arXiv Machine Learning
Jul 31
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
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.
Related stories
arXiv AI
Aug 7
APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning
arXiv:2608. 05499v1 Announce Type: cross Abstract: Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices.
arXiv Machine Learning
Jun 30
HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers
arXiv:2603. 12222v2 Announce Type: replace-cross Abstract: Vision Transformers require significant computational resources and memory bandwidth, severely limiting their deployment on resource-constraint hardware.
arXiv AI
Jul 28
Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
arXiv:2607. 22583v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities.
arXiv Machine Learning
Jul 9
Protocol Models: Scaling Decentralized Training with Communication-Efficient Model Parallelism
arXiv:2506. 01260v2 Announce Type: replace Abstract: Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks.
arXiv Machine Learning
Jul 10
Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism
arXiv:2506. 01260v3 Announce Type: replace Abstract: Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks.
arXiv AI
Jun 16
Scaling Adaptive Depth with Norm-Agnostic Residual Networks
arXiv:2606. 16112v1 Announce Type: cross Abstract: Residual architectures are ubiquitous in deep learning, but they suffer from a subtle structural limitation: the norm of the residual stream can grow rapidly with depth.
arXiv Machine Learning
Jun 9
BUDDY: BUdget-Driven DYnamic Depth Routing for Adaptive Large Language Model Inference
arXiv:2606. 09514v1 Announce Type: new Abstract: Large language models (LLMs) incur high inference cost due to their depth and parameter scale.
Hugging Face Trending Papers
Aug 6
APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning
Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization address this, but rely on manual, expert choices and on algorithms that are hard to apply across architectures.
arXiv Machine Learning
Jun 29
FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models
arXiv:2606. 27866v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern large models.
arXiv AI
Jul 22
Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression
arXiv:2510. 02345v4 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead.
arXiv AI
2d ago
Breaking Chains with Trees: Model-Parallel Deep Learning with $\mathcal{O}(\log N)$ Time Complexity
arXiv:2606. 21497v2 Announce Type: replace-cross Abstract: Modern deep neural networks are trained using error backpropagation, which requires sequential forward and backward computations across network layers.