占用预测论文趋势 2023–2026
BEV 占用
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 298 篇被归入该主题的论文。
主要结论
- 占用预测论文从 2023 年的 44 篇增长到 2026 年的 103 篇，三年间扩大到约 2.3 倍。
- NeurIPS 是发占用预测论文最多的会议，2023–2026 年共 105 篇，占四个会议总量的 35%。
- 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 5 篇。
- 在「自动驾驶」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的运动规划是 2.4 倍，占用预测是 2.3 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 10 | 6 | 12 | 16 | 44 |
| 2024 | 20 | 8 | 27 | 15 | 70 |
| 2025 | 28 | 18 | 19 | 16 | 81 |
| 2026 | 47 | 14 | 23 | 19 | 103 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- NeurIPS 2026A Kernel Nonconformity Score for Multivariate Conformal Prediction
- ICML 2026Asymmetric conformal prediction with penalized kernel sum-of-squares
- ICLR 2026Conformal Prediction for Long-Tailed Classification
- CVPR 2026An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving
- NeurIPS 2025Accident Anticipation via Temporal Occurrence Prediction
- ICML 2025Conformal Prediction with Cellwise Outliers: A Detect-then-Impute Approach
- ICLR 2025Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence
- CVPR 20253D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
- NeurIPS 2024AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
- ICML 2024Auditing Private Prediction
- ICLR 2024Revisiting Link Prediction: a data perspective
- CVPR 2024PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation
- NeurIPS 2023Calibrating “Cheap Signals” in Peer Review without a Prior
- ICML 2023Conformal Prediction for Federated Uncertainty Quantification Under Label Shift
- ICLR 2023Batch Multivalid Conformal Prediction
- CVPR 2023Diverse 3D Hand Gesture Prediction From Body Dynamics by Bilateral Hand Disentanglement
- NeurIPS 2026AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks
- ICML 2026Improving Backward Conformal Prediction via Non-Conformity Score Transformation
- ICLR 2026How Stable is the Next Token? A Geometric View of LLM Prediction Stability
- CVPR 2026Detect Anything via Next Point Prediction
全部占用预测论文
共 298 篇，第 4 / 6 页
- ICML 2025Prediction models that learn to avoid missing values
- ICML 2025Prediction-Powered Adaptive Shrinkage Estimation
- ICML 2025Prediction-Powered E-Values
- ICML 2025Rectifying Conformity Scores for Better Conditional Coverage
- ICML 2025SPHINX: Structural Prediction using Hypergraph Inference Network
- ICML 2025Volume Optimality in Conformal Prediction with Structured Prediction Sets
- NeurIPS 2025Accident Anticipation via Temporal Occurrence Prediction
- NeurIPS 2025Anytime-valid, Bayes-assisted, Prediction-Powered Inference
- NeurIPS 2025Backward Conformal Prediction
- NeurIPS 2025Class conditional conformal prediction for multiple inputs by p-value aggregation
- NeurIPS 2025COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
- NeurIPS 2025Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
- NeurIPS 2025Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees
- NeurIPS 2025ConfTuner: Training Large Language Models to Express Their Confidence Verbally
- NeurIPS 2025Credal Prediction based on Relative Likelihood
- NeurIPS 2025Dynamic Focused Masking for Autoregressive Embodied Occupancy Prediction
- NeurIPS 2025Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention
- NeurIPS 2025Evolutionary Prediction Games
- NeurIPS 2025FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction
- NeurIPS 2025Holistic Order Prediction in Natural Scenes
- NeurIPS 2025IOSTOM: Offline Imitation Learning from Observations via State Transition Occupancy Matching
- NeurIPS 2025Learning from Delayed Feedback in Games via Extra Prediction
- NeurIPS 2025OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction
- NeurIPS 2025ODG: Occupancy Prediction Using Dual Gaussians
- NeurIPS 2025One Sample is Enough to Make Conformal Prediction Robust
- NeurIPS 2025Prediction with expert advice under additive noise
- NeurIPS 2025PRSformer: Disease Prediction from Million-Scale Individual Genotypes
- NeurIPS 2025QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction
- NeurIPS 2025Sample-Conditional Coverage in Split-Conformal Prediction
- NeurIPS 2025See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction
- NeurIPS 2025Smooth Quadratic Prediction Markets
- NeurIPS 2025Statistical Inference under Performativity
- NeurIPS 2025Stochastically Dominant Peer Prediction
- NeurIPS 2025Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands
- CVPR 2024Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
- CVPR 2024Adapting to Length Shift: FlexiLength Network for Trajectory Prediction
- CVPR 2024Beyond Average: Individualized Visual Scanpath Prediction
- CVPR 2024Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles
- CVPR 2024COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
- CVPR 2024How Far Can We Compress Instant-NGP-Based NeRF?
- CVPR 2024HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention
- CVPR 2024Learning Group Activity Features Through Person Attribute Prediction
- CVPR 2024Learning Occupancy for Monocular 3D Object Detection
- CVPR 2024LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction
- CVPR 2024PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation
- CVPR 2024SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
- CVPR 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction
- CVPR 2024StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation
- CVPR 2024Unsupervised Occupancy Learning from Sparse Point Cloud
- ICLR 2024Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查占用预测在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "occupancy-prediction"}
常见问题
- 2023–2026 年四大会议一共有多少篇占用预测论文？
- 共 298 篇，按年份分别是 2023 年 44 篇、2024 年 70 篇、2025 年 81 篇、2026 年 103 篇。
- NeurIPS 2026 有多少篇占用预测论文？
- NeurIPS 2026 有 47 篇占用预测论文，上一届是 28 篇。
- ICLR 2026 有多少篇占用预测论文？
- ICLR 2026 有 14 篇占用预测论文，上一届是 18 篇。
- ICML 2026 有多少篇占用预测论文？
- ICML 2026 有 23 篇占用预测论文，上一届是 19 篇。
- CVPR 2026 有多少篇占用预测论文？
- CVPR 2026 有 19 篇占用预测论文，上一届是 16 篇。
- 哪个会议的占用预测论文最多？
- NeurIPS，2023–2026 年共 105 篇。