H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression
cs.LG, cs.AR, cs.NE
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/ClarityLab-Org/h3dnas
Terminology
Sources
- Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning
- HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA
- ONNXPruner: ONNX-Based General Model Pruning Adapter
- Exploring Vision Neural Network Pruning via Screening Methodology
- Structurally Prune Anything: Any Architecture, Any Framework, Any Time
- Using binary string to prove the Collatz conjecture
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- YOLOv3: An Incremental Improvement
- Sector Rotation by Factor Model and Fundamental Analysis
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks