conftrace_

model reconstruction

5 papers

Explore in graph

Co-occurring keywords

shapley value (206) missing datum (111) expert pruning (10) expert diversity (2) rademacher observation (2) missing observation (4) silent-state model (1) large language model (13587) contribution evaluation (2) knowledge amalgamation (7)

Papers

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts ACL 2025
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory NIPS 2024
Learning Hidden Markov Models When the Locations of Missing Observations are Unknown ICML 2023
SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning NIPS 2023
Rademacher Observations, Private Data, and Boosting ICML 2015