UI Understanding papers, 2023–2026

Key findings

• UI Understanding went from 15 papers in 2023 to 27 in 2026, roughly 1.8x in three years.
• NeurIPS publishes the most UI Understanding work: 23 papers from 2023 to 2026, 30% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 0 in 2023 to 9 in 2026.
• Among the 5 topics under Education and HCI, it ranks #3 by 2026 paper count; the fastest grower in the group, User Modeling, is up 2.9x versus 1.8x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering
• ICML 2026A Single Layer to Explain Them All: Understanding Massive Values in Large Language Models
• ICLR 2026Towards Understanding the Shape of Representations in Protein Language Models
• CVPR 2026RISE Single Static Radar-based Indoor Scene Understanding
• NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
• ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
• ICLR 2025Toward Understanding In-context vs. In-weight Learning
• CVPR 2025MP-GUI: Modality Perception with MLLMs for GUI Understanding
• ICML 2024CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents
• ICLR 2024Understanding In-Context Learning from Repetitions
• CVPR 2024PanoContext-Former: Panoramic Total Scene Understanding with a Transformer
• NeurIPS 2023Understanding the detrimental class-level effects of data augmentation
• ICML 2023How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding
• ICLR 2023First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains
• CVPR 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
• NeurIPS 2026Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
• ICML 2026Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions
• ICLR 2026Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods
• CVPR 20264D-RGPT Toward Region-level 4D Understanding via Perceptual Distillation
• NeurIPS 2025Towards a Geometric Understanding of Tensor Learning via the t-Product

All UI Understanding papers

19 papers, page 1 of 1

1. CVPR 2025FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding
2. CVPR 2025GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration
3. CVPR 2025HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
4. CVPR 2025MP-GUI: Modality Perception with MLLMs for GUI Understanding
5. CVPR 2025PEACE: Empowering Geologic Map Holistic Understanding with MLLMs
6. CVPR 2025SpiritSight Agent: Advanced GUI Agent with One Look
7. ICLR 2025Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
8. ICLR 2025Toward Understanding In-context vs. In-weight Learning
9. ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
10. ICML 2025Position: AI Agents Need Authenticated Delegation
11. ICML 2025Understanding Mode Connectivity via Parameter Space Symmetry
12. ICML 2025Understanding Nonlinear Implicit Bias via Region Counts in Input Space
13. ICML 2025Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra
14. NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
15. NeurIPS 2025Towards a Geometric Understanding of Tensor Learning via the t-Product
16. NeurIPS 2025Towards Understanding Transformers in Learning Random Walks
17. NeurIPS 2025Understanding Adam Requires Better Rotation Dependent Assumptions
18. NeurIPS 2025Understanding Bias Terms in Neural Representations
19. NeurIPS 2025Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability

FAQ

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

77 in total: 15 in 2023, 16 in 2024, 19 in 2025, 27 in 2026.

How many UI Understanding papers are at NeurIPS 2026?

NeurIPS 2026 has 16 UI Understanding papers, versus 6 the year before.

How many UI Understanding papers are at ICLR 2026?

ICLR 2026 has 2 UI Understanding papers, versus 2 the year before.

How many UI Understanding papers are at ICML 2026?

ICML 2026 has 2 UI Understanding papers, versus 5 the year before.

How many UI Understanding papers are at CVPR 2026?

CVPR 2026 has 7 UI Understanding papers, versus 6 the year before.

Which conference publishes the most UI Understanding papers?

NeurIPS, with 23 papers from 2023 to 2026.