DepthVAR adaptively allocates per-token computational depth in VAR models using a cyclic rotated scheduler and dynamic layer masking to achieve 2.3-3.1x inference speedup with minimal quality loss.
arXiv preprint arXiv:2307.02628 , year=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
PAC-Bayesian bounds for early-exit networks depend on expected depth E[D] and exit-depth entropy H(D), with sample complexity O((E[D] · d + H(D))/ε²) and provable advantages over fixed-depth networks under stated conditions.
VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.
N-vium achieves 57.9% wall-clock speedup over matched standard transformers at no perplexity cost by mixing exact predictions from multiple model depths.
The paper surveys energy efficiency strategies for Agentic AI inference by proposing a new accounting framework and taxonomy that spans model simplification, computation control, input optimization, and cross-layer co-design with wireless networks.
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
citing papers explorer
-
Depth Adaptive Efficient Visual Autoregressive Modeling
DepthVAR adaptively allocates per-token computational depth in VAR models using a cyclic rotated scheduler and dynamic layer masking to achieve 2.3-3.1x inference speedup with minimal quality loss.
-
When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth
PAC-Bayesian bounds for early-exit networks depend on expected depth E[D] and exit-depth entropy H(D), with sample complexity O((E[D] · d + H(D))/ε²) and provable advantages over fixed-depth networks under stated conditions.
-
VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.
-
N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation
N-vium achieves 57.9% wall-clock speedup over matched standard transformers at no perplexity cost by mixing exact predictions from multiple model depths.
-
Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey
The paper surveys energy efficiency strategies for Agentic AI inference by proposing a new accounting framework and taxonomy that spans model simplification, computation control, input optimization, and cross-layer co-design with wireless networks.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
-
Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
- River-LLM: Large Language Model Seamless Exit Based on KV Share