Deep learning · large language models papers, 2023–2026

Key findings

• Deep learning · large language models went from 488 papers in 2023 to 1,131 in 2026, roughly 2.3x in three years.
• ICML publishes the most Deep learning · large language models work: 1,608 papers from 2023 to 2026, 69% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 5 in 2023 to 184 in 2026.
• Among the 11 topics under Deep Learning, it ranks #3 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 2.3x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Deep learning · large language models papers

1,131 papers, page 21 of 23

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

FAQ

How many Deep learning · large language models papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

2,334 in total: 488 in 2023, 298 in 2024, 417 in 2025, 1,131 in 2026.

How many Deep learning · large language models papers are at NeurIPS 2024?

NeurIPS 2024 has 298 Deep learning · large language models papers, versus 415 the year before.

How many Deep learning · large language models papers are at ICLR 2025?

ICLR 2025 has 13 Deep learning · large language models papers.

How many Deep learning · large language models papers are at ICML 2026?

ICML 2026 has 1,131 Deep learning · large language models papers, versus 404 the year before.

Which conference publishes the most Deep learning · large language models papers?

ICML, with 1,608 papers from 2023 to 2026.