高效训练论文趋势 2023–2026

主要结论

• 高效训练论文从 2023 年的 346 篇增长到 2026 年的 603 篇，三年间扩大到约 1.7 倍。
• NeurIPS 是发高效训练论文最多的会议，2023–2026 年共 499 篇，占四个会议总量的 28%。
• 交叉方向里涨得最快的是深度学习 · large language models：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 50 篇。
• 在「效率与系统」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的硬件协同是 4.4 倍，高效训练是 1.7 倍。

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 2026Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation
• ICML 2026A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
• ICLR 2026An Efficient SE(p)-Invariant Transport Metric Driven by Polar Transport Discrepancy-based Representation
• CVPR 2026A Bit is All You Need Efficient Video Capture via
• NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
• ICML 2025A Sample Efficient Conditional Independence Test in the Presence of Discretization
• ICLR 2025Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
• CVPR 2025Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
• NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
• ICML 2024A fast algorithm to simulate nonlinear resistive networks
• ICLR 2024Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
• CVPR 2024Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack
• NeurIPS 2023Alternating Updates for Efficient Transformers
• ICML 2023Auxiliary Modality Learning with Generalized Curriculum Distillation
• ICLR 2023A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
• CVPR 2023A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
• NeurIPS 2026Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training
• ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
• ICLR 2026AQER: A Scalable and Efficient Data Loader for Digital Quantum Computers
• CVPR 2026Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning

全部高效训练论文

共 1,765 篇，第 11 / 36 页

501. NeurIPS 2026GramStatTexNet: Efficient, Interpretable, and Neuro-Inspired Texture Analysis-by-Synthesis
502. NeurIPS 2026HetCCL: Efficient LLM Training on Heterogeneous Vendor GPUs
503. NeurIPS 2026HiFloat4 Format for Language Model Pre-training on Ascend NPUs
504. NeurIPS 2026Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
505. NeurIPS 2026How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
506. NeurIPS 2026Human-Inspired, Task-Dimension-Guided Exploration for Efficient Learning and Transfer in High Dimensions
507. NeurIPS 2026Hyperbolic Language Models: From Zipf to Compute-Optimal Scaling
508. NeurIPS 2026HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
509. NeurIPS 2026IncAgg: Efficient Memory-Enhanced Graph Learning via Incremental Aggregation
510. NeurIPS 2026Joint Sequence--Vocabulary Selection for Efficient LLM Distillation
511. NeurIPS 2026Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling
512. NeurIPS 2026Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
513. NeurIPS 2026Leech Lattice Vector Quantization for Efficient LLM Compression
514. NeurIPS 2026LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling
515. NeurIPS 2026LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling
516. NeurIPS 2026LLM Routing Through the Lens of Recommendation: A Roadmap for Efficient AI Orchestration
517. NeurIPS 2026Logical Distillation of Transformer Encoders
518. NeurIPS 2026LoopPrune: Evolutionary Module Selection with Iterative Execution for Efficient Large Language Model Compression
519. NeurIPS 2026Magnitude-preserving Layers Enable Efficient GANs
520. NeurIPS 2026Map-Guided Caching: A Global Perspective for Efficient Diffusion Transformer
521. NeurIPS 2026Matched-Control Tests of Partition-Source Claims in One Routed Distillation Family
522. NeurIPS 2026MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging
523. NeurIPS 2026Meta-memorization and memorization scaling laws in transformers
524. NeurIPS 2026MGMem: An Efficient, Deterministic, and Provenance-Preserving Framework for Long-Horizon Agent Memory
525. NeurIPS 2026Mixture-of-Top-$k$ Attention: Efficient Attention as Scalable Fast Weights
526. NeurIPS 2026MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenario
527. NeurIPS 2026Neural Neural Scaling Laws
528. NeurIPS 2026NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training
529. NeurIPS 2026NIKA: Efficient Neural Video Representation via Structured Latent Diversity
530. NeurIPS 2026Normalized Architectures are Natively 4-Bit
531. NeurIPS 2026NoTA: Normalized Tensor Adaptation for Parameter-Efficient Continual Learning
532. NeurIPS 2026Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamic Mechanisms and Efficient Alignment
533. NeurIPS 2026OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
534. NeurIPS 2026OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
535. NeurIPS 2026On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification
536. NeurIPS 2026On Neural Scaling Laws for Weather Emulation through Continual Training
537. NeurIPS 2026On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
538. NeurIPS 2026One Temperature to Rule Them All?
539. NeurIPS 2026Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation
540. NeurIPS 2026Optimal scaling laws in learning hierarchical multi-index models
541. NeurIPS 2026Orlicz–Sobolev with Musielak: An Efficient Regularization Approach for Graph-based IPM
542. NeurIPS 2026Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers
543. NeurIPS 2026PACE: Pareto-Adaptive Compression for Efficient Native MLLMs
544. NeurIPS 2026Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
545. NeurIPS 2026Patch Hierarchical Attention Transformers for Efficient Particle Jet Tagging
546. NeurIPS 2026PipeFSDP: Efficient Pipeline Parallel under Fully Sharded Data Parallel for Large Language Model Training
547. NeurIPS 2026Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation
548. NeurIPS 2026Predicting and improving test-time scaling laws via reward tail-guided search
549. NeurIPS 2026Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
550. NeurIPS 2026Progressive Layer-wise Supervision: Deep-to-Shallow Supervision Annealing for Efficient and Robust Speech Deepfake Detection

常见问题

2023–2026 年四大会议一共有多少篇高效训练论文？

共 1,765 篇，按年份分别是 2023 年 346 篇、2024 年 300 篇、2025 年 516 篇、2026 年 603 篇。

NeurIPS 2026 有多少篇高效训练论文？

NeurIPS 2026 有 177 篇高效训练论文，上一届是 190 篇。

ICLR 2026 有多少篇高效训练论文？

ICLR 2026 有 148 篇高效训练论文，上一届是 126 篇。

ICML 2026 有多少篇高效训练论文？

ICML 2026 有 169 篇高效训练论文，上一届是 118 篇。

CVPR 2026 有多少篇高效训练论文？

CVPR 2026 有 109 篇高效训练论文，上一届是 82 篇。

哪个会议的高效训练论文最多？

NeurIPS，2023–2026 年共 499 篇。