Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs
Large language models (LLMs) achieve strong generation and reasoning performance, but the Transformer architecture incurs high inference cost. Existing acceleration methods often rely on task-specific fine-tuning or training from scratch, increasing adaptation cost and limiting cross-task usability. We present an Adaptive Depth Sparse Framework (AdaDSF) that converts off-the-shelf pre-trained LLMs into depth-sparse models without full retraining. Our key insight is that layers contribute unequally to representation transformation, characterized by the cosine similarity between layer input and
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%mudler/LocalAI →
“Shared author/contributor keys: guo”
- LinkedLinked via arxiv author · 85%Yidu Wu →
“Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs”
- LinkedLinked via arxiv author · 85%Fengxiang Wang →
“Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs”
- LinkedLinked via arxiv author · 85%Kejie Zhao →
“Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs”
- LinkedLinked via arxiv author · 85%Zhangchi Wang →
“Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs”
- LinkedLinked via arxiv author · 85%Qinghai Guo →
“Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs”