基础模型适配论文趋势 2023–2026

微调与适配

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,492 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

基础模型适配论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202381183624159
202494507056270
20251741497662461
202618218714291602

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

全部基础模型适配论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 602 篇，第 5 / 13 页

  1. ICLR 2026Modality-free Graph In-context Alignment
  2. ICLR 2026MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition
  3. ICLR 2026MoSA: Mosaic Shared Adaptation of Large Language Models
  4. ICLR 2026Multi-Domain Transferable Graph Gluing for Building Graph Foundation Models
  5. ICLR 2026NEO — No-Optimization Test-Time Adaptation through Latent Re-Centering
  6. ICLR 2026New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
  7. ICLR 2026NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching
  8. ICLR 2026No outlier channels but with outlier blocks
  9. ICLR 2026Noise Stability of Transformer Models
  10. ICLR 2026Not All Documents Are What You Need for Extracting Instruction Tuning Data
  11. ICLR 2026Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models
  12. ICLR 2026On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
  13. ICLR 2026On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs
  14. ICLR 2026Optimistic Task Inference for Behavior Foundation Models
  15. ICLR 2026PARD: Accelerating LLM Inference with Low‑Cost PARallel Draft Model Adaptation
  16. ICLR 2026PAS: Estimating the target accuracy before domain adaptation
  17. ICLR 2026pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models
  18. ICLR 2026Pi-CCA: Prompt-Invariant CCA Certificates for Replay-Free Continual Multimodal Learning
  19. ICLR 2026PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection
  20. ICLR 2026Plug-and-Play Compositionality for Boosting Continual Learning with Foundation Models
  21. ICLR 2026Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
  22. ICLR 2026PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
  23. ICLR 2026Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning
  24. ICLR 2026Prompt-MII: Meta-Learning Instruction Induction for LLMs
  25. ICLR 2026Proximal Supervised Fine-Tuning
  26. ICLR 2026Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation
  27. ICLR 2026Q-Learning with Fine-Grained Gap-Dependent Regret
  28. ICLR 2026Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization
  29. ICLR 2026QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models
  30. ICLR 2026Reconstruct Anything Model a lightweight foundation model for computational imaging
  31. ICLR 2026Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
  32. ICLR 2026Repurposing Foundation Model for Generalizable Medical Time Series Classification
  33. ICLR 2026Revisiting the Past: Data Unlearning with Model State History
  34. ICLR 2026Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
  35. ICLR 2026Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
  36. ICLR 2026Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study
  37. ICLR 2026SeeDNorm: Self-Rescaled Dynamic Normalization
  38. ICLR 2026SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNING
  39. ICLR 2026SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
  40. ICLR 2026SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
  41. ICLR 2026Sparse Attention Adaptation for Long Reasoning
  42. ICLR 2026Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
  43. ICLR 2026Sparsity-promoting Fine-tuning for Equivariant Materials Foundation Model
  44. ICLR 2026Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
  45. ICLR 2026Speculative Speculative Decoding
  46. ICLR 2026ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning
  47. ICLR 2026Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaption
  48. ICLR 2026StochasTok: Improving Fine-Grained Subword Understanding in LLMs
  49. ICLR 2026Study of Training Dynamics for Memory-Constrained Fine-Tuning
  50. ICLR 2026SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal Basis

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 查基础模型适配在 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": "foundation-model-adaptation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇基础模型适配论文？
共 1,492 篇，按年份分别是 2023 年 159 篇、2024 年 270 篇、2025 年 461 篇、2026 年 602 篇。
NeurIPS 2026 有多少篇基础模型适配论文？
NeurIPS 2026 有 182 篇基础模型适配论文，上一届是 174 篇。
ICLR 2026 有多少篇基础模型适配论文？
ICLR 2026 有 187 篇基础模型适配论文，上一届是 149 篇。
ICML 2026 有多少篇基础模型适配论文？
ICML 2026 有 142 篇基础模型适配论文，上一届是 76 篇。
CVPR 2026 有多少篇基础模型适配论文？
CVPR 2026 有 91 篇基础模型适配论文，上一届是 62 篇。
哪个会议的基础模型适配论文最多？
NeurIPS，2023–2026 年共 531 篇。

「元学习与迁移」下的其他主题