Edge Inference papers, 2023–2026

Key findings

• Edge Inference went from 7 papers in 2023 to 28 in 2026, roughly 4.0x in three years.
• NeurIPS publishes the most Edge Inference work: 21 papers from 2023 to 2026, 38% of the four-venue total.
• The fastest-growing overlap is with Federated Edge Inference: papers tagged with both rose from 3 in 2023 to 15 in 2026.
• Among the 5 topics under Hardware and Compilers, it ranks #4 by 2026 paper count; the fastest grower in the group, Chip Design ML, is up 2.3x versus 4.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
• ICML 2026Faster Activation Functions at the Edge for Post-Training Speedups
• ICLR 2026Neural Graduated Assignment for Maximum Common Edge Subgraphs
• CVPR 2026E2-SCI Elastic Edge-Cloud Speculative Decoding via Credit Inertia
• NeurIPS 2025CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
• ICML 2025Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges
• ICLR 2025Grokking at the Edge of Numerical Stability
• CVPR 2025QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
• NeurIPS 2024Stepping on the Edge: Curvature Aware Learning Rate Tuners
• CVPR 20243D Neural Edge Reconstruction
• NeurIPS 2023From Trainable Negative Depth to Edge Heterophily in Graphs
• ICML 2023Second-order regression models exhibit progressive sharpening to the edge of stability
• ICLR 2023Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
• CVPR 2023The Treasure Beneath Multiple Annotations: An Uncertainty-Aware Edge Detector
• NeurIPS 2026Edge of Stability Selectively Shapes Learning Across the Data Distribution
• ICML 2026PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
• ICLR 2026Tequila: Deadzone-free Ternary Quantization for Large Language Models
• CVPR 2026Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation
• NeurIPS 2025Sim-LLM: Optimizing LLM Inference at the Edge through Inter-Task KV Reuse
• ICML 2025Towards characterizing the value of edge embeddings in Graph Neural Networks

All Edge Inference papers

10 papers, page 1 of 1

1. NeurIPS 2026Computer Use at the Edge of the Statistical Precipice
2. NeurIPS 2026Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
3. NeurIPS 2026EAT: Eviction-Aware Training for Long-Context LLM Inference on Edge Devices
4. NeurIPS 2026Edge of Stability Selectively Shapes Learning Across the Data Distribution
5. NeurIPS 2026Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
6. NeurIPS 2026Generalization at the Edge of Stability
7. NeurIPS 2026Geometry-Constrained Kolmogorov–Arnold Networks: Learning Edge Geometry via Banach Duality
8. NeurIPS 2026MedPsy: State‑of‑the‑Art Small Medical Language Models for Efficient Edge Deployment
9. NeurIPS 2026MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenario
10. NeurIPS 2026SGD at the Edge of Stability: The Stochastic Sharpness Gap

FAQ

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

55 in total: 7 in 2023, 6 in 2024, 14 in 2025, 28 in 2026.

How many Edge Inference papers are at NeurIPS 2026?

NeurIPS 2026 has 10 Edge Inference papers, versus 7 the year before.

How many Edge Inference papers are at ICLR 2026?

ICLR 2026 has 3 Edge Inference papers, versus 2 the year before.

How many Edge Inference papers are at ICML 2026?

ICML 2026 has 9 Edge Inference papers, versus 3 the year before.

How many Edge Inference papers are at CVPR 2026?

CVPR 2026 has 6 Edge Inference papers, versus 2 the year before.

Which conference publishes the most Edge Inference papers?

NeurIPS, with 21 papers from 2023 to 2026.