本页面排查出了 NeurIPS 2024 论文中的 98 个假开源项目，数目触目惊心。
1. 缘起与技术： 起源于被无数个 "Coming Soon" 占坑仓库浪费时间的愤怒。数据截止 2026 年 2 月 3 日，此时距 NeurIPS 2024 召开（2024.12）已逾一年之久——在这个时间点仍未填上的坑，大概率已是永久的 "Coming Soon"。本项目融合 OpenReview/GitHub API 及 PDF 解析技术，利用 Vibe Coding（AI 驱动开发）技术，仅用一晚构建。
2. 免责声明： 系统基于自动化爬取与启发式逻辑，难免存在误判（假阳性/假阴性）。统计结果仅供参考，使用前请自行核验。
3. 时代的警示： 随着 Agentic AI 的崛起，深度核查学术诚信的成本将趋近于零。未来，谁是脚踏实地的研究者，谁是投机取巧的 "Paper Machine"，将在大数据下一览无余。请珍惜羽毛。
4. 最后的直言： “没时间”永远不是违背承诺的借口。若无力开源，便不该在论文中画饼。菜不是原罪；但当贪欲超出了能力的边界，迫使你献祭学术道德来换取虚名时，这就是罪。
| 论文标题 | GitHub 链接 | 第一作者 | 通讯作者 | 所属机构 |
|---|---|---|---|---|
| Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling | Qiannan Zhang | Fei Wang | Weill Cornell Medicine, Cornell University | |
| Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound | Reuben Adams | Benjamin Guedj | Jozef Stefan Institute, University College London, University of London | |
| Learning predictable and robust neural representations by straightening image sequences | Xueyan Niu | Eero P Simoncelli | New York University | |
| Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization | Junlin He | Wei Ma | Hong Kong Polytechnic University | |
| Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization | Junlin He | Wei Ma | Johns Hopkins University, Hong Kong Polytechnic University | |
| LP-3DGS: Learning to Prune 3D Gaussian Splatting | Zhaoliang Zhang | Deliang Fan | University of North Carolina at Charlotte, School of Data Science, University of Virginia, Johns Hopkins University, Arizona State University | |
| Enhancing Protein Mutation Effect Prediction through a Retrieval-Augmented Framework | Ruihan Guo | Jianzhu Ma | Helixon, University of Illinois at Urbana-Champaign, New York University, Univ. of Illinois at Urbana-Champaign, Tsinghua University, Massachusetts Institute of Technology, Helixon Research, University of Illinois, Urbana Champaign | |
| TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation | Seong Hyeon Park | Jinwoo Shin | Korea Advanced Institute of Science and Technology, Hanyang University, Korea University, Korea Advanced Institute of Science & Technology | |
| Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking | Gabriel Rioux | Youssef Mroueh | International Business Machines, IBM, Cornell University, MIT-IBM Watson AI Lab, IBM Research | |
| On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift | Pratiksha Thaker | Virginia Smith | Carnegie Mellon University, School of Computer Science, Carnegie Mellon University | |
| Neural Residual Diffusion Models for Deep Scalable Vision Generation | Zhiyuan Ma | Bowen Zhou | Huazhong University of Science and Technology, Shanghai Artificial Intelligence Laboratory, Tsinghua University | |
| Learning from Offline Foundation Features with Tensor Augmentations | Emir Konuk | Kevin Smith | KTH Royal Institute of Technology, AstraZeneca | |
| 3D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization | Rui Jiao | Yang Liu | Tsinghua University, Renmin University of China, Tsinghua University | |
| Alignment at Pre-training! Towards Native Alignment for Arabic LLMs | Juhao Liang | Jinchao Xu | The Chinese University of Hong Kong (Shenzhen); National University of Singapore, The Chinese University of Hong Kong, The Chinese University of Hong Kong, Shenzhen, Tsinghua University, Shenzhen Research Institute of Big Data, King Abdullah University of Science and Technology | |
| Adversarial Moment-Matching Distillation of Large Language Models | Chen Jia | Chen Jia | Other/Independent | |
| SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network | Weiyu Guo | Hui Xiong | Hong Kong University of Science and Technology (Guangzhou), Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Hong Kong University of Science and Technology | |
| Swift Sampler: Efficient Learning of Sampler by 10 Parameters | Jiawei Yao | Canran Xiao | University of Sydney, SUN YAT-SEN UNIVERSITY | |
| A theoretical design of concept sets: improving the predictability of concept bottleneck models | Max Ruiz Luyten | Mihaela van der Schaar | University of Cambridge | |
| LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems | Pengkun Wang | Yang Wang | City University of Hong Kong, Lanzhou University, University of Science and Technology of China | |
| Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization | Xinyu Lyu | Jingkuan Song | University of Electronic Science and Technology of China, Southwest University of Finance and Economics, Tongji University | |
| Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning | Hang Zhou | Yunhe Wang | Tianjin University, Huawei Noah's Ark Lab, Huawei Technologies Ltd. | |
| Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration | Yichong Huang | Bing Qin | Cloud Computing, Peng Cheng Laboratory, Harbin Institute of Technology | |
| Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models | Jack Merullo | Ellie Pavlick | Brown University, Eberhard-Karls-Universität Tübingen | |
| Compact Language Models via Pruning and Knowledge Distillation | Saurav Muralidharan | Pavlo Molchanov | NVIDIA, NVIDIA Research | |
| Geometric Exploitation for Indoor Panoramic Semantic Segmentation | Duc Cao Dinh | Kyusung Cho | 3i.ai, MAXST, Maxst co Ltd. | |
| Probabilistic Conformal Distillation for Enhancing Missing Modality Robustness | mengxi Chen | Yanfeng Wang | Shanghai Jiaotong University, Shanghai Jiao Tong University | |
| RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting | Hsiang Hsu | Chun-Fu Chen | J.P. Morgan Chase, INRIA, JP Morgan & Chase Bank, JPMorganChase, GTAR, J.P. Morgan | |
| Toward Efficient Inference for Mixture of Experts | Haiyang Huang | Benjamin Lee | Washington University, Saint Louis, University of Pennsylvania, Facebook, Meta AI, Meta | |
| FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models | Gong Zhang | Irfan Essa | Google DeepMind, Google, Facebook | |
| Alias-Free Mamba Neural Operator | Jianwei Zheng | Xiaoqin Zhang | Zhejiang University of Technology | |
| Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse Problems | Jason Hu | Jeffrey A Fessler | GE HealthCare, University of Michigan - Ann Arbor | |
| 3D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning | Zhifan Ye | Yingyan Celine Lin | Department of Computer Science and Engineering, Hong Kong University of Science and Technology, University of Minnesota - Twin Cities, Georgia Institute of Technology, University of Science and Technology of China | |
| Beyond Accuracy: Tracking more like Human via Visual Search | Dailing Zhang | Kaiqi Huang | Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Institute of Automation, Chinese Academy of Sciences, Nanyang Technological University, Institute of automation, Chinese academy of science | |
| FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making | Yangyang Yu | Qianqian Xie | Columbia University, Rice University, Wuhan University, Millennium, Harvard University, Accenture, Stevens Institute of Technology, University of Manchester | |
| Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line | Eungyeup Kim | J Zico Kolter | School of Computer Science, Carnegie Mellon University, Carnegie Mellon University, CMU, Carnegie Mellon University | |
| Selective Explanations | Lucas Monteiro Paes | Flavio Calmon | International Business Machines, Apple, Harvard University | |
| GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent | Hongtai Zeng | Qinglai Guo | Tsinghua University, Electrical Engineering, Alibaba Group, Xi'an Jiaotong University | |
| ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving | Tao MA | Hongsheng Li | AI for Science, Shanghai AI Laboratory, Shanghai Artificial Intelligence Laboratory, Fudan University, Shanghai AI Lab, Shanghai AI Laboratory | |
| Proving Theorems Recursively | Haiming Wang | Xiaodan Liang | The Hong Kong University of Science and Technology (Guangzhou), Department of Computer Science and Engineering, Hong Kong University of Science and Technology, University of Hong Kong, Moonshot AI, ETH Zurich, University of Edinburgh, University of Edinburgh, SUN YAT-SEN UNIVERSITY | |
| Pretraining with Random Noise for Fast and Robust Learning without Weight Transport | Jeonghwan Cheon | Se-Bum Paik | Korea Advanced Institute of Science & Technology | |
| The Surprising Effectiveness of SP Voting with Partial Preferences | Hadi Hosseini | Amrit Puhan | University of Warwick, Pennsylvania State University | |
| Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond | Alan Jeffares | Mihaela van der Schaar | University of Cambridge, Mistral AI, Microsoft Research | |
| A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization | Yinuo Jiang | Ye Yuan | Huazhong University of Science and Technology, Department of Automation, Tsinghua University | |
| VISA: Variational Inference with Sequential Sample-Average Approximations | Heiko Zimmermann | Jan-Willem van de Meent | Pasteur Labs - ISI, University of Amsterdam | |
| PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling | Hao Wu | Xiao Luo | Tencent Jarvis Lab, Shandong University of Science and Technology, Tongji University, Fred Hutchinson Cancer Research Center | |
| Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way | Ming Chen | Yingwu Chen | South-Central Minzu University, National University of Defense Technology, Tsinghua University, Central China Normal University | |
| RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling | Tianhang Wang | changjun jiang | Tongji University, University of Science and Technology of China, Tsinghua University, Johns Hopkins University | |
| EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing | Qibo Qiu | Xiaofei He | Zhejiang University, Phigent | |
| Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner | Xing Cui | Zhaofeng He | Beijing University of Posts and Telecommunications, Beijing University of Post and Telecommunication | |
| A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm | Tianchi Liao | Chuan Chen | SUN YAT-SEN UNIVERSITY, Sun Yat-Sen University, Sun Yat-sen University | |
| DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting | Xiaodi Li | Yi Yang | Nanyang Technological University, Zhejiang University, Harvard Medical School, Harvard University | |
| Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization | Qianli Shen | Kenji Kawaguchi | Alibaba Group, national university of singaore, National University of Singapore, Johns Hopkins University, National University of Singapore, University of Southampton | |
| Linear Uncertainty Quantification of Graphical Model Inference | Chenghua Guo | Xi Zhang | HKUST-GZ, Beijing University of Posts and Telecommunications, Iowa State University, Lehigh University | |
| Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs | Yuxuan Qiao | Kai Chen | Shanghai Artificial Intelligence Laboratory, The Chinese University of Hong Kong, College of Computer Science and Technology, Zhejiang University, nanjing university, Shanghai AI Laboratory, University of Science and Technology of China, Southeast University | |
| SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform | Aditya Desai | Anshumali Shrivastava | Rice University, Rice University, George Mason University | |
| Mission Impossible: A Statistical Perspective on Jailbreaking LLMs | Jingtong Su | Karen Ullrich | Meta AI | |
| Unveiling LoRA Intrinsic Ranks via Salience Analysis | Wenjun Ke | Yining Li | Meta Inc., Southeast University | |
| CLIPCEIL: Domain Generalization through CLIP via Channel rEfinement and Image-text aLignment | Xi Yu | Yuewei Lin | Brookhaven national laboratory, Brookhaven National Lab, Brookhaven National Laboratory | |
| Foundation Inference Models for Markov Jump Processes | David Berghaus | Ramses J Sanchez | Fraunhofer Institute IAIS, Fraunhofer IAIS, JetBrains, Universität Potsdam, Rheinische Friedrich-Wilhelms Universität Bonn | |
| EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation | Xinyi Yu | Liu Liu | China Mobile Communications Company Limited Research Institute, Hefei University of Technology, Zhejiang University of Technology, The University of Warwick | |
| GRANOLA: Adaptive Normalization for Graph Neural Networks | Moshe Eliasof | Haggai Maron | University of Cambridge, Technion - Israel Institute of Technology, Technion, Arc Institute | |
| Association Pattern-aware Fusion for Biological Entity Relationship Prediction | Lingxiang Jia | Mingli Song | Zhejiang University | |
| MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts | Xiaokun Feng | Kaiqi Huang | Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Institute of Automation, Chinese Academy of Sciences, Nanyang Technological University, Institute of automation, Chinese academy of science | |
| CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing | Yen-Ju Lu | Jesus Villalba | Amazon, Whiting School of Engineering, Johns Hopkins University | |
| $\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition | Jianqing Xu | Bryan Hooi | Tencent Youtu Lab, Amazon, national university of singaore, National University of Singapore, National University of Singapore, University of Science and Technology of China | |
| Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning | Bei Li | Xunliang Cai | Meituan, Microsoft, Northeastern University, Tsinghua University, University of Maryland, College Park | |
| Information Re-Organization Improves Reasoning in Large Language Models | Xiaoxia Cheng | Weiming Lu | Zhejiang University, Shandong University | |
| Online Feature Updates Improve Online (Generalized) Label Shift Adaptation | Ruihan Wu | Kilian Q Weinberger | University of California, San Diego, Amazon, Cornell University, University of Oxford, Google | |
| Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation | Xuehao Cui | Xiaohong Liu | Shanghai Jiaotong University, Shanghai Jiao Tong University | |
| IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering | Ruosen Li | Xinya Du | Carnegie Mellon University, University of Texas at Dallas | |
| LG-CAV: Train Any Concept Activation Vector with Language Guidance | Qihan Huang | Mingli Song | Alibaba Group, Hangzhou City University, Zhejiang University | |
| Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency | Yue Li | Zhiwei Xiong | MiroMind, University of Science and Technology of China, USTC | |
| IR-CM: The Fast and General-purpose Image Restoration Method Based on Consistency Model | Xiaoxuan Gong | Jie Ma | Huazhong University of Science and Technology | |
| Unified Lexical Representation for Interpretable Visual-Language Alignment | Yifan Li | Tong He | Amazon, Fudan University | |
| UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond | Kun Zhou | Jiangbo Lu | The Chinese University of Hong Kong, Shenzhen, SmartMore Corporation | |
| Artemis: Towards Referential Understanding in Complex Videos | Jihao Qiu | Yunjie Tian | University of the Chinese Academy of Sciences, State University of New York at Buffalo, University of Chinese Academy of Sciences, Huawei Technologies Ltd. | |
| Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models | Liulei Li | Yi Yang | Zhejiang University | |
| Learning 3D Equivariant Implicit Function with Patch-Level Pose-Invariant Representation | Xin Hu | Jian Sun | Xi'an Jiaotong University, Shandong University | |
| Rethinking Imbalance in Image Super-Resolution for Efficient Inference | Wei Yu | Xiangyang Ji | Harbin Institute of Technology, Peking University, Tsinghua University | |
| SPO: Sequential Monte Carlo Policy Optimisation | Matthew Macfarlane | Alexandre Laterre | InstaDeep, University of Amsterdam, CFDX, University College London, University of London | |
| UniMTS: Unified Pre-training for Motion Time Series | Xiyuan Zhang | Jingbo Shang | Amazon, AWS, University of California, San Diego, Qualcomm Inc, QualComm | |
| Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging | Jiamian Wang | ZHIQIANG TAO | Rochester Institute of Technology, Shanghai Jiaotong University, Westlake University | |
| $\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning | Runqian Wang | Leonid Karlinsky | International Business Machines, MERCK & CO., INC., Massachusetts Institute of Technology | |
| Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting | Qingxiang Liu | Yuxuan Liang | The Hong Kong University of Science and Technology (Guangzhou), Salesforce AI Research, Chinese Academy of Sciences | |
| Unscrambling disease progression at scale: fast inference of event permutations with optimal transport | Peter A. Wijeratne | Daniel C. Alexander | University College London, University of Sussex | |
| AirSketch: Generative Motion to Sketch | Hui Xian Grace Lim | Ser-Nam Lim | University of Central Florida | |
| FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling | ZAIXI ZHANG | Qi Liu | Princeton University, University of Science and Technology of China | |
| Vision-Language Navigation with Energy-Based Policy | Rui Liu | Yi Yang | Zhejiang University | |
| Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection? | Qingsong Zhao | Cairong Zhao | Fudan University, Shanghai Aritifcal Intelligence Laboratory, Tongji University, Shanghai AI Laboratory | |
| How Control Information Influences Multilingual Text Image Generation and Editing? | Boqiang Zhang | Hongtao Xie | University of Science and Technology of China | |
| Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic Segmentation | Qi Bi | Yefeng Zheng | LIESMARS, Tencent, Guangxi Medical University | |
| Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting | Jincheng Zhong | Mingsheng Long | Tsinghua University, Kuaishou- 快手科技 | |
| Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections | Jiacong Xu | Vishal M. Patel | Adobe Systems, Johns Hopkins University | |
| Identifying General Mechanism Shifts in Linear Causal Representations | Tianyu Chen | Pradeep Kumar Ravikumar | Soroco, Carnegie Mellon University, Institute of Science and Technology, University of Texas at Austin | |
| Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading | Qi Bi | Yefeng Zheng | LIESMARS, Tencent, Guangxi Medical University | |
| Reconstruction of Manipulated Garment with Guided Deformation Prior | Ren Li | Pascal Fua | Mohamed bin Zayed University of Artificial Intelligence, EPFL - EPF Lausanne | |
| ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field | Kiyohiro Nakayama | Leonidas Guibas | Stanford University, NVIDIA, Simon Fraser University | |
| PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding | Jincen Jiang | Xuequan Lu | Bournemouth University, Shanghai University, Northwest A&F University, Dept. of Computer Sci. & Eng., Shanghai Jiao Tong University, Zhejiang University |