Jacob Nielsen

JacobBITLABS's activity

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

upvoted a paper 8 days ago

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

Paper • 2606.10747 • Published 16 days ago • 13

upvoted 2 papers 14 days ago

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

Paper • 2606.09707 • Published 16 days ago • 8

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

Paper • 2606.09697 • Published 16 days ago • 7

upvoted a paper 19 days ago

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

Paper • 2606.06286 • Published 21 days ago • 8

upvoted 2 papers 28 days ago

The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment

Paper • 2605.07462 • Published May 8 • 3

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

Paper • 2605.26045 • Published about 1 month ago • 12

updated a dataset about 2 months ago

schneiderkamplab/Edda-Beta

Viewer • Updated Apr 29 • 114 • 14

published a dataset about 2 months ago

schneiderkamplab/Edda-Beta

Viewer • Updated Apr 29 • 114 • 14

updated a dataset about 2 months ago

schneiderkamplab/DA-Refusals

Updated Apr 28 • 9

published a dataset about 2 months ago

schneiderkamplab/DA-Refusals

Updated Apr 28 • 9

updated a dataset 3 months ago

schneiderkamplab/danish-tool-calling-benchmark

Viewer • Updated Apr 6 • 290 • 81 • 1

published a dataset 3 months ago

schneiderkamplab/danish-tool-calling-benchmark

Viewer • Updated Apr 6 • 290 • 81 • 1

updated a dataset 4 months ago

schneiderkamplab/SDU-Daisy

Viewer • Updated Feb 16 • 592 • 61

authored a paper 4 months ago

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

Paper • 2602.08818 • Published Feb 9 • 2

submitted a paper to Daily Papers 4 months ago

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

Paper • 2602.08818 • Published Feb 9 • 2

published a dataset 4 months ago

schneiderkamplab/SDU-Daisy

Viewer • Updated Feb 16 • 592 • 61

New activity in danish-foundation-models/danish-dynaword 5 months ago

Governmentpdfs

🚀 1

2

#112 opened 5 months ago by

JacobBITLABS

authored 2 papers 6 months ago

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?

Paper • 2502.11895 • Published Feb 17, 2025 • 3

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

Paper • 2502.06728 • Published Feb 10, 2025

updated a dataset 9 months ago

JacobBITLABS/Polyp-Box

Viewer • Updated Oct 11, 2025 • 3.96k • 11