model editing
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Oct 2026
3 papers in the last two months, against 0 in the two before.
Start here
Two papers to read first, in the order they came out- 1Repurposing backdoor trigger mechanisms as probes for adversarial defense in CLIP models
Repurposing adversarial activation shifts as backdoor probes defends CLIP against attacks at test time without retraining.
Oct 2026 - 2Alternative tokenizations can bypass targeted LLM editing and unlearning
Alternative tokenizations of input strings bypass localized modifications in LLMs and recover suppressed knowledge.
Oct 2026
How fast it is moving
Often studied with
test-time adaptationAdapting a deployed model during inference using new data or interactions, without a separate training phase.2 togetherbackdoor attackA hidden trigger in a model causes malicious behavior only when activated, while the model otherwise appears benign.1 togethercontinual learningA learning paradigm where a model sequentially acquires knowledge from multiple tasks without significantly forgetting earlier ones.1 togetherThe papers
Most central to this idea first, not most recent.
- Top Universitycs.CR
Alternative tokenizations can bypass targeted LLM editing and unlearning
Alternative tokenizations of input strings bypass localized modifications in LLMs and recover suppressed knowledge.
National University of Singapore, A*STAR Institute of Advanced Intelligence and Computing, Singapore · Oct 2026
- Research Labcs.CV
Repurposing backdoor trigger mechanisms as probes for adversarial defense in CLIP models
Repurposing adversarial activation shifts as backdoor probes defends CLIP against attacks at test time without retraining.
Xuzhou University of Technology, Chinese Academy of Sciences · Oct 2026
- Big Techcs.LG
Language models' accuracy varies with update timing, not just update counts
The Control Map evaluates test-time updates by recording update histories and separating acquisition, retention, and locality.
Meta AI · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.