conftrace_

expert merging

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) mixture of expert (2) model compression (2) parameter reduction (1) misinformation detection (1) state-of-the-art model (1) reaction generation (1) mixture-of-experts (1) zero-shot language tasks (1) sparse activation (1)

Papers

Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging AAAI 2026 Retraining-free Merging of Sparse MoE via Hierarchical Clustering ICML 2025 DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection ACL 2024 Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy ICLR 2024 SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data NeurIPS 2024