低秩适配论文趋势 2023–2026

主要结论

• 低秩适配论文从 2023 年的 282 篇增长到 2026 年的 841 篇，三年间扩大到约 3.0 倍。
• NeurIPS 是发低秩适配论文最多的会议，2023–2026 年共 781 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 4 篇增至 2026 年的 61 篇。
• 在「优化与缩放」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的缩放定律是 4.1 倍，低秩适配是 3.0 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 2026$\delta$-Mem: : Efficient Online Memory For Large Language Models
• ICML 2026A3: an Analytical Low-Rank Approximation Framework for Attention
• ICLR 2026A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
• CVPR 20262-Shots in the Dark Low-Light Denoising with Minimal Data Acquisition
• NeurIPS 2025A geometric framework for momentum-based optimizers for low-rank training
• ICML 2025Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning
• ICLR 2025A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning
• CVPR 2025AdaDARE-gamma: Balancing Stability and Plasticity in Multi-modal LLMs through Efficient Adaptation
• NeurIPS 2024Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
• ICML 2024A Tensor Decomposition Perspective on Second-order RNNs
• ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
• CVPR 2024DePT: Decoupled Prompt Tuning
• NeurIPS 2023A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression
• ICML 2023A Three-regime Model of Network Pruning
• ICLR 2023A General Rank Preserving Framework for Asymmetric Image Retrieval
• CVPR 20231% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions
• NeurIPS 2026A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction
• ICML 2026Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
• ICLR 2026ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models
• CVPR 2026Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation

全部低秩适配论文

共 781 篇，第 10 / 16 页

451. NeurIPS 2025Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning
452. NeurIPS 2025RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models
453. NeurIPS 2025Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
454. NeurIPS 2025Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
455. NeurIPS 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
456. NeurIPS 2025ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
457. NeurIPS 2025Restoring Pruned Large Language Models via Lost Component Compensation
458. NeurIPS 2025Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning
459. NeurIPS 2025Ridge Boosting is Both Robust and Efficient
460. NeurIPS 2025RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models
461. NeurIPS 2025Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset
462. NeurIPS 2025RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
463. NeurIPS 2025Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA
464. NeurIPS 2025Robust Integrated Learning and Pauli Noise Mitigation for Parametrized Quantum Circuits
465. NeurIPS 2025RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
466. NeurIPS 2025S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
467. NeurIPS 2025SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
468. NeurIPS 2025SALS: Sparse Attention in Latent Space for KV Cache Compression
469. NeurIPS 2025Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function
470. NeurIPS 2025Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
471. NeurIPS 2025Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies
472. NeurIPS 2025Self Iterative Label Refinement via Robust Unlabeled Learning
473. NeurIPS 2025Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
474. NeurIPS 2025Separating the 'what' and 'how' of compositional computation to enable reuse and continual learning
475. NeurIPS 2025Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models
476. NeurIPS 2025Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
477. NeurIPS 2025Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling
478. NeurIPS 2025Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks
479. NeurIPS 2025SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
480. NeurIPS 2025Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
481. NeurIPS 2025Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy
482. NeurIPS 2025Spike-RetinexFormer: Rethinking Low-light Image Enhancement with Spiking Neural Networks
483. NeurIPS 2025SplashNet: Split‑and‑Share Encoders for Accurate and Efficient Typing with Surface Electromyography
484. NeurIPS 2025STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
485. NeurIPS 2025StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
486. NeurIPS 2025SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training
487. NeurIPS 2025SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
488. NeurIPS 2025Tensor Product Attention Is All You Need
489. NeurIPS 2025Test-Time Adaptation by Causal Trimming
490. NeurIPS 2025The Best Instruction-Tuning Data are Those That Fit
491. NeurIPS 2025The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
492. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
493. NeurIPS 2025The Persistence of Neural Collapse Despite Low-Rank Bias
494. NeurIPS 2025The Primacy of Magnitude in Low-Rank Adaptation
495. NeurIPS 2025Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding
496. NeurIPS 2025Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning
497. NeurIPS 2025Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
498. NeurIPS 2025Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
499. NeurIPS 2025TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
500. NeurIPS 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses

常见问题

2023–2026 年四大会议一共有多少篇低秩适配论文？

共 2,273 篇，按年份分别是 2023 年 282 篇、2024 年 518 篇、2025 年 632 篇、2026 年 841 篇。

NeurIPS 2026 有多少篇低秩适配论文？

NeurIPS 2026 有 269 篇低秩适配论文，上一届是 241 篇。

ICLR 2026 有多少篇低秩适配论文？

ICLR 2026 有 184 篇低秩适配论文，上一届是 152 篇。

ICML 2026 有多少篇低秩适配论文？

ICML 2026 有 240 篇低秩适配论文，上一届是 136 篇。

CVPR 2026 有多少篇低秩适配论文？

CVPR 2026 有 148 篇低秩适配论文，上一届是 103 篇。

哪个会议的低秩适配论文最多？

NeurIPS，2023–2026 年共 781 篇。