data.js

const opensource_projects_data = [
    {
        "title": "OpenStoryline: An Agentic Framework for Autonomous, Human-Aligned Video Creation",
        "image": "pics/projects_publications/openstoryline.jpg",
        "authors": "Qiwei Yang, Jincheng Liao, Sijie Xu, Xin Zhou, Liyao Rong, Boxiang Zhou, Fengyuan Zhang, Yibo Chen, Dejia Song, Xu Tang, Yao Hu",
        "arxiv_link": null,
        "code_link": "https://github.com/FireRedTeam/FireRed-OpenStoryline",
        "demo_link": "https://fireredteam.github.io/demos/firered_openstoryline"
    },
    {
        "title": "FireRedChat: A Fully Self-Hosted Solution for Full-Duplex Voice Interaction",
        "image": "pics/projects_publications/fireredchat.jpg",
        "authors": "Junjie Chen, Yao Hu, Junjie Li, Kangyue Li, Kun Liu, Wenpeng Li, Xu Li, Ziyuan Li, Feiyu Shen, Xu Tang, Manzhen Wei, Yichen Wu, Fenglong Xie, Kaituo Xu, Kun Xie",
        "arxiv_link": "https://arxiv.org/abs/2509.06502",
        "code_link": "https://github.com/FireRedTeam/FireRedChat",
        "demo_link": "https://fireredteam.github.io/demos/firered_chat"
    },
    {
        "title": "IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning",
        "image": "pics/projects_publications/ivc_prune.jpg",
        "authors": "Zhichao Sun, Yidong Ma, Gang Liu, Yibo Chen, Xu Tang, Yao Hu, Yongchao Xu",
        "arxiv_link": "https://arxiv.org/abs/2602.03060",
        "code_link": "https://github.com/FireRedTeam/IVC-Prune",
        "demo_link": null
    },
    {
        "title": "FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot",
        "image": "pics/projects_publications/fireredtts2.jpg",
        "authors": "Kun Xie, Feiyu Shen, Junjie Li, Fenglong Xie, Xu Tang, Yao Hu",
        "arxiv_link": "https://arxiv.org/abs/2509.02020",
        "code_link": "https://github.com/FireRedTeam/FireRedTTS2",
        "demo_link": "https://fireredteam.github.io/demos/firered_tts_2"
    },
    {
        "title": "InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention",
        "image": "pics/projects_publications/instance_assemble.jpeg",
        "authors": "Qiang Xiang, Shuang Sun, Binglei Li, Dejia Song, Huaxia Li, Nemo Chen, Xu Tang, Yao Hu, Junping Zhang",
        "arxiv_link": "https://arxiv.org/abs/2509.16691",
        "code_link": "https://github.com/FireRedTeam/InstanceAssemble",
        "demo_link": null
    },
    {
        "title": "InstantID: Zero-shot Identity-Preserving Generation in Seconds",
        "image": "pics/projects_publications/instantid.jpg",
        "authors": "Qixun Wang, Xu Bai, Haofan Wang, Zekui Qin, Anthony Chen, Huaxia Li, Xu Tang, Yao Hu",
        "arxiv_link": "https://arxiv.org/abs/2401.07519",
        "code_link": "https://github.com/instantX-research/InstantID",
        "demo_link": null
    },
    {
        "title": "DynamicPose: A Robust Image-to-Video Framework for Portrait Animation Driven by Pose Sequences",
        "image": "pics/projects_publications/dynamicpose.jpg",
        "authors": "Yanqin Chen, Changhao Qiao, Sijie Xu, Yang Chen, Wei Zhu, Dejia Song",
        "arxiv_link": null,
        "code_link": "https://github.com/FireRedTeam/DynamicPose",
        "demo_link": null
    },
    {
        "title": "PhotoPoster: A High-Fidelity Two-Stage Pose-Driven Image Generation Framework",
        "image": "pics/projects_publications/photo_poster.jpg",
        "authors": "Yanqin Chen, Changhao Qiao, Sijie Xu, Yang Chen, Wei Zhu, Dejia Song",
        "arxiv_link": null,
        "code_link": "https://github.com/FireRedTeam/PhotoPoster",
        "demo_link": "https://photo-poster.github.io"
    },
    {
        "title": "CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection",
        "image": "pics/projects_publications/cq_dino.jpg",
        "authors": "Zhichao Sun, Huazhang Hu, Yidong Ma, Gang Liu, Yibo Chen, Xu Tang, Yao Hu, Yongchao Xu",
        "arxiv_link": "https://arxiv.org/abs/2503.18430",
        "code_link": "https://github.com/FireRedTeam/CQ-DINO",
        "demo_link": null
    },
    {
        "title": "FireRedASR: Open-Source Industrial-Grade Automatic Speech Recognition Models",
        "image": "pics/projects_publications/fireredasr.jpg",
        "authors": "Kaituo Xu, Fenglong Xie, Xu Tang, Yao Hu",
        "arxiv_link": "https://arxiv.org/pdf/2501.14350",
        "code_link": "https://github.com/FireRedTeam/FireRedASR",
        "demo_link": "https://fireredteam.github.io/demos/firered_asr",
    },
    {
        "title": "FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech System",
        "image": "pics/projects_publications/fireredtts-1s.jpg",
        "authors": "Haohan Guo, Yao Hu, Kun Liu, Feiyu Shen, Xu Tang, Yichen Wu, Fenglong Xie, Kun Xie, Kaituo Xu",
        "arxiv_link": "https://arxiv.org/abs/2503.20499",
        "code_link": "https://github.com/FireRedTeam/FireRedTTS",
        "demo_link": "https://fireredteam.github.io/demos/firered_tts_1s",
    },
    {
        "title": "The Xiaohongshu Speech Synthesis System for Blizzard Challenge 2023",
        "image": "pics/projects_publications/fireredtts_2023.jpg",
        "authors": "Kun Xie, Yichen Wu, Fenglong Xie",
        "arxiv_link": "https://www.isca-archive.org/blizzard_2023/xie23_blizzard.pdf",
        "code_link": null,
        "demo_link": null,
    },
    {
        "title": "StoryMaker: Towards Consistent Characters in Text-to-Image Generation",
        "image": "pics/projects_publications/story_maker.jpg",
        "authors": "Zhengguang Zhou, Jing Li, Huaxia Li, Nemo Chen, Xu Tang",
        "arxiv_link": "https://arxiv.org/abs/2409.12576",
        "code_link": "https://github.com/FireRedTeam/StoryMaker",
        "demo_link": null,
    },
    {
        "title": "LayerDiffuse-Flux",
        "image": "pics/projects_publications/layerdiffuse_flux.jpg",
        "authors": "Qiang Xiang, Shuang Sun",
        "arxiv_link": null,
        "code_link": "https://github.com/FireRedTeam/LayerDiffuse-Flux",
        "demo_link": null,
    },
    {
        "title": "InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation",
        "image": "pics/projects_publications/instant_style.jpg",
        "authors": "Haofan Wang, Matteo Spinelli, Qixun Wang, Xu Bai, Zekui Qin, Anthony Chen",
        "arxiv_link": "https://arxiv.org/abs/2404.02733",
        "code_link": "https://github.com/instantX-research/InstantStyle",
        "demo_link": "https://instantstyle.github.io",
    }
];


const publications_data = [
    {
        "title": "HyMiRec: A Hybrid Multi-interest Learning Framework for LLM-based Sequential Recommendation",
        "image": "pics/projects_publications/hymirec.jpg",
        "authors": "Jingyi Zhou, Cheng Chen, Kai Zuo, Manjie Xu, Zhendong Fu, Yibo Chen, Xu Tang, Yao Hu",
        "conference_name": "(WWW) The ACM Web Conference",
        "arxiv_link": "https://arxiv.org/pdf/2510.13738",
        "code_link": null,
        "demo_link": null
    },
    {
        "title": "IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning",
        "image": "pics/projects_publications/ivc_prune.jpg",
        "authors": "Zhichao Sun, Yidong Ma, Gang Liu, Yibo Chen, Xu Tang, Yao Hu, Yongchao Xu",
        "conference_name": "(ICLR) The International Conference on Learning Representations",
        "arxiv_link": "https://arxiv.org/abs/2602.03060",
        "code_link": "https://github.com/FireRedTeam/IVC-Prune",
        "demo_link": null
    },
    {
        "title": "DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors",
        "image": "pics/projects_publications/dynamic_face.jpg",
        "authors": "Runqi Wang,Yang Chen,Sijie Xu,Tianyao He,Wei Zhu,Dejia Song,Nemo Chen,Xu Tang,Yao Hu",
        "conference_name": "(ICCV) IEEE InternationalConference on Computer Vision",
        "arxiv_link": "https://arxiv.org/abs/2501.08553",
        "code_link": null,
        "demo_link": "https://dynamic-face.github.io"
    },
    {
        "title": "InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention",
        "image": "pics/projects_publications/instance_assemble.jpeg",
        "authors": "Qiang Xiang, Shuang Sun, Binglei Li, Dejia Song, Huaxia Li, Nemo Chen, Xu Tang, Yao Hu, Junping Zhang",
        "conference_name": "(NIPS) Conference and Workshop on Neural Information Processing Systems",
        "arxiv_link": "https://arxiv.org/abs/2509.16691",
        "code_link": "https://github.com/FireRedTeam/InstanceAssemble",
        "demo_link": null
    },
        {
        "title": "CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection",
        "image": "pics/projects_publications/cq_dino.jpg",
        "authors": "Zhichao Sun, Huazhang Hu, Yidong Ma, Gang Liu, Nemo Chen, Xu Tang, Yao Hu, Yongchao Xu ",
        "conference_name": "(NIPS) Conference and Workshop on Neural Information Processing Systems",
        "arxiv_link": "https://arxiv.org/abs/2503.18430",
        "code_link": "https://github.com/FireRedTeam/CQ-DINO",
        "demo_link": null
    },
    {
        "title": "Single Trajectory Distillation for Accelerating Image and Video Style Transfer",
        "image": "pics/projects_publications/single_trajectory.jpg",
        "authors": "Sijie Xu, Runqi Wang, Wei Zhu, Dejia Song, Nemo Chen, Xu Tang, Yao Hu",
        "conference_name": "(ACM MM) ACM International Conference on Multimedia",
        "arxiv_link": "https://arxiv.org/abs/2412.18945",
        "code_link": "https://github.com/FireRedTeam/Single-Trajectory-Distillation",
        "demo_link": "https://single-trajectory-distillation.github.io/"
    },
    {
        "title": "Speaking from Coarse to Fine: Improving Neural Codec Language Model via Multi-Scale Speech Coding and Generation",
        "image": "pics/projects_publications/cofi_speech.jpg",
        "authors": "Haohan  Guo, Fenglong Xie, Dongchao Yang, Xixin Wu, Helen Meng",
        "conference_name": "(ICASSP) IEEE International Conference on Acoustics, Speech and Signal Processing",
        "arxiv_link": "https://arxiv.org/abs/2409.11630",
        "code_link": null,
        "demo_link": "https://hhguo.github.io/DemoCoFiSpeech"
    },
    {
        "title": "GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer",
        "image": "pics/projects_publications/geoformer.jpg",
        "authors": "Jinpeng Yu, Binbin Huang, Yuxuan Zhang, Huaxia Li, Xu Tang, Shenghua Gao",
        "conference_name": "(ACM MM) ACM International Conference on Multimedia",
        "arxiv_link": "https://arxiv.org/abs/2408.06596",
        "code_link": "https://github.com/Jinpeng-Yu/GeoFormer",
        "demo_link": null
    },
    {
        "title": "Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance",
        "image": "pics/projects_publications/target_driven_distillation.jpg",
        "authors": "Cunzheng Wang, Ziyuan Guo, Yuxuan Duan, Huaxia Li, Nemo Chen, Xu Tang, Yao Hu",
        "conference_name": "(AAAI) Association for the Advancement of Artificial Intelligence",
        "arxiv_link": "https://arxiv.org/abs/2409.01347",
        "code_link": "https://github.com/FireRedTeam/Target-Driven-Distillation",
        "demo_link": "https://redaigc.github.io/TDD"
    },
    {
        "title": "Pseudo-plane Regularized Signed Distance Field for Neural Indoor Scene Reconstruction",
        "image": "pics/projects_publications/pseudo_plane_regularized.jpg",
        "authors": "Jing Li, Jinpeng Yu, Ruoyu Wang, Shenghua Gao",
        "conference_name": "(IJCV) International Journal of Computer Vision",
        "arxiv_link": "https://www.researchgate.net/publication/387574915_Pseudo-Plane_Regularized_Signed_Distance_Field_for_Neural_Indoor_Scene_Reconstruction",
        "code_link": null,
        "demo_link": null
    },
    {
        "title": "StoryMaker: Towards Consistent Characters in Text-to-Image Generation",
        "image": "pics/projects_publications/story_maker.jpg",
        "authors": "Zhengguang Zhou, Jing Li, Huaxia Li, Nemo Chen, Xu Tang",
        "conference_name": "Arxiv",
        "arxiv_link": "https://arxiv.org/abs/2409.12576",
        "code_link": "https://github.com/FireRedTeam/StoryMaker",
        "demo_link": ""
    },
    {
        "title": "Socodec: A Semantic-Ordered Multi-Stream Speech Codec for Efficient Language Model Based Text-to-Speech Synthesis",
        "image": "pics/projects_publications/socodec.jpg",
        "authors": "Haohan Guo, Fenglong Xie, Kun Xie, Dongchao Yang, Dake Guo, Xixin Wu, Helen Meng",
        "conference_name": "(SLT) IEEE Spoken Language Technology Workshop",
        "arxiv_link": "https://arxiv.org/abs/2409.00933",
        "code_link": "https://github.com/hhguo/SoCodec",
        "demo_link": "https://hhguo.github.io/DemoSoCodec/"
    },
    {
        "title": "Addressing Index Collapse of Large-Codebook Speech Tokenizer with Dual-Decoding Product-Quantized Variational Auto-Encoder",
        "image": "pics/projects_publications/addressing_index.jpg",
        "authors": "Haohan Guo, Fenglong Xie, Dongchao Yang, Hui Lu, Xixin Wu, Helen Meng",
        "conference_name": "(SLT) IEEE Spoken Language Technology Workshop",
        "arxiv_link": "https://arxiv.org/abs/2406.02940",
        "code_link": null,
        "demo_link": null
    },
    {
        "title": "Controllable Mind Visual Diffusion Model",
        "image": "pics/projects_publications/controllable_mind.jpg",
        "authors": "Bohan Zeng, Shanglin Li, Xuhui Liu, Sicheng Gao, Xiaolong Jiang, Xu Tang, Yao Hu, Jianzhuang Liu, Baochang Zhang",
        "conference_name": "(AAAI) Association for the Advancement of Artificial Intelligence",
        "arxiv_link": "https://arxiv.org/abs/2305.10135",
        "code_link": "https://github.com/zengbohan0217/CMVDM",
        "demo_link": null
    },
    {
        "title": "OV-VIS: Open-Vocabulary Video Instance Segmentation",
        "image": "pics/projects_publications/ov_vis.jpg",
        "authors": "Haochen Wang, Cilin Yan, Keyan Chen, Xiaolong Jiang, Xu Tang, Yao Hu, Guoliang Kang, Weidi Xie, Efstratios Gavves",
        "conference_name": "(IJCV) International Journal of Computer Vision",
        "arxiv_link": "https://arxiv.org/abs/2305.16835",
        "code_link": null,
        "demo_link": null
    },
    {
        "title": "OV-DAR: Open-vocabulary Object Detection and Attributes Recognition",
        "image": "pics/projects_publications/ov_dar.png",
        "authors": "Keyan Chen, Xiaolong Jiang, Haochen Wang, Cilin Yan, Yan Gao, Xu Tang, Yao Hu, Weidi Xie",
        "conference_name": "(IJCV) International Journal of Computer Vision",
        "arxiv_link": "https://link.springer.com/article/10.1007/s11263-024-02144-1",
        "code_link": null,
        "demo_link": null
    },
    {
        "title": "SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation",
        "image": "pics/projects_publications/ssr_encoder.jpg",
        "authors": "Yuxuan Zhang, Jiaming Liu, Yiren Song, Rui Wang, Hao Tang, Jinpeng Yu, Huaxia Li, Xu Tang, Yao Hu, Han Pan, Zhongliang Jing",
        "conference_name": "(CVPR) IEEE Conference on Computer Vision and Pattern Recognition",
        "arxiv_link": "https://arxiv.org/abs/2312.16272",
        "code_link": "https://github.com/Xiaojiu-z/SSR_Encoder",
        "demo_link": "https://ssr-encoder.github.io"
    },
    {
        "title": "ZONE: Zero-Shot Instruction-Guided Local Editing",
        "image": "pics/projects_publications/zone.jpg",
        "authors": "Shanglin Li, Bohan Zeng, Yutang Feng, Sicheng Gao, Xuhui Liu, Jiaming Liu, Li Lin, Xu Tang, Yao Hu, Jianzhuang Liu, Baochang Zhang",
        "conference_name": "(CVPR) IEEE Conference on Computer Vision and Pattern Recognition",
        "arxiv_link": "https://arxiv.org/abs/2312.16794",
        "code_link": "https://github.com/lsl001006/ZONE",
        "demo_link": null
    },
    {
        "title": "Multimodal Sense-Informed Prediction of 3D Human Poses",
        "image": "pics/projects_publications/multimodal_sense.jpg",
        "authors": "Zhenyu Lou, Qiongjie Cui, Haofan Wang, Xu Tang, Hong Zhou",
        "conference_name": "(CVPR) IEEE Conference on Computer Vision and Pattern Recognition",
        "arxiv_link": "https://arxiv.org/abs/2405.02911",
        "code_link": "https://github.com/kjle6/SIF3D-master",
        "demo_link": "https://sites.google.com/view/cvpr2024sif3d"
    },
    {
        "title": "Expressive Forecasting of 3D Whole-body Human Motions",
        "image": "pics/projects_publications/expressive_forecasting.jpg",
        "authors": "Pengxiang Ding, Qiongjie Cui, Haofan Wang, Min Zhang Mengyuan Liu and Donglin Wang",
        "conference_name": "(AAAI) Association for the Advancement of Artificial Intelligence",
        "arxiv_link": "https://arxiv.org/abs/2312.11972",
        "code_link": "https://github.com/Dingpx/EAI",
        "demo_link": null
    },
    {
        "title": "RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation",
        "image": "pics/projects_publications/roomdesigner.jpg",
        "authors": "Yiqun Zhao, Zibo Zhao, Jing Li, Sixun Dong, Shenghua Gao",
        "conference_name": "(3DV) Proceedings of the International Conference on 3D Vision",
        "arxiv_link": "https://arxiv.org/abs/2310.10027",
        "code_link": "https://github.com/zhao-yiqun/RoomDesigner",
        "demo_link": null
    },
    {
        "title": "Synthesizing Physically Plausible Human Motions in 3D Scenes",
        "image": "pics/projects_publications/synthesizing_physically.jpg",
        "authors": "Liang Pan, Jingbo Wang, Buzhen Huang, Junyu Zhang, Haofan Wang, Xu Tang, Yangang Wang",
        "conference_name": "(3DV) Proceedings of the International Conference on 3D Vision",
        "arxiv_link": "https://arxiv.org/abs/2308.09036",
        "code_link": "https://github.com/liangpan99/InterScene",
        "demo_link": "https://liangpan99.github.io/InterScene"
    },
    {
        "title": "TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding",
        "image": "pics/projects_publications/tsp_transformer.jpg",
        "authors": "Shuo Wang, Jing Li, Zibo Zhao, Dongze Lian, Binbin Huang, Xiaomei Wang, Zhengxin Li, Shenghua Gao",
        "conference_name": "(WACV) Winter Conference on Applications of Computer Vision",
        "arxiv_link": "https://arxiv.org/abs/2311.03427",
        "code_link": "https://github.com/tb2-sy/TSP-Transformer",
        "demo_link": null
    },
    {
        "title": "QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning",
        "image": "pics/projects_publications/qstts.jpg",
        "authors": "Haohan Guo, Fenglong Xie, Jiawen Kang, Yujia Xiao, Xixin Wu, Helen Meng",
        "conference_name": "(TASLP) IEEE Transactions on Audio, Speech and Language Processing",
        "arxiv_link": "https://arxiv.org/abs/2309.00126",
        "code_link": null,
        "demo_link": "https://hhguo.github.io/DemoQSTTS"
    },
    {
        "title": "Tri-Stage Training with Language-Specific Encoder and Bilingual Acoustic Learner for Code-Switching Speech Recognition",
        "image": "pics/projects_publications/tristage_training.jpg",
        "authors": "Xuefei Wang, Yuan Jin, Fenglong Xie, Yanhua Long",
        "conference_name": "Applied Acoustics",
        "arxiv_link": "https://www.researchgate.net/publication/378643627_Tri-stage_training_with_language-specific_encoder_and_bilingual_acoustic_learner_for_code-switching_speech_recognition",
        "code_link": null,
        "demo_link": null
    },
    {
        "title": "Towards Open-Vocabulary Video Instance Segmentation",
        "image": "pics/projects_publications/towards_open_vocabulary.jpg",
        "authors": "Haochen Wang, Cilin Yan, Shuai Wang, Xiaolong Jiang, Xu Tang, Yao Hu, Weidi Xie, Efstratios Gavves",
        "conference_name": "(ICCV) IEEE InternationalConference on Computer Vision",
        "arxiv_link": "https://arxiv.org/abs/2304.01715",
        "code_link": "https://github.com/haochenheheda/LVVIS",
        "demo_link": null
    },
    {
        "title": "OvarNet: Towards Open-Vocabulary Object Attribute Recognition",
        "image": "pics/projects_publications/ovarnet.jpg",
        "authors": "Keyan Chen, Xiaolong Jiang, Yao Hu, Xu Tang, Yan Gao, Jianqi Chen, Weidi Xie",
        "conference_name": "(CVPR) IEEE Conference on Computer Vision and Pattern Recognition",
        "arxiv_link": "https://arxiv.org/pdf/2301.09506",
        "code_link": "https://github.com/KyanChen/OvarNet",
        "demo_link": "https://chenkeyan.top/OvarNet/"
    },
    {
        "title": "MSMC-TTS: Multi-Stage Multi-Codebook VQ-VAE Based Neural TTS",
        "image": "pics/projects_publications/msmc_tts.jpg",
        "authors": "Haohan Guo, Fenglong Xie, Xixin Wu, Frank K Soong, Helen Meng",
        "conference_name": "(TASLP) IEEE/ACM Transactions on Audio, Speech, and Language Processing",
        "arxiv_link": "https://ieeexplore.ieee.org/document/10114504",
        "code_link": "https://github.com/hhguo/MSMC-TTS",
        "demo_link": null
    }
];