Lukas Galke Poech

lgalke's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 6 hours ago

Multilingual GSM-Symbolic: What determines capability transfer across languages?

Paper • 2610.03367 • Published 4 days ago • 25

upvoted a paper about 11 hours ago

Multilingual GSM-Symbolic: What determines capability transfer across languages?

Paper • 2610.03367 • Published 4 days ago • 25

authored 6 papers 5 days ago

Selecting The Most Informative Tokens in Natural Language Autoencoders

Paper • 2609.37040 • Published 7 days ago • 17

Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures

Paper • 2608.19889 • Published Aug 20

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

Paper • 2608.13517 • Published Aug 13 • 33

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

Paper • 2606.09697 • Published Jun 8 • 7

SDUs DAISY: A Benchmark for Danish Culture

Paper • 2601.19930 • Published Jan 11

Isolating Culture Neurons in Multilingual Large Language Models

Paper • 2508.02241 • Published Nov 11, 2025

upvoted a paper 6 days ago

Selecting The Most Informative Tokens in Natural Language Autoencoders

Paper • 2609.37040 • Published 7 days ago • 17

updated a model 14 days ago

danish-foundation-models/DFM-Mimir

Text Generation • 2B • Updated 12 days ago • 3.82k • 86

liked a model about 2 months ago

danish-foundation-models/DFM-Mimir

Text Generation • 2B • Updated 12 days ago • 3.82k • 86

upvoted a paper about 2 months ago

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

Paper • 2608.13517 • Published Aug 13 • 33

authored a paper 4 months ago

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

Paper • 2606.10747 • Published Jun 9 • 13

upvoted a paper 4 months ago

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

Paper • 2606.10747 • Published Jun 9 • 13

authored a paper 4 months ago

BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling

Paper • 2606.09707 • Published Jun 8 • 8

upvoted a paper 4 months ago

BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling

Paper • 2606.09707 • Published Jun 8 • 8

authored 4 papers 4 months ago

DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes

Paper • 2502.06728 • Published Feb 10, 2025

Are We Really Making Much Progress in Text Classification? A Comparative Review

Paper • 2204.03954 • Published Apr 8, 2022

Efficient Continual Learning for Small Language Models with a Discrete Key-Value Bottleneck

Paper • 2412.08528 • Published Dec 11, 2024

FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models

Paper • 2602.08818 • Published Feb 9 • 3