Applications · chemistry physics and earth sciences papers, 2023–2026

Key findings

• Applications · chemistry physics and earth sciences went from 293 papers in 2023 to 1,217 in 2026, roughly 4.2x in three years.
• NeurIPS publishes the most Applications · chemistry physics and earth sciences work: 1,107 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 3 in 2023 to 95 in 2026.
• Among the 10 topics under Application Domains, it ranks #2 by 2026 paper count; the fastest grower in the group, Applications · health medicine, is up 61x versus 4.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026(Strongly) Replicable Distribution Testers imply High Probability Distribution Testers
• ICML 2026(Be Cautious!) Bio-Foundation Models Are Not Yet Robust to Biologically Plausible Perturbations and ML Transformations
• ICLR 2026(U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs
• CVPR 2026AssemblyBench Physics-Aware Assembly of Complex Industrial Objects
• NeurIPS 2025A Partition Cover Approach to Tokenization
• ICML 2025A Machine Learning Approach to Duality in Statistical Physics
• ICLR 2025A new framework for evaluating model out-of-distribution generalisation for the biochemical domain
• CVPR 2025Accurate Differential Operators for Hybrid Neural Fields
• NeurIPS 2024$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials
• ICML 2024$\bf{\Phi}_\textrm{Flow}$: Differentiable Simulations for PyTorch, TensorFlow and Jax
• ICLR 2024A Foundation Model for Error Correction Codes
• CVPR 2024EarthLoc: Astronaut Photography Localization by Indexing Earth from Space
• NeurIPS 2023ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation
• ICML 2023A Deep Conjugate Direction Method for Iteratively Solving Linear Systems
• ICLR 2023A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet
• CVPR 20233D Human Pose Estimation via Intuitive Physics
• NeurIPS 2026ADA: Resolving Attribution Ambiguity in End-to-End Power System Dispatch via Two-Time-Scale Stochastic Approximation
• ICML 2026(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models
• ICLR 2026A Genetic Algorithm for Navigating Synthesizable Molecular Spaces
• CVPR 2026Brewing Stronger Features Dual-Teacher Distillation for Multispectral Earth Observation

All Applications · chemistry physics and earth sciences papers

299 papers, page 3 of 6

101. NeurIPS 2026IADR: Interface-Augmented Neural Operator for Phase-Field Mean-Curvature Flow
102. NeurIPS 2026Identifiable Feedback-Controlled Latent Flow for Unpaired Single-cell Spatio-Temporal Dynamics
103. NeurIPS 2026Implicit Neural Representations for Variational Problems on Graphons
104. NeurIPS 2026Improving Function Space Flow Matching with Kernel Optimal Transport
105. NeurIPS 2026Independent Latents, Robust Neural Operators
106. NeurIPS 2026INEUS: Iterative Neural Solver for High-Dimensional PIDEs
107. NeurIPS 2026Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms
108. NeurIPS 2026Inpainting physics: self-supervised learning for context-driven fluid simulation
109. NeurIPS 2026Invariant Features in Language Models: Geometric Characterization and Model Attribution
110. NeurIPS 2026Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion
111. NeurIPS 2026K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
112. NeurIPS 2026KerONet: A Single Softmax Readout Suffices for Physics-Informed Operator Learning
113. NeurIPS 2026LAPLEX: The FFT of Learnable Laplace Kernels
114. NeurIPS 2026Latent Generative Solvers for Generalizable Long-Term Physics Simulation
115. NeurIPS 2026Learned Lagrangian Models of PDEs via Euler–Lagrange Residual Minimization
116. NeurIPS 2026Learning Global Temporal Dynamics in Sparse Networks via Cycle Counts
117. NeurIPS 2026Learning Survival Models with Right-Censored Reporting Delays
118. NeurIPS 2026Learning the Committor Function using Weighted Ensemble Simulations
119. NeurIPS 2026Learning What's Real: Disentangling Signals and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics
120. NeurIPS 2026LeCellModel: Interpretable Density Estimation over the Gene Expression Manifold
121. NeurIPS 2026Lie Generator Networks for Nonlinear Partial Differential Equations
122. NeurIPS 2026Lifting Biomolecular Data Acquisition
123. NeurIPS 2026Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
124. NeurIPS 2026Locality Sensitive Hashing for p-Exponential Kernels with Applications to Density Estimation
125. NeurIPS 2026Long-Horizon Agency Belongs in the Harness, Not the Context Window Only
126. NeurIPS 2026Long-Rollout Stability in AI Weather Models: A Quantitative Benchmark and Analysis
127. NeurIPS 2026Looped Transformers with Layer Normalization Provably Learn the Power Method
128. NeurIPS 2026M$^3$: Reframing Training Measures for Discretized Physical Simulations
129. NeurIPS 2026Macrocanonical Generator Networks: data-efficient neural surrogates for amortized physics simulation
130. NeurIPS 2026Manifold-weighted neural networks
131. NeurIPS 2026Markovian Dynamics Enforcer: Feasibility Preserving Correction on Learned Dyanmics Manifolds
132. NeurIPS 2026MaterialsSaddles: 34 Million Transition States and a Flow-Matching Saddle-Point Predictor for Materials
133. NeurIPS 2026MC^2: Monte Carlo Correction for Fast Elliptic PDE Solving
134. NeurIPS 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
135. NeurIPS 2026Mesh-Free Convolution: Learned Spectral Attenuation and Transport
136. NeurIPS 2026MICA: Activation Checkpointing for Double-Backward Training of Machine Learning Interatomic Potentials
137. NeurIPS 2026Mimicking the Physicist's Eye: A VLM-centric Approach for Physics Formula Discovery
138. NeurIPS 2026MIND-DDI: Multi-Omics Interpretable Drug-Drug Interaction Prediction with Joint Optimization of Graph Structure, Neural Architecture, and Symbolic Rules
139. NeurIPS 2026Minimally Invasive Steering of Language Models
140. NeurIPS 2026Minimax Rates and Spectral Distillation for Tree Ensembles
141. NeurIPS 2026Model Immunization Beyond Condition Numbers: The Importance of Plateau Regions
142. NeurIPS 2026Module Specialization in Transformer Factual Recall under Correlated Fact Distributions
143. NeurIPS 2026MolSpecFlow: Modality-Incomplete Molecular--Spectral Learning for MS/MS
144. NeurIPS 2026MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
145. NeurIPS 2026Monroe: A Molecular Foundation Model for In-context Probabilistic Inference
146. NeurIPS 2026Mosaic: A Benchmark Suite for Differentiable Physics Solvers
147. NeurIPS 2026Multi-Oracle Agreement Reveals the Limits of Self-Consistency Evaluation in RNA Design
148. NeurIPS 2026Multiscale Microenvironment Vector Space Projection for Uncovering Diverse Pathological Biomarker
149. NeurIPS 2026Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
150. NeurIPS 2026MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence

FAQ

How many Applications · chemistry physics and earth sciences papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

3,316 in total: 293 in 2023, 680 in 2024, 1,126 in 2025, 1,217 in 2026.

How many Applications · chemistry physics and earth sciences papers are at NeurIPS 2026?

NeurIPS 2026 has 299 Applications · chemistry physics and earth sciences papers, versus 455 the year before.

How many Applications · chemistry physics and earth sciences papers are at ICLR 2026?

ICLR 2026 has 373 Applications · chemistry physics and earth sciences papers, versus 297 the year before.

How many Applications · chemistry physics and earth sciences papers are at ICML 2026?

ICML 2026 has 441 Applications · chemistry physics and earth sciences papers, versus 287 the year before.

How many Applications · chemistry physics and earth sciences papers are at CVPR 2026?

CVPR 2026 has 104 Applications · chemistry physics and earth sciences papers, versus 87 the year before.

Which conference publishes the most Applications · chemistry physics and earth sciences papers?

NeurIPS, with 1,107 papers from 2023 to 2026.