Efficient Training papers, 2023–2026

Key findings

• Efficient Training went from 346 papers in 2023 to 603 in 2026, roughly 1.7x in three years.
• NeurIPS publishes the most Efficient Training work: 499 papers from 2023 to 2026, 28% of the four-venue total.
• The fastest-growing overlap is with Deep learning · large language models: papers tagged with both rose from 6 in 2023 to 50 in 2026.
• Among the 5 topics under Efficiency and Systems, it ranks #3 by 2026 paper count; the fastest grower in the group, Hardware-Aware ML, is up 4.4x versus 1.7x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Efficient Training papers

499 papers, page 1 of 10

1. NeurIPS 2026$\delta$-Mem: : Efficient Online Memory For Large Language Models
2. NeurIPS 2026A Grid Efficient Transport Optimization Model for the Wasserstein Barycenter Problem
3. NeurIPS 2026A Solver-Efficient Neural Adversarial Attack on Subgraph Matching Models
4. NeurIPS 2026Achieve Latency-Efficient Temporal-Coding Spiking LLMs via Discretization-Aware Conversion
5. NeurIPS 2026Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
6. NeurIPS 2026Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation
7. NeurIPS 2026ADIS-Law: Unified Scaling Laws for Annealing-Phase Domain Injection in Large Language Models
8. NeurIPS 2026Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training
9. NeurIPS 2026AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition
10. NeurIPS 2026An Efficient Cross-modal Feature Reconstruction Model for Multimodal Multi-class Anomaly Detection
11. NeurIPS 2026ASVQ: What Reparameterization Is Just Enough for Efficient Codebook Learning?
12. NeurIPS 2026Asymmetric Scaling Laws from Sparse Features
13. NeurIPS 2026Attribute-Efficient Learning of Sparse Halfspaces with Constant Malicious Noise Rate
14. NeurIPS 2026Benchmarks as Measurement Instruments: Quantifying Signal and Noise for More Efficient AI Evaluations Under Distribution Shift
15. NeurIPS 2026Beyond Pairwise Supervision: Spectral Characteristic Matching for Data-Efficient Multimodal Alignment
16. NeurIPS 2026Beyond the Half Approximation: Fair and Efficient Online Class Matching
17. NeurIPS 2026Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization
18. NeurIPS 2026BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots
19. NeurIPS 2026BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node Perturbation
20. NeurIPS 2026BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
21. NeurIPS 2026ByteDistill: Cross-Tokenizer Distillation via Chunk-wise Byte-Level Distribution Alignment
22. NeurIPS 2026CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes
23. NeurIPS 2026CHoRD: Coordinating Scheduling and Data Placement for Efficient Deep Neural Network Inference on Chiplet-Based GPUs
24. NeurIPS 2026Communication-Efficient LLM Adaptation over Decentralized GPU Meshes
25. NeurIPS 2026Communication-Efficient Personalized Adaptation via Federated-Local Model Merging
26. NeurIPS 2026CommunityKV: Efficient Long-Context Decoding via Graph Partitioning
27. NeurIPS 2026CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection
28. NeurIPS 2026Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
29. NeurIPS 2026Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
30. NeurIPS 2026CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelling
31. NeurIPS 2026CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching
32. NeurIPS 2026Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws
33. NeurIPS 2026Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
34. NeurIPS 2026Dataset Distillation via Drifting
35. NeurIPS 2026Decomposing and Reshaping Scaling Laws through Token Learning Times
36. NeurIPS 2026Depth through Recurrence: Towards Ultra-Efficient On-Device ASR
37. NeurIPS 2026DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
38. NeurIPS 2026DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts
39. NeurIPS 2026Dynamic Convolutions Improve Transformers
40. NeurIPS 2026Dynamic Resolution Routing for Efficient Egocentric Grounding
41. NeurIPS 2026Dynamics-Aware Sparse Attention for Efficient Autoregressive Video Diffusion
42. NeurIPS 2026DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNs
43. NeurIPS 2026Efficient Algorithms for Distributed Saddle Problems
44. NeurIPS 2026Efficient Algorithms For Fully Dynamic Bipartite Matching In Metric Spaces
45. NeurIPS 2026Efficient algorithms for linear regression with heteroskedastic errors
46. NeurIPS 2026Efficient Benchmarking Is Just Feature Selection and Multiple Regression
47. NeurIPS 2026Efficient Brain-to-Speech Decoding with Fixed-Delay Spiking Neural Networks
48. NeurIPS 2026Efficient Collaborative LLM Fine-Tuning over Heterogeneous Mobile Devices via Many Backbones to One Side-Network Tuning
49. NeurIPS 2026Efficient Computation and Best-Response Dynamics in Anonymous Two-Action Games with Linear Utilities
50. NeurIPS 2026Efficient Decoder Scaling Strategy for Constructive Neural Routing Solvers

FAQ

How many Efficient Training papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,765 in total: 346 in 2023, 300 in 2024, 516 in 2025, 603 in 2026.

How many Efficient Training papers are at NeurIPS 2026?

NeurIPS 2026 has 177 Efficient Training papers, versus 190 the year before.

How many Efficient Training papers are at ICLR 2026?

ICLR 2026 has 148 Efficient Training papers, versus 126 the year before.

How many Efficient Training papers are at ICML 2026?

ICML 2026 has 169 Efficient Training papers, versus 118 the year before.

How many Efficient Training papers are at CVPR 2026?

CVPR 2026 has 109 Efficient Training papers, versus 82 the year before.

Which conference publishes the most Efficient Training papers?

NeurIPS, with 499 papers from 2023 to 2026.