UPMs apply periodic time-varying random invertible transforms to sharded model components in decentralized setups to render cross-time assemblies incoherent while preserving network function and incurring minimal overhead.
Advances in Neural Information Processing Systems , volume =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
LLM-Metrics probes memory in 17 LLMs across 549 2023-2024 CS papers and finds a modest Spearman correlation (rho=0.1495) with citation counts, stronger for 2024 papers.
citing papers explorer
-
Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization
UPMs apply periodic time-varying random invertible transforms to sharded model components in decentralized setups to render cross-time assemblies incoherent while preserving network function and incurring minimal overhead.
-
Understanding the Mechanism of Altruism in Large Language Models
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
-
LLM-Metrics: Measuring Research Impact Through Large Language Model Memory
LLM-Metrics probes memory in 17 LLMs across 549 2023-2024 CS papers and finds a modest Spearman correlation (rho=0.1495) with citation counts, stronger for 2024 papers.