Selecting The Most Informative Tokens in Natural Language Autoencoders
Paper • 2609.37040 • Published • 12
AI & ML interests
Interpretability of Language Models and Multi-Agent Safety
Recent Activity
View all activity
lgalke
authored 6
papers about 3 hours ago
Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures
Paper • 2608.19889 • Published
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
Paper • 2608.13517 • Published • 33
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Paper • 2606.09697 • Published • 7
SDUs DAISY: A Benchmark for Danish Culture
Paper • 2601.19930 • Published
Isolating Culture Neurons in Multilingual Large Language Models
Paper • 2508.02241 • Published
lgalke
authored 13
papers 4 months ago
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
Paper • 2606.10747 • Published • 13
BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling
Paper • 2606.09707 • Published • 8
DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes
Paper • 2502.06728 • Published
Are We Really Making Much Progress in Text Classification? A Comparative Review
Paper • 2204.03954 • Published
Efficient Continual Learning for Small Language Models with a Discrete Key-Value Bottleneck
Paper • 2412.08528 • Published
FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models
Paper • 2602.08818 • Published • 3
DaLA: Danish Linguistic Acceptability Evaluation Guided by Real World Errors
Paper • 2512.04799 • Published
SommBench: Assessing Sommelier Expertise of Language Models
Paper • 2603.12117 • Published • 1
Training Language Models to Use Prolog as a Tool
Paper • 2512.07407 • Published
The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment
Paper • 2605.07462 • Published • 3
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
Paper • 2605.31170 • Published • 8
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
Paper • 2606.06286 • Published • 8
Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
Paper • 2605.26045 • Published • 9
lgalke
authored a
paper 11 months ago