conftrace_

sparsification

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

quantization (2) activation editor (1) client-consensus (1) node-level sparsification (1) layerwise orthogonal rotations (1) perplexity gap (1) wall-clock time speed-up (1) balanced (1) conflict-aware (1) parameter differences (1)

Papers

CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging ICML 2025 EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification ICML 2025 La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation ICML 2025 LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression ICLR 2025 Compressing Large Language Models by Joint Sparsification and Quantization ICML 2024 Error Feedback Can Accurately Compress Preconditioners ICML 2024