NeurIPS2024-Reading-Paper-With-Code

---

注1：欢迎各位作者大佬提交issue，分享NeurIPS 2024论文和开源项目！

注2：关于CV领域顶级期刊（TPAMI、IJCV等）论文解读大盘点，详见： https://github.com/Paper2Chinese/Paper2Chinese

【NeurIPS 2024 论文开源目录】

• 3DGS(Gaussian Splatting)
• Mamba / SSM)
• Avatars
• Backbone
• CLIP
• MAE
• Embodied AI
• GNN
• 多模态大语言模型(MLLM)
• 大语言模型(LLM)
• 视觉语言模型(VLM)
• 多模态(Multi-modal)
• NAS
• OCR
• NeRF
• DETR
• Prompt
• 视觉问答(Visual Question Answering)
• 强化学习(Reinforcement Learning)
• 扩散模型(Diffusion Models)
• ReID(重识别)
• 长尾分布(Long-Tail)
• Vision Transformer
• 自监督学习(Self-supervised Learning)
• 联邦学习(Federated Learning)
• 增量学习(Incremental Learning)
• 数据增强(Data Augmentation)
• 目标检测(Object Detection)
• 异常检测(Anomaly Detection)
• 目标跟踪(Visual Tracking)
• 语义分割(Semantic Segmentation)
• 实例分割(Instance Segmentation)
• 全景分割(Panoptic Segmentation)
• 生物工程(bioengineering)
• 医学图像(Medical Image)
• 医学图像分割(Medical Image Segmentation)
• 视频目标分割(Video Object Segmentation)
• 视频实例分割(Video Instance Segmentation)
• 参考图像分割(Referring Image Segmentation)
• 图像抠图(Image Matting)
• 图像编辑(Image Editing)
• Low-level Vision
• 超分辨率(Super-Resolution)
• 去噪(Denoising)
• 去模糊(Deblur)
• 自动驾驶(Autonomous Driving)
• 生成对抗网络(GAN)
• 3D点云(3D Point Cloud)
• 3D目标检测(3D Object Detection)
• 3D语义分割(3D Semantic Segmentation)
• 3D目标跟踪(3D Object Tracking)
• 3D语义场景补全(3D Semantic Scene Completion)
• 3D配准(3D Registration)
• 3D人体姿态估计(3D Human Pose Estimation)
• 3D人体Mesh估计(3D Human Mesh Estimation)
• 少样本学习(Few-Shot Learning)
• 医学图像(Medical Image)
• 图像生成(Image Generation)
• 视频生成(Video Generation)
• 3D生成(3D Generation)
• 视频理解(Video Understanding)
• 持续学习(Continual Learning)
• 行为识别(Action Recognition)
• 行为检测(Action Detection)
• 人脸识别(Face Recognition)
• 文本检测(Text Detection)
• 知识蒸馏(Knowledge Distillation)
• 模型剪枝(Model Pruning)
• 图像压缩(Image Compression)
• 三维重建(3D Reconstruction)
• 深度估计(Depth Estimation)
• 轨迹预测(Trajectory Prediction)
• 车道线检测(Lane Detection)
• 图像描述(Image Captioning)
• 手语识别(Sign Language Recognition)
• 视频预测(Video Prediction)
• 新视点合成(Novel View Synthesis)
• Zero-Shot Learning(零样本学习)
• 立体匹配(Stereo Matching)
• 特征匹配(Feature Matching)
• 场景图生成(Scene Graph Generation)
• 计数(Counting)
• 隐式神经表示(Implicit Neural Representations)
• 图像质量评价(Image Quality Assessment)
• 视频质量评价(Video Quality Assessment)
• 数据集(Datasets)
• 反学习(Machine Unlearning)
• 新任务(New Tasks)
• 模型加速(Improving Reasoning)
• 时间序列(Time Series)
• 其他(Others)

3DGS(Gaussian Splatting)

Mamba / SSM

Avatars

Backbone

CLIP

A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization

• Paper：https://arxiv.org/abs/2410.00321
• Code：https://github.com/basiclab/Unraveling-Information-Mix-ups

MAE

Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups

• Paper: https://arxiv.org/pdf/2409.19092

OCR

Occupancy

NeRF

DETR

GNN

Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks

• Paper: https://arxiv.org/pdf/2409.19414
• Code: https://almogdavid.github.io/SSMA/

Prompt

Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models

• Paper: https://arxiv.org/abs/2409.20222
• Code: https://github.com/GoodAI/goodai-ltm-benchmark

大语言模型(LLM)

Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation

• Paper：https://arxiv.org/abs/2410.00263

RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models

• Paper: https://github.com/shuhao02/RouterDC

Can Models Learn Skill Composition from Examples?

• Paper: https://arxiv.org/pdf/2409.19808

视觉语言模型(LLM)

Vision-Language Models are Strong Noisy Label Detectors

• Paper: https://arxiv.org/abs/2409.196963
• Code: https://github.com/HotanLee/DeFT

多模态大语言模型(MLLM)

多模态

Towards Robust Multimodal Sentiment Analysis with Incomplete Data

• Paper: https://arxiv.org/abs/2409.20012
• Code: https://github.com/Haoyu-ha/LNLN

Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration

• Paper: https://arxiv.org/pdf/2409.19872
• Code: https://github.com/beepkh/UniKE

NAS

A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning

• Paper: https://arxiv.org/abs/2410.00485
• Code: https://nickyfot.github.io/hitchhickersguide.github.io/

强化学习(Reinforcement Learning)

Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance

• Paper: https://arxiv.org/abs/2410.02581

Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation

• Paper：https://arxiv.org/abs/2410.02172

ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination

• Paper：https://arxiv.org/pdf/2310.05208
• Code：https://github.com/sjtu-marl/ZSC-Eval

ReID(重识别)

扩散模型(Diffusion Models)

Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function

• Paper: https://arxiv.org/abs/2409.19967
• Code: https://github.com/I2-Multimedia-Lab/Magnet

Image Copy Detection for Diffusion Models

• Paper: https://arxiv.org/pdf/2409.19952
• Code: https://icdiff.github.io/

Simple and Fast Distillation of Diffusion Models

• Paper: https://arxiv.org/pdf/2409.19681
• Code: https://github.com/zju-pi/diff-sampler

Gradient-free Decoder Inversion in Latent Diffusion Models

• Paper: https://arxiv.org/pdf/2409.18442

Vision Transformer

视觉和语言(Vision-Language)

目标检测(Object Detection)

数据增强(Data Augmentation)

Learning from Offline Foundation Features with Tensor Augmentations

• Paper: https://arxiv.org/abs/2410.02527
• Code: https://github.com/emirkonuk/loffta

异常检测(Anomaly Detection)

目标跟踪(Object Tracking)

Spiking Neural Network as Adaptive Event Stream Slicer

• Paper：https://arxiv.org/abs/2410.02249

语义分割(Semantic Segmentation)

Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation

• Paper：https://arxiv.org/abs/2410.02369

DarkSAM: Fooling Segment Anything Model to Segment Nothing

• Paper：https://arxiv.org/pdf/2409.17874
• Code：https://github.com/CGCL-codes/DarkSAM

少样本学习(Few-Shot Learning)

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification

• Paper: https://arxiv.org/abs/2409.19720
• Code: https://github.com/fukexue/FAST

生物工程(bioengineering)

FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling

• Paper：https://arxiv.org/pdf/2409.19645

Generalized Protein Pocket Generation with Prior-Informed Flow Matching

• Paper: https://arxiv.org/pdf/2409.19520

医学图像(Medical Image)

Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization

• Paper: https://arxiv.org/abs/2409.20409

医学图像分割(Medical Image Segmentation)

视频目标分割(Video Object Segmentation)

人脸识别(Face Recognition)

CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition

• Paper: https://arxiv.org/pdf/2409.18876
• Code: https://github.com/szlbiubiubiu/CemiFace

3D点云(3D-Point-Cloud)

自监督学习(Self-supervised Learning)

Localizing Memorization in SSL Vision Encoders

• Paper: https://arxiv.org/pdf/2409.19069

Cross-video Identity Correlating for Person Re-identification Pre-training

• Paper: https://arxiv.org/pdf/2409.18569
• Code: https://github.com/Zplusdragon/CION_ReIDZoo

联邦学习(Federated Learning)

Hierarchical Federated Learning with Multi-Timescale Gradient Correction

• Paper: https://arxiv.org/pdf/2409.18448
• Code: https://github.com/wenzhifang/MTGC

增量学习(Incremental Learning)

Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning

• Paper: https://arxiv.org/pdf/2409.18265
• Code: https://github.com/grypesc/AdaGauss

3D语义分割(3D Semantic Segmentation)

图像编辑(Image Editing)

图像补全/图像修复(Image Inpainting)

生成对抗网络(GAN)

Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images

• Paper: https://arxiv.org/abs/2409.20530
• Code: https://berkegokmen1.github.io/dual-enc-3d-gan-inv/

视频编辑(Video Editing)

Low-level Vision

超分辨率(Super-Resolution)

去噪(Denoising)

图像去噪(Image Denoising)

3D人体姿态估计(3D Human Pose Estimation)

Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images

• Paper: https://arxiv.org/abs/2409.18364

图像生成(Image Generation)

FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner

• Paper：https://arxiv.org/abs/2409.18128
• Code：https://github.com/shiml20/FlowTurbo

视频生成(Video Generation)

3D生成

DeBaRA: Denoising-Based 3D Room Arrangement Generation

• Paper: https://arxiv.org/pdf/2409.18336

视频理解(Video Understanding)

E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

• Paper：https://arxiv.org/abs/2409.18111
• Code：https://polyu-chenlab.github.io/etbench/

持续学习(Continual Learning)

Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning

• Paper: https://arxiv.org/pdf/2409.19245
• Code: https://github.com/wxr99/Forgetting-Ignorance-or-Myopia-Revisiting-Key-Challenges-in-Online-Continual-Learning

行为识别(Action Recognition)

Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection

• Paper: https://arxiv.org/pdf/2409.19252

知识蒸馏(Knowledge Distillation)

图像压缩(Image Compression)

立体匹配(Stereo Matching)

场景图生成(Scene Graph Generation)

计数(Counting)

隐式神经表示(Implicit Neural Representations)

Towards Croppable Implicit Neural Representations

• Paper: https://arxiv.org/abs/2409.19472
• Code: https://github.com/maorash/Local-Global-INRs

视频质量评价(Video Quality Assessment)

数据集(Datasets)

Towards Comprehensive Detection of Chinese Harmful Memes

• Paper：https://arxiv.org/abs/2410.02378
• Code：https://github.com/DUT-lujunyu/ToxiCN_MM

T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition

• Paper: https://arxiv.org/abs/2409.19734
• Code: https://github.com/nctu-eva-lab/VHD11K

Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting

• Paper: https://arxiv.org/abs/2409.18591
• Code: https://github.com/Multihuntr/GFF

反学习(Machine Unlearning)

Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement

• Paper: https://arxiv.org/abs/2409.19732
• Code: https://github.com/K1nght/Unified-Unlearning-w-Remain-Geometry

新任务(New Tasks)

Most Influential Subset Selection: Challenges, Promises, and Beyond

• Paper: https://arxiv.org/pdf/2409.18153

模型加速(Improving Reasoning)

On the Inductive Bias of Stacking Towards Improving Reasoning

• Paper: https://arxiv.org/pdf/2409.19044

时间序列(Time Series)

Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective

• Paper: https://arxiv.org/pdf/2409.18696
• Code: https://github.com/ForestsKing/GLAFF

其他(Others)

Predictive Attractor Models

• Paper: https://arxiv.org/abs/2410.02430

Maia-2: A Unified Model for Human-AI Alignment in Chess

• Paper: https://arxiv.org/abs/2409.20553

PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond

• Paper: https://arxiv.org/abs/2409.19772
• Code: https://github.com/chensong1995/PPLN

RMLR: Extending Multinomial Logistic Regression into General Geometries

• Paper: https://arxiv.org/pdf/2409.19433
• Code: https://github.com/GitZH-Chen/RMLR

An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness

• Paper: https://arxiv.org/pdf/2409.19212

On the Power of Decision Trees in Auto-Regressive Language Modeling

• Paper: https://arxiv.org/pdf/2409.19150

Autoregressive Policy Optimization for Constrained Allocation Tasks

• Paper: https://arxiv.org/pdf/2409.18735
• Code: https://github.com/niklasdbs/paspo

Generative Retrieval Meets Multi-Graded Relevance

• Paper: https://arxiv.org/pdf/2409.18409

Decomposable Transformer Point Processes

• Paper: https://arxiv.org/abs/2409.18158

Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel

• Paper：https://arxiv.org/pdf/2409.18000