深度学习 · large language models论文趋势 2023–2026

主要结论

• 深度学习 · large language models论文从 2023 年的 488 篇增长到 2026 年的 1,131 篇，三年间扩大到约 2.3 倍。
• ICML 是发深度学习 · large language models论文最多的会议，2023–2026 年共 1,608 篇，占四个会议总量的 69%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 184 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 3；同组增长最快的扩散模型是 4.1 倍，深度学习 · large language models是 2.3 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

• ICML 2026“very likely” Means “uncertain”? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification
• ICML 2025(How) Do Language Models Track State?
• ICLR 2025AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
• NeurIPS 2024$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
• NeurIPS 20233D-LLM: Injecting the 3D World into Large Language Models
• ICML 2023Are Large Kernels Better Teachers than Transformers for ConvNets?
• ICML 2026$f$-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models
• ICML 2025A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?
• ICLR 2025Emergence of a High-Dimensional Abstraction Phase in Language Transformers
• NeurIPS 2024$\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning
• NeurIPS 2023A fast heuristic to optimize time-space tradeoff for large models
• ICML 2023Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models
• ICML 2026$L^3$: Large Lookup Layers
• ICML 2025Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
• ICLR 2025Holistically Evaluating the Environmental Impact of Creating Language Models
• NeurIPS 2024A distributional simplicity bias in the learning dynamics of transformers
• NeurIPS 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
• ICML 2023Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning
• ICML 2026$V_0$: A Generalist Value Model for Any Policy at State Zero
• ICML 2025Accelerating Unbiased LLM Evaluation via Synthetic Feedback

全部深度学习 · large language models论文

共 2,334 篇，第 21 / 47 页

1001. ICML 2026TiME: Test-Time Mixture-of-Experts Routing via Asymmetric CO-Optimal Transport for Continual Test-Time Adaptation
1002. ICML 2026Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts
1003. ICML 2026TodoEvolve: Learning to Architect Agent Planning Systems
1004. ICML 2026Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
1005. ICML 2026Token-Level LLM Collaboration via FusionRoute
1006. ICML 2026TokenDrop: Token-Level Importance-Aware Backward Propagation Skipping for Efficient LLM Fine-Tuning
1007. ICML 2026TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
1008. ICML 2026TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models
1009. ICML 2026TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
1010. ICML 2026ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind
1011. ICML 2026TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering
1012. ICML 2026Toward Cybersecurity-Expert Small Language Models
1013. ICML 2026Toward Safe Quantization-Aware Fine-tuning: Understanding and Mitigating Safety Alignment Degradation
1014. ICML 2026Toward Training Superintelligent Software Agents through Self-Play SWE-RL
1015. ICML 2026Towards Atoms of Large Language Models
1016. ICML 2026Towards Efficient LLMs Annealing with Principled Sample Selection
1017. ICML 2026Towards Execution-Grounded Automated AI Research
1018. ICML 2026Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
1019. ICML 2026Towards Functional Correctness of Large Code Models with Selective Generation
1020. ICML 2026Towards Multimodal Large Language Models with Both Training and Inference Efficiency
1021. ICML 2026Towards One-to-Many Temporal Grounding
1022. ICML 2026Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization
1023. ICML 2026Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level Watermarking
1024. ICML 2026Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
1025. ICML 2026Towards Understanding Massive Activations in Attention Sink Mechanism
1026. ICML 2026Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
1027. ICML 2026Towards Understanding the Dynamics of Low-Rank Adaptation
1028. ICML 2026TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation
1029. ICML 2026Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
1030. ICML 2026Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
1031. ICML 2026Train Once, Reuse Everywhere: Generalizable Implicit ICL by Routing Attention
1032. ICML 2026Training AI Co-Scientists Using Rubric Rewards
1033. ICML 2026Training Data Efficiency in Multimodal Process Reward Models
1034. ICML 2026Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
1035. ICML 2026Training LLM Agents to Empower Humans
1036. ICML 2026Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
1037. ICML 2026Training with Honeypots: Reshaping How LLMs Fail Under Adversarial Attacks
1038. ICML 2026Training-Free Vector Quantization via Gaussian VAEs
1039. ICML 2026Training-Trajectory-Aware Token Selection
1040. ICML 2026Training–Inference Consistent Segmented Execution for Long-Context LLMs
1041. ICML 2026Trajectory-Level Speculative Decoding for Diffusion Language Models
1042. ICML 2026Translation Heads: Disentangling meaning from language in LLM-based machine translation
1043. ICML 2026Transport and Merge: Cross-Architecture Merging for Large Language Models
1044. ICML 2026TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
1045. ICML 2026Trifuse: Enhancing Attention-Based GUI Grounding via Multimodal Fusion
1046. ICML 2026TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
1047. ICML 2026Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
1048. ICML 2026Trust Region Masking for Long-Horizon LLM Reinforcement Learning
1049. ICML 2026Truthfulness Does Not Scale Like Reasoning: Why Polling Fails as a Proxy Verifier
1050. ICML 2026TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · large language models论文？

共 2,334 篇，按年份分别是 2023 年 488 篇、2024 年 298 篇、2025 年 417 篇、2026 年 1,131 篇。

NeurIPS 2024 有多少篇深度学习 · large language models论文？

NeurIPS 2024 有 298 篇深度学习 · large language models论文，上一届是 415 篇。

ICLR 2025 有多少篇深度学习 · large language models论文？

ICLR 2025 有 13 篇深度学习 · large language models论文。

ICML 2026 有多少篇深度学习 · large language models论文？

ICML 2026 有 1,131 篇深度学习 · large language models论文，上一届是 404 篇。

哪个会议的深度学习 · large language models论文最多？

ICML，2023–2026 年共 1,608 篇。