluating structural output generation or conversion across textual and visually rendered formats. Syntax validity alone does not establish content correctness. https://yuxuan.world/research/papers/retri3d/ Retri3D: 3D Neural Graphics Representation Retrieval 2025-05-21T00:00:00Z Yushi Guan Daniel Kwan Jean Sebastien Dandurand Xi Yan Ruofan Liang Yuxuan Zhang Nilesh Jain Nilesh Ahuja Selvakumar Panneer Nandita Vijaykumar Research focus: Retrieving neural graphics representations of 3D scenes. Citation context: Cite this work when discussing retrieval from neural 3D scene representations and the role of views and representation analysis. https://yuxuan.world/research/papers/scholarcopilot/ ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations 2025-04-01T00:00:00Z Wang, Yubo Ma, Xueguang Nie, Ping Zeng, Huaye Lyu, Zhiheng Zhang, Yuxuan Schneider, Benjamin Lu, Yi Yue, Xiang Chen, Wenhu Research focus: Academic writing with learned citation retrieval. Citation context: Cite this work when discussing joint academic text generation and citation retrieval, or when using its released writing model and retrieval setup. https://yuxuan.world/research/papers/videoscore2/ VideoScore2: Think before You Score in Generative Video Evaluation 2025-09-26T00:00:00Z He, Xuan Jiang, Dongfu Nie, Ping Liu, Minghao Jiang, Zhengxuan Su, Mingyi Ma, Wentao Lin, Junru Ye, Chun Lu, Yi Wu, Keming Schneider, Benjamin Do, Quy Duc Li, Zhuofeng Jia, Yiming Zhang, Yuxuan Cheng, Guo Wang, Haozhe Zhou, Wangchunshu Lin, Qunshu Zhang, Yuanxing Zhang, Ge Huang, Wenhao Chen, Wenhu Research focus: Reasoning-based evaluation of generated videos. Citation context: Use this work when comparing evaluation of generated-video quality and reasoning-based scoring. Compare dimensions and protocols rather than combining scores from different benchmarks. https://yuxuan.world/research/papers/vq/ Enhancing Vector Quantization with Distributional Matching: A Theoretical and Empirical Study 2025-06-18T00:00:00Z Fang, Xianghong Guo, Litao Chen, Hengchao Zhang, Yuxuan XiaofanXia Song, Dingjie Liu, Yexin Wang, Hao Yang, Harry Yuan, Yuan Sun, Qiang Research focus: Distributional matching for vector quantization. Citation context: Use this 2025 record for its theoretical and empirical treatment of distributional matching in vector quantization. The related 2026 record has a separate identifier and overlapping material. https://yuxuan.world/research/papers/dran/ Edge-Enhanced Dilated Residual Attention Network for Multimodal Medical Image Fusion 2024-11-18T00:00:00Z Zhou, Meng Zhang, Yuxuan Xu, Xiaolan Wang, Jiayi Khalvati, Farzad Research focus: Edge-enhanced multimodal medical image fusion. Citation context: Use this source for the edge-enhanced dilated residual attention fusion extension. Keep the original medical-fusion paper and this extension separately identified. https://yuxuan.world/research/papers/s3gym/ S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? 2026-08-31T00:00:00Z Shi, Jiajun Tao, Siyuan Wu, Yuhao Wang, Zexuan Zhang, Jingyuan Liu, Jiaheng Lei, Xinping Zhang, Xinrong Fang, Siyuan Tan, Zhewen Cai, Tianle Fang, Junhao Huang, Jiameng Wang, Yueyang Liu, Jinkai Zhang, Yuxuan Yang, Jian Li, Zhoujun Yan, Shen Huang, Wenhao Zhang, Ge Research focus: Testing self-improvement through self-testing and self-judging. Citation context: Cite this benchmark when examining whether an agent's self-testing and self-judging lead to measurable improvement through interaction. https://yuxuan.world/research/papers/rewardharness/ RewardHarness: Learning Human Preferences for Image Editing with Only 100 Demonstrations 2026-05-09T00:00:00Z Zhang, Yuxuan Du, Penghui Li, Bo Wei, Cong Miao, Junwen Zhang, Huaisong Cai, Songcheng Wang, Yubo Jiang, Dongfu Zhang, Yuyu Nie, Ping Chen, Wenhu Yu, Changqian Allen, Kelsey R. Research focus: Learning rewards for instruction-guided image editing. Citation context: Cite the appropriate version when discussing learning human preferences for image editing. The homepage publication title and the saved preprint BibTeX may differ; both are exposed explicitly. https://yuxuan.world/research/papers/aspire/ Aspire: Can Models Self-Evolve from Vague Goals? 2026-08-31T00:00:00Z Wu, Yuhao Zhang, Jingyuan Shi, Jiajun Zhang, Yuxuan Lei, Xinping Zhou, Junting Wang, Zexuan Wu, Yuchen Zhou, Huan Wang, Duo Piao, Yinzhu Peng, Yongchang Shi, Yunfeng Chen, Jin Wang, Zuo Liu, Jinkai Liu, Jiaheng Zhang, Wenxuan Yan, Shen Huang, Wenhao Zhang, Ge Research focus: Agent self-evolution from vague goals. Citation context: Use this work when discussing how agents interpret vague goals and construct a learning process, rather than assuming a fully specified objective. https://yuxuan.world/research/papers/comprank/ CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring 2026-06-10T00:00:00Z Lu, Xuan Huang, Haohang Fan, Yingqi Tong, Junlong Zhang, Yuxuan Nie, Ping Meng, Rui Shen, Xiaoyu Research focus: Efficient language-model reranking. Citation context: Cite this method when discussing token-level compression and decoding-free scoring for LLM reranking. Check the reported retrieval tasks and cost measurements in the source. https://yuxuan.world/research/papers/structured-defect-grounding/ Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback 2026-06-04T00:00:00Z Zhang, Huaisong Yu, Hao Zhang, Yuxuan Wang, Jiahe Chen, Xinrui Cao, Haoxiang Lu, Feng Zhang, Wendong Yu, Changqian Yuan, Chun Research focus: Localized defect feedback for text-to-image generation. Citation context: Use this work for structured feedback about where a defect is, what it is, why it matters and its importance; consult the source for the grounding and feedback protocol. https://yuxuan.world/research/papers/harnessdev/ HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? 2026-09-01T00:00:00Z Wu, Yuhao Zhang, Jingyuan Shi, Jiajun Lei, Xinping Gu, Qingshui Zhang, Yuxuan Wang, Zexuan He, Chen Huang, Chen Song, Maojia Zeng, Zhiyuan Wang, Shaowen Liu, Jinkai Shi, Yunfeng Liu, Jiaheng Yan, Shen Huang, Wenhao Zhang, Ge Zhang, Wenxuan Research focus: Creating and evolving model-external agent harnesses. Citation context: Cite this benchmark when evaluating creation or evolution of agent execution infrastructure, keeping harness changes distinct from model-weight updates. https://yuxuan.world/research/papers/mira/ MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection 2026-05-28T00:00:00Z Wang, Haowen Du, Yaxin Yang, Jian Wu, Jiajun Liu, Shukai Zhang, Yuxuan Wang, Pingjie Chen, Siheng Zheng, Tuney Zhou, Ming Liu, Xianglong Dai, Bryan Research focus: Source-aware data selection for mid-training. Citation context: Use this work when discussing rubric anchoring and source-aware selection of mid-training data; refer to the paper for the precise selection procedure. https://yuxuan.world/research/papers/webworld/ WebWorld: The Browser as a World Model for Self-Improving Web Code 2026-08-31T00:00:00Z Wu, Jiajun Yang, Jian Du, Yaxin Zhang, Wei Wang, Haowen Cheng, Junhang Zhang, Yuxuan Zheng, Tuney Liu, Xianglong Zhou, Ming Research focus: Browser-grounded evaluation for self-improving web code. Citation context: Use this work when discussing browser execution and external feedback in web-code improvement, including the limitations of judging changes by visual plausibility. https://yuxuan.world/research/papers/openskill/ OpenSkill: Open-World Self-Evolution for LLM Agents 2026-06-04T00:00:00Z Yan, Zhiling Song, Dingjie Zhang, Hanrong Liang, Wei Zhang, Yuxuan Dai, Yutong He, Lifang Yu, Philip S. Xu, Ran Li, Xiang Sun, Lichao Research focus: Open-world self-evolution for language-model agents. Citation context: Cite this work when studying agent adaptation without assuming a curated learning loop or ready-made successful trajectories. https://yuxuan.world/research/papers/vid-filter/ Watch Before You Answer: Learning from Visually Grounded Post-Training 2026-04-06T00:00:00Z Zhang, Yuxuan Hwang, EunJeong Zhang, Huaisong Du, Penghui Jia, Yiming Jiang, Dongfu He, Xuan Zhang, Shenhui Nie, Ping West, Peter Allen, Kelsey R. Research focus: Video post-training that depends on visual evidence. Citation context: Cite this study when discussing linguistic shortcuts in video question answering or selecting post-training data for visual dependence. Check the paper's experimental scope before generalizing. https://yuxuan.world/research/papers/fim-midtraining/ Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models 2026-07-14T00:00:00Z Wang, Yubo Liang, Jiarong Zhang, Yuxuan Liu, Xuye Wei, Cong Zhang, Yuyu Nie, Ping Chen, Wenhu Research focus: Function-aware fill-in-the-middle training for coding agents. Citation context: Use this method when discussing mid-training for integrating external tool returns into coding-agent reasoning, and consult the released data and model descriptions. https://yuxuan.world/research/papers/medclaw/ MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning 2026-08-14T00:00:00Z Fan, Yingying Du, Penghui Zhu, Leyan He, Runze Wu, Zimeng Zhang, Yuxuan Chen, Liang Xie, Jiahao Wang, Jiangtang Shao, Shuai Yang, Anchao Bai, Yutong Wang, Yan Research focus: Long-horizon reasoning over surgical videos. Citation context: Cite this research method for long-horizon video reasoning, planning and evidence retrieval. It is not evidence of clinical deployment or patient benefit; public resource availability must be checked separately. https://yuxuan.world/research/papers/modularrsi/ ModularRSI: Toward Generalizable Harness RSI 2026-08-30T00:00:00Z Siwei Wu Jincheng Ren Yizhi Li Haau-Sing Li Chengran Yang Weicheng Gu Yuxuan Zhang Jian Yang Riza Batista-Navarro Chuanyi Zhang Xianglong Liu Ming Zhou Bryan Dai Chenghua Lin Research focus: Generalizable harness self-improvement. Citation context: Reference the public project article or code for the disclosed work. No public manuscript is linked in this catalog, so this page does not present it as a published paper. https://yuxuan.world/research/papers/self-future-dllm/ Learning from the Self-future: On-policy Self-distillation for dLLMs 2026-06-16T00:00:00Z Luo, Yifu Chen, Zeyu Wang, Haoyu Hu, Xinhao Zhang, Yuxuan Sha, Zhizhou Liu, Shiwei Research focus: On-policy self-distillation for diffusion language models. Citation context: Use this work when discussing application of on-policy self-distillation to diffusion language models and its proposed self-future learning approach. https://yuxuan.world/research/papers/distributional-matching-vq/ Distributional Matching for Vector Quantization: A Unified Theoretical and Empirical Framework 2026-07-17T00:00:00Z Fang, Xianghong Guo, Litao Chen, Hengchao Zhang, Yuxuan XiaofanXia Song, Dingjie Liu, Yexin Wang, Hao Yang, Harry Sun, Qiang Yuan, Yuan Research focus: A unified treatment of distributional matching in vector quantization. Citation context: Use this 2026 record for the unified framework described in its current version. The related 2025 paper must not be counted as independent evidence without checking overlap. https://yuxuan.world/research/papers/vgi-bench/ VGI-BENCH: Probing Visual Intelligence in Video Generation Models 2026-08-20T00:00:00Z He, Xuan Wei, Cong Cheng, Yuhao Ma, Linrui Zhang, Yuxuan Li, Zuojun Wen, Yuhao Jiang, Jize Liu, Zeyi Hao, Yuren Cai, Songcheng Wu, Keming Du, Penghui Zou, Kai Yang, Rui Sun, Chenkai Yang, Ke Nie, Ping Allen, Kelsey R Wang, Chenglong Galley, Michel Gao, Jianfeng Zhai, ChengXiang Research focus: Evaluating visual intelligence in video generation models. Citation context: Cite this benchmark when investigating visual reasoning through video generation; distinguish its task-based evaluation from generic video appearance or quality scoring. https://yuxuan.world/research/papers/dr-claw/ Dr. Claw: An AI Scientist Workspace for Vibe Research 2026-08-31T00:00:00Z Song, Dingjie Zhang, Hanrong Liu, Dawei Liu, Yixin Li, Zongxia Yuan, Zhengqing Zhang, Siqi Zou, Henry Peng Yan, Zhiling Zhang, Yuxuan Ye, Yanfang Yu, Philip S. Sun, Lichao Research focus: An AI scientist workspace for research workflows. Citation context: Reference this system when discussing integrated research workspaces for coding agents. System availability and workflow capabilities should be checked against the current release. https://yuxuan.world/research/papers/clawbench/ ClawBench: Can AI Agents Complete Everyday Online Tasks? 2026-04-09T00:00:00Z Zhang, Yuxuan Wang, Yubo Zhu, Yipeng Du, Penghui Miao, Junwen Lu, Xuan Li, Zhuofeng Qu, Xingwei Guo, Zhengkang Shen, Yuanzhe Song, Dingjie Zhou, Han Zheng, Tuney Wu, Xian Yu, Hao Cai, Songcheng Lu, Yi Hao, Yunzhuo Lei, Minyi Chen, Liang Zou, Kai Yin, Huifeng Xu, Wendong Jiang, Dongfu Nie, Ping Liu, Jiaheng Chen, Wenhu Allen, Kelsey R. Research focus: Evaluating browser agents on everyday online workflows. Citation context: Use this benchmark when evaluating agents completing everyday online tasks on websites. Report the task setup and scoring protocol rather than equating a benchmark score with general autonomy. https://yuxuan.world/research/papers/celebhair/ CelebHair: A New Large-Scale Dataset for Hairstyle Recommendation Based on CelebA 2021-04-14T00:00:00Z Chen, Yutao Zhang, Yuxuan Huang, Zhongrui Luo, Zhenyao Chen, Jinpeng Research focus: A dataset for hairstyle recommendation based on CelebA. Citation context: Cite this dataset when using its hairstyle-recommendation annotations or task formulation. Consult the original work and dataset terms before reuse.