Hardware-Aware ML papers, 2023–2026

Key findings

• Hardware-Aware ML went from 173 papers in 2023 to 765 in 2026, roughly 4.4x in three years.
• CVPR publishes the most Hardware-Aware ML work: 479 papers from 2023 to 2026, 31% of the four-venue total.
• The fastest-growing overlap is with Diffusion Models: papers tagged with both rose from 4 in 2023 to 58 in 2026.
• Among the 5 topics under Efficiency and Systems, it ranks #2 by 2026 paper count; the fastest grower in the group, Datasets and Benchmarks, is up 2.1x versus 4.4x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026AcceleGrad#: Adaptive Geometry-Aware Acceleration
• ICML 2026A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
• ICLR 2026Confident Block Diagonal Structure-Aware Invariable Graph Completion for Incomplete Multi-view Clustering
• CVPR 2026ActAvatar Temporally-Aware Precise Action Control for Talking Avatars
• NeurIPS 2025AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
• ICML 2025CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
• ICLR 2025FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
• CVPR 2025A Distractor-Aware Memory for Visual Object Tracking with SAM2
• NeurIPS 2024HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
• ICML 2024A Universal Class of Sharpness-Aware Minimization Algorithms
• ICLR 2024Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
• CVPR 2024Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification
• NeurIPS 2023Affinity-Aware Graph Networks
• ICML 2023A Three-regime Model of Network Pruning
• ICLR 2023$\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks
• CVPR 20233D-Aware Face Swapping
• NeurIPS 2026Accelerating Rectified Flow Models via Trajectory-Aware Caching
• ICML 2026Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
• ICLR 2026Distribution-Aware Multi-Granularity Phase Coding: Towards Lower Conversion Error for Spike-Driven Large Language Models
• CVPR 2026BD-Merging Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning

All Hardware-Aware ML papers

1,524 papers, page 14 of 31

651. NeurIPS 2026MOBO-CAPS: Multi-objective Bayesian Optimization with Cardinality-Aware Pareto Selection
652. NeurIPS 2026Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models
653. NeurIPS 2026Mode-Controlled Policy Optimization: A Geometry-Aware Recipe for LLM Post-Training
654. NeurIPS 2026Model Distribution-Aware Multimodal Dataset Distillation
655. NeurIPS 2026Model-Aware Tokenizer Transfer
656. NeurIPS 2026Module-Aware Optimization for Graph Neural Networks
657. NeurIPS 2026MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
658. NeurIPS 2026MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues
659. NeurIPS 2026Neighbor-Aware Snapshot-Based Temporal Graph Learning
660. NeurIPS 2026No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics
661. NeurIPS 2026No Free Alignment: Observability-Aware Alignment for Multimodal Heterogeneous Learning
662. NeurIPS 2026Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
663. NeurIPS 2026OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
664. NeurIPS 2026On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification
665. NeurIPS 2026Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers
666. NeurIPS 2026Overcoming the Resolution Limit: Significance-Aware Regularization for Intersectional Fairness
667. NeurIPS 2026PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
668. NeurIPS 2026PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
669. NeurIPS 2026Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models
670. NeurIPS 2026Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
671. NeurIPS 2026Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
672. NeurIPS 2026PolySplat: Workload-Regime-Aware Rasterization for 3D Gaussian Splatting
673. NeurIPS 2026Position-aware eXplanation: A Model-Agnostic Framework for Positional Attributions
674. NeurIPS 2026Pref-DetectGPT: Unveiling Machine-Generated Text via Preference-Aware Curvature Measurement
675. NeurIPS 2026PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
676. NeurIPS 2026probly: Uncertainty-Aware Machine Learning
677. NeurIPS 2026Process-Aware LNS for Large-Scale MILP via Context-Enhanced Fine-Tuned LLM-driven Selector
678. NeurIPS 2026Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents
679. NeurIPS 2026Progressive Memory Transformer: Memory-Aware Attention for Time-Series
680. NeurIPS 2026ProQuant: Progressive Quantization-aware Training for Edge MLLMs
681. NeurIPS 2026QuantDemoire: Quantization with Outlier Aware for Image Demoiréing
682. NeurIPS 2026RADAR: Routing Agents via Difficulty-Aware Recovery
683. NeurIPS 2026RAMA: Resistance-Aware Multi-Hop Aggregation Graph Representation Learning for Robust Ethereum Account Classification
684. NeurIPS 2026Readiness-Aware Sample Selection for Noisy Labels with Class Imbalance
685. NeurIPS 2026Reasoning-Aware IRT: Explainable Evaluation of Test-Time Scaling in Reasoning Models
686. NeurIPS 2026Recovering Evolving User Preference State via Adaptive Interaction-aware Representation Correction
687. NeurIPS 2026Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation
688. NeurIPS 2026Relation-Aware Graph Foundation Model
689. NeurIPS 2026Relative Energy Barriers for Copyright-Aware Language Model Adaptation
690. NeurIPS 2026Reliability-Coupled Manifold-Aware Diffusion for Missing-Modality Inference
691. NeurIPS 2026Reliable Federated Multi-View Learning via Conflict-Aware Evidence Calibration
692. NeurIPS 2026ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
693. NeurIPS 2026ResFusion: Medical Image Fusion Driven by Implicit-Forward Diffusion and Time-aware Joint Optimization
694. NeurIPS 2026Resolution-Aware Structural Density Peak Clustering
695. NeurIPS 2026Resource-Aware Parameter-Efficient Model Adaptation for Onboard High-Dimensional Data
696. NeurIPS 2026Rethinking Diffusion Decoding via Structural Commitment
697. NeurIPS 2026Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding
698. NeurIPS 2026ReVMap: Vectorized Global Mapping via Connectivity-Aware Local Map Fusion
699. NeurIPS 2026RigRecon: Efficient Rig-Aware Street Reconstruction via Dual-Path Spatio-Temporal Interaction
700. NeurIPS 2026Risk-Aware Action Repetition via Expected Skip Evaluation

FAQ

How many Hardware-Aware ML papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,524 in total: 173 in 2023, 263 in 2024, 323 in 2025, 765 in 2026.

How many Hardware-Aware ML papers are at NeurIPS 2026?

NeurIPS 2026 has 263 Hardware-Aware ML papers, versus 120 the year before.

How many Hardware-Aware ML papers are at ICLR 2026?

ICLR 2026 has 120 Hardware-Aware ML papers, versus 44 the year before.

How many Hardware-Aware ML papers are at ICML 2026?

ICML 2026 has 186 Hardware-Aware ML papers, versus 72 the year before.

How many Hardware-Aware ML papers are at CVPR 2026?

CVPR 2026 has 196 Hardware-Aware ML papers, versus 87 the year before.

Which conference publishes the most Hardware-Aware ML papers?

CVPR, with 479 papers from 2023 to 2026.