Information Terra projects document embeddings onto a globe with poles as narrative endpoints, latitude as progress along the geodesic, and longitude as thematic deviation, with density-based land features and a monotone narrative trail, demonstrated on a 540-article Cuban protests corpus.
Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques , pages =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
method 1polarities
use method 1representative citing papers
SafeMoE isolates unsafe knowledge in domain-specific LoRA experts and routes them via a lightweight gate trained on safe responses to produce safer and more informative LLM outputs with zero-shot generalization.
Continual pre-training on a German medical corpus lets 7B models close much of the performance gap with 24B general models on medical benchmarks, though merging introduces some language mixing and verbosity.
DoRA-RBAC experiments on LLaMA-3.1-8B and Mistral-7B across QA benchmarks show geometry-aware merging offers no advantage over Euclidean averaging, indicating adapter interference stems from nonlinear representation interactions rather than parameter-space geometry.
citing papers explorer
-
Information Terra: A Narrative-Anchored Semantic-First Projection of Document Embeddings
Information Terra projects document embeddings onto a globe with poles as narrative endpoints, latitude as progress along the geodesic, and longitude as thematic deviation, with density-based land features and a monotone narrative trail, demonstrated on a 540-article Cuban protests corpus.
-
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
SafeMoE isolates unsafe knowledge in domain-specific LoRA experts and routes them via a lightweight gate trained on safe responses to produce safer and more informative LLM outputs with zero-shot generalization.
-
Can Continual Pre-training Bridge the Performance Gap between General-purpose and Specialized Language Models in the Medical Domain?
Continual pre-training on a German medical corpus lets 7B models close much of the performance gap with 24B general models on medical benchmarks, though merging introduces some language mixing and verbosity.
-
PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry
DoRA-RBAC experiments on LLaMA-3.1-8B and Mistral-7B across QA benchmarks show geometry-aware merging offers no advantage over Euclidean averaging, indicating adapter interference stems from nonlinear representation interactions rather than parameter-space geometry.