Mechanism Design papers, 2023–2026

Key findings

• Mechanism Design went from 140 papers in 2023 to 426 in 2026, roughly 3.0x in three years.
• NeurIPS publishes the most Mechanism Design work: 394 papers from 2023 to 2026, 38% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 5 in 2023 to 42 in 2026.
• Among the 5 topics under Games and Planning, it ranks #2 by 2026 paper count; the fastest grower in the group, Classical Planning, is up 3.3x versus 3.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks
• ICML 2026Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
• ICLR 2026Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation
• CVPR 2026FEAT Fashion Editing and Try-On from Any Design
• NeurIPS 2025A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
• ICML 2025Benign Overfitting in Token Selection of Attention Mechanism
• ICLR 2025AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning
• CVPR 2025A Selective Re-learning Mechanism for Hyperspectral Fusion Imaging
• NeurIPS 2024AFBench: A Large-scale Benchmark for Airfoil Design
• ICML 2024CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model
• ICLR 2024Adaptive Instrument Design for Indirect Experiments
• CVPR 2024InceptionNeXt: When Inception Meets ConvNeXt
• NeurIPS 2023An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions
• ICML 2023AbODE: Ab initio antibody design using conjoined ODEs
• ICLR 2023Conditional Antibody Design as 3D Equivariant Graph Translation
• CVPR 2023Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization
• NeurIPS 2026A Unified Framework for Uniform-Price Resource Allocation Mechanisms
• ICML 2026Anatomy of Massive Activations and Attention Sinks
• ICLR 2026How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data
• CVPR 2026Parallax to Align Them All An OmniParallax Attention Mechanism for

All Mechanism Design papers

394 papers, page 4 of 8

151. NeurIPS 2026Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping
152. NeurIPS 2026Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
153. NeurIPS 2026Support Before Frequency in Discrete Diffusion
154. NeurIPS 2026Swimba: Switch Mamba Model Scales State Space Models
155. NeurIPS 2026Take It or Leave It: Intent-Controlled Partial Optimal Transport
156. NeurIPS 2026TANGO: RNA Topology and Geometry Co-Design
157. NeurIPS 2026Task-Driven Bayesian Experimental Design Yields Singly Intractable Objectives for Joint Policy Training
158. NeurIPS 2026Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models
159. NeurIPS 2026The Alternation Depth Principle for Neural Operator Design
160. NeurIPS 2026The Design Space of Tri-Modal Masked Diffusion Models
161. NeurIPS 2026The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
162. NeurIPS 2026The Key to Going Linear: Analysis-Driven Transformer Linearization
163. NeurIPS 2026The Path Not Taken: RLVR Learns Off the Principals
164. NeurIPS 2026The Power of Menus in Dynamic Pricing: Near Optimal Regret and Equivalence Results
165. NeurIPS 2026The Quantization Benefits of Residual-Free Transformers
166. NeurIPS 2026The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
167. NeurIPS 2026Treat Domain-Specific Languages as Design Variables in LLM Agents
168. NeurIPS 2026Two is better than one: designing heterogeneous scales in binary rating systems
169. NeurIPS 2026Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
170. NeurIPS 2026Variable-Length Generative Protein Design via Generalized Poisson Flow
171. NeurIPS 2026VEHBench: A Stage-Local Diagnostic Benchmark for LLM-Assisted Vibration Energy Harvester Design
172. NeurIPS 2026Verifier Choice is a Benchmark Design Variable: Auditing Structural Counting Evaluation in Text-to-Image Models
173. NeurIPS 2026Virtual Head Attention
174. NeurIPS 2026When Does Knowing the State Help? Diagnosing Process vs. Outcome Reward Design
175. NeurIPS 2026μLM: Rethinking Sub-100M Language Models through Memory-First Design
176. NeurIPS 2025A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
177. NeurIPS 2025A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing
178. NeurIPS 2025A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
179. NeurIPS 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition
180. NeurIPS 2025AlphaFold Database Debiasing for Robust Inverse Folding
181. NeurIPS 2025Ambient Proteins - Training Diffusion Models on Noisy Structures
182. NeurIPS 2025Attention Mechanism, Max-Affine Partition, and Universal Approximation
183. NeurIPS 2025Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings
184. NeurIPS 2025Bayes optimal learning of attention-indexed models
185. NeurIPS 2025Beyond Last-Click: An Optimal Mechanism for Ad Attribution
186. NeurIPS 2025BikeBench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints
187. NeurIPS 2025Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind
188. NeurIPS 2025Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism
189. NeurIPS 2025Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization
190. NeurIPS 2025Compress Large Language Models via Collaboration Between Learning and Matrix Approximation
191. NeurIPS 2025Convergent Functions, Divergent Forms
192. NeurIPS 2025Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image Classification
193. NeurIPS 2025CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design
194. NeurIPS 2025Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL
195. NeurIPS 2025DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
196. NeurIPS 2025Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference
197. NeurIPS 2025DuSA: Fast and Accurate Dual-Stage Sparse Attention Mechanism Accelerating Both Training and Inference
198. NeurIPS 2025Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval
199. NeurIPS 2025Efficient Bayesian Experiment Design with Equivariant Networks
200. NeurIPS 2025Emergence of Linear Truth Encodings in Language Models

FAQ

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

1,037 in total: 140 in 2023, 200 in 2024, 271 in 2025, 426 in 2026.

How many Mechanism Design papers are at NeurIPS 2026?

NeurIPS 2026 has 175 Mechanism Design papers, versus 108 the year before.

How many Mechanism Design papers are at ICLR 2026?

ICLR 2026 has 65 Mechanism Design papers, versus 58 the year before.

How many Mechanism Design papers are at ICML 2026?

ICML 2026 has 128 Mechanism Design papers, versus 65 the year before.

How many Mechanism Design papers are at CVPR 2026?

CVPR 2026 has 58 Mechanism Design papers, versus 40 the year before.

Which conference publishes the most Mechanism Design papers?

NeurIPS, with 394 papers from 2023 to 2026.