← Back to all news
arXiv Machine Learning

H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression

H3DNAS is a hardware‑aware compression framework that operates directly on ONNX computational graphs, eliminating the need for original source code or gradient access. It introduces a Channel Dependency Graph to classify operators and compute a provable compression ceiling, and employs a two‑stage hierarchical search that prunes architectures via L1‑importance channel selection and applies GhostConv mutations to Pareto‑optimal candidates. Applied to 3D point‑cloud models on the ModelNet40 dataset, H3DNAS reduces parameters by up to 65.5% and achieves significant inference speedups with negligible accuracy loss.

Related stories

Hugging Face Trending Papers
Sep 2

H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression

H3DNAS is a hardware‑aware compression framework that operates directly on ONNX computational graphs, eliminating the need for original source code or gradient access. It introduces a Channel Dependency Graph to classify operators and compute a provable compression ceiling, and a two‑stage hierarchical search that prunes architectures via L1‑importance channel selection and applies GhostConv mutations. On the ModelNet40 dataset, H3DNAS achieves significant parameter reductions and inference speedups for PointNet, PointNet++, and PointMLP with minimal accuracy loss.

efficiency
More like this →
arXiv AI
Jun 10

Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters

arXiv:2606. 09924v1 Announce Type: cross Abstract: Deploying deep neural networks on memory-constrained edge accelerators is bottlenecked by per-inference off-chip weight transfer rather than computation: the dense network cannot be retained on-chip, and every parameter must be loaded for every input.

By Kohga Tanaka, Hiroaki Nishi
fine-tuningefficiencymultimodal
More like this →
arXiv Machine Learning
Aug 31

Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates

The paper introduces EMR‑HyperNEAT, an eager multi‑resolution grid approach that replaces the recursive quadtree subdivision of ES‑HyperNEAT with a parallelizable evaluation of all grid positions followed by a variance‑based filter. This reformulation removes sequential dependencies, enabling efficient batching across cores and population members, and reduces computational complexity from <O(4^D)> to <O(4^D/P)>. Experiments show 12–34× GPU speedups at depths 5–7 on XOR and higher solve rates across benchmarks.

By Romain Claret, Michael O'Neill, Paul Cotofrei, Kilian Stoffel
benchmarks
More like this →
arXiv Machine Learning
Sep 22

Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone

The paper introduces Neural Spectral Capacity (NSC), a closed‑form metric derived from the singular‑value spectrum of weight matrices that can be computed solely from a network’s architectural specification. Unlike traditional measures such as #Params and #FLOPs, NSC captures architectural structure (depth, width, head, FFN allocations) and can be evaluated without instantiating the model, data, or gradients. Using a dynamic‑programming solver (NSC‑DP), the authors demonstrate that NSC can efficiently identify architectures that outperform existing training‑free proxies across Transformer and CNN families, and achieve state‑of‑the‑art results in tasks such as WikiText‑103 and commonsense reasoning with LLaMA‑7B. whyItMatters":"NSC provides a fast, architecture‑only proxy that outperforms conventional metrics and training‑free proxies, enabling more effective design and pruning of large models without costly training or data."

By Chenyu Zhu, Ruoyu Zhao, Zhichao Lu
llms
More like this →