null-space projection
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Nov 2026
3 papers in the last two months, against 0 in the two before.
Start here
Three papers to read first, in the order they came out- 1Null-space activation steering enables training-free LLM unlearning without utility loss
Nullify erases LLM memorized data via null-space activation steering, preserving utility without weight updates.
Oct 2026 - 2Orthogonal Boundary Unlearning preserves benign skills while removing dangerous ones
Restricting unlearning updates to the orthogonal complement of a benign capability subspace removes hazardous dual-use capabilities without degrading benign performance.
Oct 2026 - 3Merging AI models improves by removing conflicting feature directions
Joint Null-Space Projection merges fine-tuned models without data, achieving 89.45% accuracy on eight CLIP tasks by removing cross-task subspace interference.
Nov 2026
How fast it is moving
Often studied with
activation steeringActivation steering modifies a model's internal vector representations during inference to shift behavior, such as editing outputs, removing capabilities, or controlling trust.1 togethermachine unlearningRemoving specific knowledge, behaviors, or concepts from a trained model while preserving overall capability.1 togethersafety alignmentProcess of training models to recognize and refuse harmful requests, ensuring outputs remain safe.1 togetherThe papers
Most central to this idea first, not most recent.
- Academiccs.CV
Merging AI models improves by removing conflicting feature directions
Joint Null-Space Projection merges fine-tuned models without data, achieving 89.45% accuracy on eight CLIP tasks by removing cross-task subspace interference.
Tohoku University · Nov 2026
- Independentcs.LG
Orthogonal Boundary Unlearning preserves benign skills while removing dangerous ones
Restricting unlearning updates to the orthogonal complement of a benign capability subspace removes hazardous dual-use capabilities without degrading benign performance.
Oct 2026
- Top Universitycs.LG
Null-space activation steering enables training-free LLM unlearning without utility loss
Nullify erases LLM memorized data via null-space activation steering, preserving utility without weight updates.
Fudan University, BEDI Cloud · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.