DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
Paper • 2608.13517 • Published • 33
AI & ML interests
Interpretability-informed control
Recent Activity
View all activity
Papers
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
giannorÂ
submitted a
paper to Daily Papers 26 days ago
giannorÂ
authored a
paper 28 days ago
EvilScriptÂ
updated a
dataset about 2 months ago
lgalkeÂ
authored a
paper 3 months ago
filo362Â
authored a
paper 3 months ago
filo362Â
submitted a
paper to Daily Papers 3 months ago
EvilScriptÂ
authored a
paper 3 months ago
filo362Â
authored a
paper 3 months ago
giannorÂ
authored a
paper 3 months ago
lgalkeÂ
authored a
paper 3 months ago
giannorÂ
authored a
paper 3 months ago
EvilScriptÂ
authored a
paper 3 months ago
giannorÂ
submitted 2
papers to Daily Papers 3 months ago
lgalkeÂ
authored 6
papers 3 months ago
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