这份整理怎么读
这篇整理把 2025/2026 年 AI+CV 顶会的主会中稿论文拆成两层：首页看整体分布和入口，具体会议页看该会议的论文清单、领域分布、关键词云图和高亮论文。这样读起来更接近索引，也避免把两万多篇论文堆在同一个页面里。
总览
- 已纳入 main conference papers：33919
- 统计范围：2025/2026，AI+CV 顶会；2026 未公开 accepted list 的会议标记为 pending。
- 统计口径：不含 workshop、demo、student abstract、challenge。
- Official area / track：优先使用官方投稿分类。OpenReview 会议取
primary_area；AAAI 取 OJS technical track；CVF/IJCAI 若公开页没有投稿分类字段，则标为Official category unavailable。 - Affiliation：只使用官方论文页能读到的单位信息；没有公开时标为“官方页面未列出”。
- Recognition：OpenReview 会议页中的
Oral、Spotlight等标签会单独列出；Best/Outstanding 只收录当前官方源明确标记的论文。
| 年份 | 会议 | 状态 | 篇数 | 分布与论文清单 |
|---|---|---|---|---|
| 2025 | AAAI | available |
3028 | 打开 2025 AAAI |
| 2025 | CVPR | available |
2871 | 打开 2025 CVPR |
| 2025 | ICCV | available |
2701 | 打开 2025 ICCV |
| 2025 | ICLR | available |
3703 | 打开 2025 ICLR |
| 2025 | ICML | available |
3257 | 打开 2025 ICML |
| 2025 | IJCAI | available |
1279 | 打开 2025 IJCAI |
| 2025 | NeurIPS | available |
5286 | 打开 2025 NeurIPS |
| 2026 | AAAI | available |
2375 | 打开 2026 AAAI |
| 2026 | CVPR | available |
4068 | 打开 2026 CVPR |
| 2026 | ICLR | available |
5351 | 打开 2026 ICLR |
| 2026 | ICML | pending |
0 | 打开 2026 ICML |
| 2026 | IJCAI | pending |
0 | 打开 2026 IJCAI |
| 2026 | NeurIPS | pending |
0 | 打开 2026 NeurIPS |
| 2026 | ECCV | pending |
0 | 打开 2026 ECCV |
全局 Official Area / Track Distribution
| Official area / track | 篇数 | 占比 |
|---|---|---|
| Official category unavailable | 10919 | 32.2% |
| Technical Track | 5403 | 15.9% |
| deep_learning | 1733 | 5.1% |
| foundation or frontier models, including LLMs | 1314 | 3.9% |
| applications to computer vision, audio, language, and other modalities | 1153 | 3.4% |
| applications | 1014 | 3.0% |
| generative models | 875 | 2.6% |
| alignment, fairness, safety, privacy, and societal considerations | 755 | 2.2% |
| datasets and benchmarks | 667 | 2.0% |
| optimization | 593 | 1.7% |
| reinforcement learning | 537 | 1.6% |
| unsupervised, self-supervised, semi-supervised, and supervised representation learning | 504 | 1.5% |
| theory | 492 | 1.5% |
| deep_learning->large_language_models | 437 | 1.3% |
| reinforcement_learning | 418 | 1.2% |
| general_machine_learning | 399 | 1.2% |
| applications to physical sciences (physics, chemistry, biology, etc.) | 398 | 1.2% |
| social_and_economic_aspects_of_machine_learning | 393 | 1.2% |
| interpretability and explainable AI | 355 | 1.0% |
| learning theory | 329 | 1.0% |
| machine_learning_for_sciences | 325 | 1.0% |
| other topics in machine learning (i.e., none of the above) | 317 | 0.9% |
| applications to robotics, autonomy, planning | 269 | 0.8% |
| learning on graphs and other geometries & topologies | 247 | 0.7% |
| probabilistic_methods | 226 | 0.7% |
| transfer learning, meta learning, and lifelong learning | 213 | 0.6% |
| probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.) | 202 | 0.6% |
| applications to neuroscience & cognitive science | 179 | 0.5% |
| applications->computer_vision | 176 | 0.5% |
| Other official areas | 3077 | 9.1% |
| Total | 33919 | 100.0% |
全局 Best / Outstanding Papers
当前官方数据源中没有识别到。
全局 Highlight / Spotlight / Oral Papers
| Recognition | 篇数 |
|---|---|
| Spotlight | 1278 |
| Oral | 622 |
全局关键词云图
OpenReview 通常给出 keywords 或 primary area；CVF/AAAI/IJCAI 的官方列表通常不稳定公开关键词，因此这些会议主要用标题词参与聚类。
全局 Keywords / Topic Clusters
| Official area / track | 高频关键词 |
|---|---|
| Official category unavailable | generation(1078), image(1072), video(983), diffusion(968), visual(620), detection(598), multimodal(577), segmentation(509), object(449), gaussian(449) |
| Technical Track | image(414), detection(375), diffusion(335), language(334), graph(314), generation(309), framework(247), video(238), multimodal(230), segmentation(208) |
| deep_learning | Large Language Models(115), LLM(79), Large Language Model(52), Reinforcement Learning(51), large language models(50), LLMs(43), Reasoning(41), Diffusion Models(40), diffusion models(36), reasoning(31) |
| foundation or frontier models, including LLMs | including LLMs(1314), Large Language Models(191), LLM(107), Reinforcement Learning(96), Large Language Model(86), large language models(75), LLMs(59), Reasoning(59), reasoning(45), large language model(44) |
| applications to computer vision, audio, language, and other modalities | audio(1157), language(1153), and other modalities(1153), Large Language Models(41), Reinforcement Learning(36), 3D Gaussian Splatting(30), LLM(23), Diffusion Models(21), 3D Reconstruction(20), Gaussian Splatting(19) |
| applications | Large Language Models(27), 3D Gaussian Splatting(21), Reinforcement Learning(20), Diffusion Models(19), LLM(18), 3D Reconstruction(18), Diffusion Model(17), Gaussian Splatting(15), Novel View Synthesis(14), Vision-Language Models(13) |
| generative models | Diffusion Models(81), diffusion models(67), Diffusion Model(51), Diffusion models(42), generative models(41), Video Generation(36), Generative Models(35), diffusion model(34), Flow Matching(27), flow matching(25) |
| alignment, fairness, safety, privacy, and societal considerations | safety(781), privacy(772), fairness(765), and societal considerations(755), Large Language Models(61), LLM(41), alignment(34), Alignment(28), Safety(28), large language models(26) |
| datasets and benchmarks | Benchmark(108), benchmark(85), LLM(37), Large Language Models(36), Evaluation(28), dataset(26), evaluation(21), Dataset(19), Benchmarking(19), large language models(17) |
| optimization | optimization(45), Optimization(32), stochastic optimization(24), convex optimization(18), nonconvex optimization(16), Large Language Models(14), Federated Learning(11), acceleration(11), Combinatorial Optimization(11), Neural Combinatorial Optimization(11) |
| reinforcement learning | Reinforcement Learning(143), reinforcement learning(100), Offline Reinforcement Learning(27), Reinforcement learning(21), multi-agent reinforcement learning(14), Large Language Models(12), offline reinforcement learning(11), representation learning(11), Exploration(10), model-based reinforcement learning(10) |
| unsupervised, self-supervised, semi-supervised, and supervised representation learning | self-supervised(504), semi-supervised(504), and supervised representation learning(504), representation learning(41), Representation Learning(23), self-supervised learning(15), contrastive learning(12), unsupervised learning(12), Self-supervised learning(12), Contrastive Learning(9) |
| theory | learning theory(19), online learning(19), Online Learning(12), Learning Theory(10), sample complexity(10), PAC learning(10), transformers(9), Transformers(8), theory(7), feature learning(7) |
| deep_learning->large_language_models | Large Language Models(82), large language models(42), LLM(34), Large Language Model(32), Reasoning(18), RLHF(16), reasoning(16), LLMs(16), large language model(13), language models(11) |
| reinforcement_learning | Reinforcement Learning(99), reinforcement learning(56), Imitation Learning(20), Reinforcement learning(20), Offline Reinforcement Learning(14), Robotics(12), multi-agent reinforcement learning(10), Deep Reinforcement Learning(9), Large Language Models(9), Multi-Agent Reinforcement Learning(9) |
| general_machine_learning | Federated Learning(8), Representation Learning(7), contrastive learning(7), Conformal Prediction(6), conformal prediction(6), Contrastive Learning(6), Self-Supervised Learning(6), uncertainty quantification(5), Continual Learning(5), self-supervised learning(5) |
| applications to physical sciences (physics, chemistry, biology, etc.) | biology(404), chemistry(398), etc.)(398), AI for Science(15), flow matching(13), Large Language Models(13), diffusion models(11), Flow Matching(10), PDE(10), AI4Science(9) |
| social_and_economic_aspects_of_machine_learning | interpretability(25), Interpretability(20), Differential Privacy(18), Large Language Models(16), differential privacy(16), LLM(15), Fairness(12), large language models(12), fairness(12), mechanistic interpretability(11) |
| interpretability and explainable AI | interpretability(64), Interpretability(56), mechanistic interpretability(40), Mechanistic Interpretability(25), Large Language Models(16), LLMs(15), Explainable AI(15), Explainability(14), explainability(13), large language models(12) |
| learning theory | learning theory(14), generalization(14), deep learning theory(13), Transformer(12), feature learning(10), neural networks(9), theory(9), Learning theory(8), scaling laws(6), transformers(6) |
| machine_learning_for_sciences | AI4Science(12), Graph Neural Networks(11), Diffusion Models(10), Flow Matching(8), AI for Science(6), flow matching(6), Partial Differential Equations(6), foundation model(5), Molecular Dynamics(5), Deep Learning(5) |
| other topics in machine learning (i.e., none of the above) | none of the above)(317), Federated Learning(12), Large Language Models(11), large language models(10), Large Language Model(8), LLM(8), Optimal Transport(7), deep learning(5), Quantization(5), transformers(4) |
| applications to robotics, autonomy, planning | autonomy(270), planning(270), Reinforcement Learning(21), Autonomous Driving(19), Imitation Learning(18), Robotics(18), Robot Learning(15), robotics(15), Robotic Manipulation(14), Embodied AI(13) |
| learning on graphs and other geometries & topologies | Graph Neural Networks(41), graph neural networks(22), Graph neural networks(10), Graph Neural Network(10), graph neural network(8), Geometric Deep Learning(7), expressivity(6), GNN(6), Graph Learning(6), equivariance(6) |
| probabilistic_methods | causal inference(13), variational inference(12), Causal Inference(12), Uncertainty Quantification(12), causality(8), Bayesian inference(7), Causal inference(7), conformal prediction(7), Causal Discovery(6), Bayesian optimization(6) |
| transfer learning, meta learning, and lifelong learning | meta learning(214), and lifelong learning(213), Continual Learning(27), continual learning(22), transfer learning(10), Knowledge Distillation(10), Large Language Models(8), model merging(7), Continual learning(7), test-time adaptation(7) |
| probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.) | variational inference(213), sampling(210), UQ(202), etc.)(202), Uncertainty Quantification(14), Bayesian optimization(10), Conformal Prediction(9), uncertainty quantification(9), Variational Inference(8), Sampling(8) |
| applications to neuroscience & cognitive science | neuroscience(24), fMRI(15), Spiking Neural Networks(11), EEG(10), computational neuroscience(9), representation learning(8), cognitive science(8), Neuroscience(7), contrastive learning(5), self-supervised learning(5) |
| applications->computer_vision | Diffusion Model(7), 3D Gaussian Splatting(6), Diffusion Models(6), computer vision(5), Autonomous Driving(4), Image Generation(4), Image Editing(4), Deepfake Detection(3), Diffusion(3), Semantic Segmentation(3) |
| deep_learning->generative_models_and_autoencoders | diffusion models(21), Diffusion Models(18), generative models(11), Diffusion Model(11), Diffusion models(11), Diffusion(7), Flow Matching(6), diffusion(6), flow matching(6), Generative Models(5) |
| neuroscience_and_cognitive_science | neuroscience(15), Neuroscience(13), Spiking Neural Networks(12), EEG(10), fMRI(9), computational neuroscience(8), self-supervised learning(8), Computational Neuroscience(6), transformers(4), reinforcement learning(4) |
| learning on time series and dynamical systems | Time Series Forecasting(15), time series(12), time series forecasting(9), Time series(7), dynamical systems(7), foundation models(7), Time Series(6), time-series(4), Time series forecasting(4), Representation Learning(4) |
| applications->chemistry_physics_and_earth_sciences | AI for Science(5), drug discovery(4), flow matching(4), generative models(4), PDEs(4), Neural Operator(4), molecular dynamics(3), diffusion models(3), Molecular Dynamics(3), PDE(3) |
| deep_learning->graph_neural_networks | Graph Neural Networks(31), graph neural networks(12), Graph Neural Network(5), Link Prediction(4), Graph neural networks(4), Large Language Models(4), Graph Transformers(4), GNN(3), GNNs(3), Graph Learning(3) |
| theory->learning_theory | learning theory(6), sample complexity(5), Generalization Analysis(4), in-context learning(2), feature learning(2), single-index models(2), PAC Learning(2), high-dimensional statistics(2), Generalization Bound(2), generalization(2) |
| causal reasoning | causal inference(15), causal discovery(13), Causal Discovery(10), Causal Inference(9), causality(6), Causality(5), treatment effect estimation(3), causal structure learning(3), identifiability(3), latent variables(3) |
| neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.) | logic & formal reasoning(75), etc.)(75), Large Language Models(11), Autoformalization(5), Neural Theorem Proving(4), Formal Mathematics(4), LLM(4), Symbolic Regression(4), LLMs(3), Formal Theorem Proving(3) |
| social_aspects->accountability_transparency_and_interpretability | Interpretability(16), interpretability(15), Mechanistic Interpretability(7), mechanistic interpretability(6), Sparse Autoencoders(5), LLM(4), XAI(4), explainability(3), Explainable AI(3), explainable AI(3) |
| infrastructure, software libraries, hardware, systems, etc. | software libraries(72), hardware(72), systems(72), etc.(72), large language models(5), efficiency(5), GPU(4), large language model(4), Distributed Training(4), Large Language Models(4) |
| applications->health_medicine | healthcare(3), generative models(3), Representation Learning(3), scRNA-seq(3), protein design(3), Benchmark(3), Healthcare(3), Deep Learning(2), benchmark(2), EHR(2) |
| general_machine_learning->causality | causal inference(11), causal discovery(8), Causality(6), Causal inference(4), causality(4), Causal Inference(4), Causal Discovery(4), neural networks(3), Treatment Effect Estimation(3), unmeasured confounding(3) |
| social_aspects->privacy | Differential Privacy(16), differential privacy(15), Federated Learning(9), federated learning(6), Differential privacy(4), Privacy(3), machine unlearning(3), large language models(2), synthetic data(2), Privacy Protection(2) |
| deep_learning->robustness | robustness(6), Robustness(5), CLIP(4), Adversarial Robustness(3), adversarial robustness(3), spurious correlation(2), Large Language Models(2), Machine Learning(2), certification(2), benchmark(2) |
| theory->online_learning_and_bandits | bandits(6), Bandits(6), online learning(6), Online Learning(5), pure exploration(4), linear bandits(3), bandit(2), linear bandit(2), Contextual bandits(2), Linear Bandits(2) |
| other | Federated Learning(6), safety(2), Quantum Machine Learning(2), Large Language Models(2), Multimodal Learning(2), time series(2), jailbreak attack(1), large visual language models(1), visual thoughts(1), Code Generation(1) |
| evaluation | evaluation(10), Large Language Models(7), Evaluation(4), benchmark(3), Mathematical Reasoning(2), LLM-as-a-Judge(2), language models(2), benchmarks(2), bias(2), Robustness Evaluation(2) |
| deep_learning->algorithms | Deep Learning(6), LLMs(4), deep learning(3), second-order optimization(2), Large Language Models(2), transformer(2), quantization(2), Spiking Neural Networks(2), Model Merging(2), Quantization(2) |
| general_machine_learning->transfer_multitask_and_metalearning | Model Merging(9), test-time adaptation(4), transfer learning(3), meta-learning(3), in-context learning(3), Transfer Learning(3), Continual Learning(3), Domain Generalization(2), parameter-efficient fine-tuning(2), Parameter-efficient fine-tuning(2) |
| infrastructure | LLM(5), Large Language Model(4), Mixture-of-Experts(2), LLMs(2), Distributed training(2), federated learning(2), Quantization(2), LLM Inference(2), large language models(2), context parallelism(2) |
| general_machine_learning->representation_learning | Representation Learning(8), representation learning(3), Multimodal Learning(3), Contrastive Learning(3), Topological Deep Learning(2), Machine Learning(2), CLIP(2), density-based distance(1), Fermat distance(1), Riemannian geometry(1) |
| deep_learning->foundation_models | Foundation Model(5), Large Language Model(4), Foundation Models(3), Multimodal Large Language Models(3), Vision Language Models(2), foundation models(2), large language models(2), In-Context Learning(2), pre-training(2), post-training(2) |
| applications->everything_else | Large Language Models(2), Code Generation(2), Reasoning(2), LLMs(2), diffusion(2), synthetic data(2), Reinforcement Learning(2), Multi-class logistic regression model(1), Pairwise maximum likelihood estimation(1), Rare class analysis(1) |
| deep_learning->theory | sharpness(3), loss landscape(3), optimization(3), Diffusion models(3), Implicit Bias(2), linear mode connectivity(2), convergence(2), Neural networks(2), P(2), feature learning(2) |
| applications->neuroscience_cognitive_science | neuroscience(8), Neuroscience(5), Brain-Computer Interface(4), Spiking Neural Networks(3), spiking neural networks(3), robustness(2), computational neuroscience(2), psychology(2), cognitive science(2), multimodal(2) |
| social_aspects->safety | safety(4), Safety(4), large language models(3), Alignment(3), LLM(3), AI safety(3), Jailbreaking(3), LLM safety(2), large language model(2), LLMs(2) |
| reinforcement_learning->deep_rl | Reinforcement Learning(11), reinforcement learning(6), World Models(4), online reinforcement learning(4), Deep Reinforcement Learning(4), Model-based Reinforcement Learning(3), Reinforcement Learning from Human Feedback(2), Machine Learning(2), q-learning(2), representation learning(2) |
| deep_learning->sequential_models_time_series | Time series forecasting(6), Time Series Forecasting(6), Time Series(5), time series(3), interpretability(3), Transformer(3), Foundation models(3), Deep Learning(3), mamba(2), in-context learning(2) |
| general_machine_learning->supervised_learning | Machine Learning(3), decision forests(2), consistency(2), learning theory(2), Knowledge Distillation(2), label distribution learning(2), label polysemy(2), Crowdsourcing learning(2), ensembles(1), model efficiency(1) |
| deep_learning->attention_mechanisms | attention(6), transformers(4), Transformers(4), Attention(3), Transformer(3), transformer(3), Sparse Attention(3), in-context learning(3), Training Dynamics(2), relational(2) |
| general_machine_learning->evaluation | Large Language Models(5), Evaluation(5), benchmark(5), evaluations(5), Benchmark(4), large language models(3), synthetic data(3), evaluation(3), llm(3), evals(2) |
| deep_learning->everything_else | deep learning(3), Hessian(2), Factorization(1), Compositionality(1), Compositional Generalization(1), Data Efficiency(1), Local symmetry discovery(1), symmetry discovery(1), equivariance(1), gauge equivariant neural network(1) |
| applications->robotics | Robotics(4), imitation learning(3), Imitation Learning(3), Vision-Language Models(2), Autonomous Driving(2), Planning(2), diffusion model(2), manipulation(2), Manipulation(2), Behavior Cloning(2) |
| theory->deep_learning | deep learning(5), deep learning theory(3), Deep learning theory(2), transformers(2), theory(2), Implicit Regularization(2), Overparameterization(2), attention(2), representation(2), generalization(2) |
| applications->language_speech_and_dialog | Large Language Model(3), Automatic Speech Recognition(2), Large Language Models(2), Generative Model(2), NLP(1), Cryptic Crosswords(1), Reasoning(1), Proof/Verification(1), synthetic data(1), language model(1) |
| theory->reinforcement_learning_and_planning | reinforcement learning(6), Reinforcement Learning(6), Function Approximation(3), Reinforcement learning(2), Regret Minimization(2), offline reinforcement learning(2), generalization(2), Reinforcement Learning Theory(2), Quantum Machine Learning(2), Reinforcement learning theory(2) |
| general_machine_learning->clustering | clustering(4), Clustering(3), Multi-view Clustering(3), Federated Learning(3), Multi-View Clustering(3), spectral clustering(2), Multi-modal clustering(2), Information bottleneck(2), Multi-view clustering(2), Correlation Clustering(1) |
| theory->game_theory | Nash Equilibrium(5), game theory(3), Mechanism Design(2), policy gradient methods(2), Auction Design(2), Game Theory(2), online learning(2), Auction Theory(1), Testing Distributional Assumptions(1), Preference Aggregation(1) |
| general_machine_learning->online_learning_active_learning_and_bandits | online learning(7), Best Arm Identification(2), active learning(2), optimal design(2), Dynamic Regret(2), machine learning(2), Online Learning(2), Active learning(2), test-time adaptation(2), Game theory(1) |
| optimization->large_scale_parallel_and_distributed | Optimization(4), federated learning(3), Federated Learning(3), Pipeline Parallelism(2), distributed optimization(2), Large Language Models(2), Distributed Learning(2), decentralized optimization(2), Asynchronous Optimization(2), stochastic optimization(2) |
| social_aspects->security | large language models(3), security(3), large language model(2), code security(2), benchmark(2), adversarial attacks(2), prompt optimization(2), Diffusion Model(2), Adversarial Purification(2), Adversarial Attack(2) |
| reinforcement_learning->multiagent | Multi-Agent Reinforcement Learning(5), Multi-agent Reinforcement Learning(5), Reinforcement Learning(3), multi-agent systems(2), multi-agent reinforcement learning(2), reinforcement learning(2), multi-agent(2), Hypergraph Convolution(1), Dynamic Grouping(1), Multi-Agent Cooperation(1) |
| general_machine_learning->unsupervised_and_semisupervised_learning | Anomaly Detection(3), semi-supervised learning(3), manifold learning(2), Representation Learning(2), unsupervised learning(2), Dimension Reduction(1), Denoising(1), Diffusion Maps(1), Laplacian(1), VAE(1) |
| deep_learning->other_representation_learning | Transformer(3), Interpretability(2), representation alignment(2), diffusion model(2), Mixture of Experts(2), CLIP(2), representation learning(2), Trajectory representation learning(1), mobility learning(1), spatio-temporal learning(1) |
| general_machine_learning->everything_else | Federated learning(2), Conformal Prediction(2), language models(1), safety(1), interpretability(1), reliability(1), Machine unlearning(1), poisoning attack(1), thrust vector control theory(1), John's Theorem(1) |
| applications->time_series | time series(3), Time Series(3), Time series forecasting(3), Multivariate time series forecasting(2), Time Series Foundation Models(2), Time Series Forecasting(2), Time Series Classification(2), machine learning(2), Large Language Models(2), Time Series Analysis(1) |
| optimization->discrete_and_combinatorial_optimization | Combinatorial Optimization(6), Neural Combinatorial Optimization(3), Mixed Integer Linear Programming(3), submodular optimization(2), Large Language Model(2), Vehicle Routing Problem(1), Multi-Task Learning(1), Task-Specific Prompt(1), Dual Attention Mechanism(1), Cross-Problem Learning(1) |
| theory->optimization | differential privacy(2), algorithms(2), parameterized complexity(2), non-convex optimization(2), Clustering(2), optimization(2), Information theoretic generalization(1), Langevin(1), SGD(1), Permutation-based SGD(1) |
| reinforcement_learning->batchoffline | Offline Reinforcement Learning(4), reinforcement learning(3), Decision Transformer(2), offline reinforcement learning(2), Offline Goal-Conditioned Reinforcement Learning(2), latent action learning(1), imitation learning(1), learning from observations(1), learning from videos(1), latent action model(1) |
| social_aspects->fairness | fairness(9), Fairness(6), Large Language Models(2), Watermarking(1), Knowledge Graph(1), Diffusion Models(1), Generative Models(1), Counterfactual fairness(1), Principal strata(1), bias mitigation(1) |
| probabilistic_methods->monte_carlo_and_sampling_methods | sampling(2), Sampling(2), MCMC(2), Markov chain Monte Carlo(2), jarzynski(1), generative models(1), diffusion(1), monte carlo(1), Stochastic Optimal Control(1), Bridges(1) |
| theory->everything_else | distributed diffusion models(1), generation error bound(1), Tensors(1), Kronecker measurements(1), Sketching(1), Matrix-Vector(1), Lower Bound(1), Query Complexity(1), prediction-powered inference(1), L-statistics(1) |
| general_machine_learning->sequential_network_and_time_series_modeling | time series forecasting(3), Time Series(2), Invariances(1), Neural Networks(1), Convolutions(1), spatio-temporal modeling(1), time-series modeling(1), time-shift operator(1), Khatri-Rao neural operator(1), neural operator(1) |
| deep_learning->selfsupervised_learning | self-supervised learning(4), Self-supervised learning(2), Semi-supervised learning(2), contrastive learning(2), JEPA(1), MoE(1), multimodal(1), alignment(1), Contrastive learning(1), labeling error(1) |
| probabilistic_methods->bayesian_models_and_methods | Bayesian Deep Learning(2), Uncertainty Quantification(2), Bayesian Inference(2), Bayesian optimization(2), Kalman Filtering(1), Sensor Scheduling(1), Bayesian State-Space Models(1), Control(1), Bayesian Neural Networks(1), BNNs(1) |
| theory->probabilistic_methods | Conformal prediction(2), Calibration(2), DDPM(1), Stochastic Localization(1), speculative decoding(1), probabilistic inference(1), tractable models(1), expressive-efficiency(1), Data Analysis Pipeline(1), AutoML(1) |
| probabilistic_methods->variational_inference | Variational Inference(5), Bayesian Inference(2), Multilayer matrix factorization(1), Variational inference(1), Variational diffusion models(1), Dimension reduction(1), Diffusion bridge(1), variational approximation(1), change of measure(1), Phylogenetic Inference(1) |
| reinforcement_learning->planning | Monte-Carlo Tree Search(3), planning(3), Reinforcement Learning(2), iLQR(1), Differentiable control(1), Learning based control(1), Continuous Reinforcement Learning Planning(1), Planning under Uncertainty(1), Monte-carlo tree search(1), distributionally robust reinforcement learning(1) |
| optimization->stochastic | stochastic optimization(3), Optimization(1), Stochastic Optimization(1), Coordinate Descent(1), Random Permutations(1), Sample average approximation(1), diametrical risk minimization(1), confidence bound(1), heavy tails(1), Non-convex Optimization(1) |
| social_aspects->robustness | Semantic Bias(1), Shortcut Learning(1), Siamese Networks(1), Model Generalization(1), Debiasing(1), Tabular LLM(1), Model Multiplicity(1), Few-shot Learning(1), Prediction Consistency(1), Certification(1) |
| social_aspects->alignment | RLHF(3), AI Alignment(2), Reinforcement Learning(2), preference learning(2), Safety Alignment(2), Value lock-in(1), Human-AI interaction(1), Myopic Optimization(1), LLM Agents(1), Process Supervision(1) |
| general_machine_learning->scalable_algorithms | Extreme Multi-Label Classification(1), Low-Precision Training(1), Peak Memory Optimization(1), FLOAT8 training(1), Sci-ML(1), Physics Informed Neural Networks(1), Natural Gradients(1), Sketching(1), Dimensionality Reduction(1), Dimension Reduction(1) |
| social_aspects | LLM(1), membership inference(1), dataset inference(1), watermarking(1), test set contamination(1), algorithmic monoculture(1), evaluations(1), LLMs(1), Healthcare(1), Safety(1) |
| optimization->nonconvex | Contextual Optimization(1), Machine Learning(1), Constrained Optimization(1), primal-dual algorithms(1), stochastic optimization(1), single-loop algorithms(1), linear inequality constraints(1), Continual optimization(1), meta-parameter optimization(1), Matrix factorisation(1) |
| theory->domain_adaptation_and_transfer_learning | Domain adaptation(2), Transfer Learning(2), In-context learning(1), Generalization(1), OOD(1), out-of-distribution(1), Machine Learning(1), ICL(1), model ensemble(1), fine-tuning(1) |
| optimization->zeroorder_and_blackbox_optimization | Bayesian optimization(2), Universal optimization(1), Offline optimization(1), discrete optimization(1), derivative-free optimization(1), black-box function(1), regret bounds(1), subspace learning(1), neural networks(1), surrogate modeling(1) |
| probabilistic_methods->gaussian_processes | stochastic poisson surface reconstruction(1), geometric gaussian processes(1), computer graphics(1), Gaussian process(1), Kronecker(1), Bayesian(1), scalable(1), product kernel(1), gridded data(1), missing values(1) |
| optimization->convex | convex optimization(3), Convex optimizaton(1), Nonsmooth optimization(1), Shuffling methods(1), neural operators(1), proximal optimization(1), bregman divergence(1), fourier neural operator(1), cutting plane method(1), active learning(1) |
| probabilistic_methods->everything_else | online multiple testing(1), generalized -investing(1), e-value(1), false discovery rate(1), prediction-powered inference(1), e-values(1), statistical inference(1), distribution-free methods(1), human-ai(1), consensus(1) |
| applications->social_sciences | interpretability(1), hypothesis generation(1), sparse autoencoders(1), computational social science(1), topic modeling(1), Pluralistic Alignment(1), Text-to-Image Diffusion(1), Intersectionality(1), Urban Planning(1), DPO(1) |
| reinforcement_learning->online | Reinforcement Learning(2), Model-Free Reinforcement Learning(1), Policy Optimization(1), Offline-to-online RL(1), Unsupervised Pre-training(1), Exploration(1), Anomaly Detection(1), Safety Mechanisms(1), Distributional Reinforcement Learning(1), Risk Aversion(1) |
| general_machine_learning->hardware_and_software | PyTorch(2), Quantization(2), Rematerialization(1), Checkpointing(1), Memory-Efficient Training(1), Neural Networks(1), Integer Linear Programming(1), Training(1), Linear RNNs(1), Sparsity(1) |
| optimization->everything_else | Manifold Denoising(1), Learning-to-optimize(1), Quantum Computing(1), QAOA(1), Correlation Clustering(1), Inverse problems(1), data-driven priors(1), deep equilibrium(1), iterative refinement(1), spatial adaptivity.(1) |
| reinforcement_learning->everything_else | Multi-Objective Optimization(1), Multi-Objective Reinforcement Learning(1), Embodied AI(1), Model implanting(1), World models(1), Large language model(1), Reinforcement learning(1), Biological agents(1), Comparative study(1), Variance-penalized temporal difference learning(1) |
| general_machine_learning->kernel_methods | kernel methods(2), Learning with Invariances(1), Kernels(1), Spectral Theory(1), point processes(1), kernel intensity estimators(1), representer theorem(1), least squares loss(1), probability metrics(1), quantiles(1) |
| reinforcement_learning->inverse | Inverse Reinforcement Learning(3), Imitation Learning(2), Learning from Videos(1), Reward Formulation(1), Learning from Human Feedback(1), Preference Based Reinforcement Learning(1), Robust Learning(1), Inverse game(1), Quantal Response Equilibrium(1), Reward recovery(1) |
| probabilistic_methods->graphical_models | decision-making(1), probabilistic optimization(1), structural model(1), Probabilistic Circuits(1), Density Estimation(1), High-dimensional graphical model(1), Maximum marginal likelihood estimation(1), Marginal recoverability(1), Mixture model(1), Gene regulatory network(1) |
| theory->active_learning_and_interactive_learning | Experimental Design(1), Factorial Experiment(1), Combinatorial Interventions(1), Multi-Armed Bandits(1), Causal Inference(1), Average Treatment Effect(1), Operator Learning(1), Active Learning(1), PDEs(1), graph(1) |
| probabilistic_methods->structure_learning | causal discovery(2), Causal discovery(1), discrete latent variables(1), graph neural network(1), time series(1), non-stationary(1), probabilistic modelling(1), identifiability(1), search-and-score structure learning(1), latent variable(1) |
| applications->energy | CPU(1), Inference(1), Power Grid Control(1), Large Language Models-enhanced Reinforcement Learning(1) |
| reinforcement_learning->policy_search | reinforcement learning(1), policy gradients(1), convergence(1), deterministic policies(1), Goal-Conditioned Reinforcement Learning(1), Policy Regularization(1), Continuity of Goal-Achievement Ability(1) |
| probabilistic_methods->spectral_methods | Weight Matrix Compression(1), Noise-filtering(1), Generalization Performance(1), Random Matrix Theory(1) |
| social_aspects->everything_else | suitability(1), reliability(1), robustness(1), classifier(1), unlabeled data(1) |
阅读路径
建议先看全局分布，再按会议进入独立页面。每个会议页都把高亮论文放在前面，完整列表放在最后。