Multilingual GSM-Symbolic: What determines capability transfer across languages?
Paper • 2610.03367 • Published • 52
AI & ML interests
Interpretability-informed control
Recent Activity
View all activity
Papers
Selecting The Most Informative Tokens in Natural Language Autoencoders
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
lgalkeÂ
authored a
paper 18 days ago
giannorÂ
authored a
paper 18 days ago
lgalkeÂ
authored 6
papers 22 days ago
Selecting The Most Informative Tokens in Natural Language Autoencoders
Paper • 2609.37040 • Published • 18
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
giannorÂ
authored a
paper 23 days ago
EvilScriptÂ
authored a
paper 23 days ago
EvilScriptÂ
submitted a
paper to Daily Papers 23 days ago
giannorÂ
submitted a
paper to Daily Papers 2 months ago
giannorÂ
authored a
paper 2 months ago
EvilScriptÂ
updated a
dataset 3 months ago
lgalkeÂ
authored a
paper 4 months ago
filo362Â
authored a
paper 4 months ago
filo362Â
submitted a
paper to Daily Papers 4 months ago
EvilScriptÂ
authored a
paper 4 months ago
filo362Â
authored a
paper 4 months ago
giannorÂ
authored a
paper 4 months ago