Get started
Author

Lukas Galke Poech

Observed name: Poech, Lukas Galke
Observed institution: University of Southern Denmark
OpenAlex ID: A5138298884
Verbalizing Activation Differences with Natural Language Autoencoders
2026 · Núñez, Andrea Blasi, Barmina, Gianluca, et al. · arXiv (Cornell University)
PDF
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
2026 · Stine Lyngsø Beltoft, William Brach, et al. · Proceedings of the AAAI/ACM Conference on AI Ethics and Society
PDF
Curating the Collapse: How Sample-Level Auditing Accelerates Model Collapse in Synthesis of Tabular Data
2026 · William Martin Stevenson, Anne Gerdes, et al. · Proceedings of the AAAI/ACM Conference on AI Ethics and Society
PDF
Multilingual GSM-Symbolic: What determines capability transfer across languages?
2026 · Enevoldsen, Kenneth, Herchert, Riley, et al. · arXiv (Cornell University)
PDF
Selecting The Most Informative Tokens in Natural Language Autoencoders
2026 · Torrielli, Federico, Barmina, Gianluca, et al. · arXiv (Cornell University)
PDF
Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers
2026 · Ahmed, Md Shamim, Poech, Lukas Galke, et al. · arXiv (Cornell University)
PDF
Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures
2026 · Nielsen, Jacob, Namazifard, Danial, et al. · arXiv (Cornell University)
PDF
Mimir: A Sub-2B Hierarchical Reasoning Model Trained on Permissible Data Punches Above Its Weight Class
2026 · Schneider-Kamp, Peter, Nielsen, Jacob, et al. · arXiv (Cornell University)
PDF
The Energy Society: A Simulation Environment for Studying Agent Cooperation under Survival Pressure
2026 · Hansen, Lucas Bergholdt, Torrielli, Federico, et al. · arXiv (Cornell University)
PDF
Influence of Prompt Engineering on Small Language Models for Guarded Query Routing
2026 · Šléher, Richard, Brach, William, et al. · arXiv (Cornell University)
PDF
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
2026 · Tonini, Filippo, Torrielli, Federico, et al. · arXiv (Cornell University)
PDF
BrainSurgery: Reproducible and Flexible Declarative Weight Manipulations for Model Editing and Upcycling
2026 · Barmina, Gianluca, Pirchert, Annemette Broch, et al. · arXiv (Cornell University)
PDF
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
2026 · Barmina, Gianluca, Torrielli, Federico, et al. · arXiv (Cornell University)
PDF
LLMs Can Leak Training Data But Do They Want To? Evaluating Memorization Propensity in LLMs
2026 · Barmina, Gianluca, Schneider-Kamp, Peter, et al. · arXiv (Cornell University)
PDF
Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
2026 · Torrielli, Federico, Schneider-Kamp, Peter, et al. · arXiv (Cornell University)
PDF
ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning
2026 · Ahmed, Md Shamim, Firoozbakht, Farzaneh, et al. · arXiv (Cornell University)
PDF
The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment
2026 · Brach, William, Torrielli, Federico, et al. · arXiv (Cornell University)
PDF
SommBench: Assessing Sommelier Expertise of Language Models
2026 · William Brach, Tomas Bedej, et al. · Language Resources and Evaluation Conference (LREC)
PDF
The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning
2026 · Ahmed, Md Shamim, Dusanic, Maja, et al. · arXiv (Cornell University)
PDF
SommBench: Assessing Sommelier Expertise of Language Models
2026 · Brach, William, Bedej, Tomas, et al. · arXiv (Cornell University)
PDF
FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models
2026 · Pirchert, Annemette Brok, Nielsen, Jacob, et al. · arXiv (Cornell University)
PDF
SDUs DAISY: A Benchmark for Danish Culture
2026 · Nielsen, Jacob, Beltoft, Stine L., et al. · arXiv (Cornell University)
PDF
Training Language Models to Use Prolog as a Tool
2026 · Niklas Mellgren, Peter Schneider-Kamp, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
Rethinking Pivot Programming Languages in Code Language Models
2026 · Andor Diera, Lukas Galke Poech, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Isolating Culture Neurons in Multilingual Large Language Models
2025 · Namazifard, Danial, Poech, Lukas Galke · arXiv (Cornell University)
PDF
Works count: 26
Citation count:
H-index:
I10-index:
Year
Topic
Type