Explore tweets tagged as #MachineUnlearning
@ponguru
Ponnurangam Kumaraguru “PK”
2 months
📢 🚀 @nptel_official Course Alert! 📢🚀 Super thrilled to co-teach #ResponsibleAI starting July with Profs. { @ravi_iitm & @arunrajkumar485} . Register at & Course website Please spread the word. #ProfGiri #Teaching #Interpretability #MachineUnlearning
Tweet media one
0
9
29
@pr0grammerHumor
programmerHumor
9 months
machineUnlearning.
Tweet media one
0
0
0
@lukeatlife
Luke Cosgrove
21 days
What if AI didn’t just think - but forgot? 🤯.Imagine models designed to unlearn outdated ideas, bad data, and yesterday’s biases - evolving in real-time like living minds. Not just smarter, but wiser. Just a thought. #AI #MachineUnlearning #FutureTech #EthicalAI #NextGenAI.
0
0
1
@bryanklow
Bryan Kian Hsiang Low
2 months
When a company claims that your personal data has been removed from their model, have you ever wondered whether they've indeed done so? 🤔 . If a new paper on arXiv claims that its proposed #MachineUnlearning algorithm can unlearn your personal data from an #LLM, how do we know
0
1
4
@bryanklow
Bryan Kian Hsiang Low
4 months
(1) Traditional utility-centric #MachineUnlearning metrics rely on referencing a retrained model, which is prohibitively expensive😨. These metrics also struggle when the forget & retain sets contain similar data, which is a common scenario in realistic deployments😖. (2/n).#LLM
Tweet media one
1
0
0
@bryanklow
Bryan Kian Hsiang Low
4 months
(3) WaterDrum embeds robust watermarks into text data & measures the #watermark strength after #MachineUnlearning:.- It produces calibrated scores without referencing the retrained model;.- The signal is orthogonal to model performance & applicable even with similar data. (4/n)
Tweet media one
1
0
1
@CognaptusBlog
o
1 month
Forgetting by Remembering: A Smarter Path to Machine Unlearning #machineunlearning #privacy #influencefunctions #incrementallearning #AIethics.
0
0
0
@bimedotcom
BusinessIntelligence
2 years
Tweet media one
Tweet media two
Tweet media three
Tweet media four
4
34
48
@isced_
ISCed
2 years
#MachineUnlearning- Learning to Forget - iHLS
Tweet media one
0
0
0
@drund
Drund
2 months
A look at how a new framework makes #MachineUnlearning faster, more practical, and privacy-compliant for real-world #AI systems. @helpnetsecurity .
0
0
0
@CognaptusBlog
o
2 months
Collapse to Forget: Turning Model Collapse into a Privacy Feature for LLMs #machineunlearning #privacy #LLMs #modelcollapse #compliance #AIgovernance.
0
0
0
@juandoming
juandoming
2 years
@juandoming EL MACHINE UNLEARNING EN LA EDUCACIÓN DISRUPTIVA:.#machineUnlearning #Educaciondisruptiva #educación #algoritmos #IA #desaprendizaje
Tweet media one
1
0
1
@DPrasanthNair
D Prasanth Nair
2 years
Interesting to see.#machineUnlearning as a future #technology . @Gartner_inc
Tweet media one
0
0
3
@CognaptusBlog
o
2 months
The Sink That Remembers: Solving LLM Memorization Without Forgetting Everything Else #LLMtraining #AIsafety #machineunlearning #dataprivacy #MemSinks.
0
0
0
@woojinrad
Woojin Kim
1 year
Machine Unlearning in Generative AI: A Survey . #MachineUnlearning #GenAI.👉
Tweet media one
0
0
0
@_sungmin_cha
Sungmin Cha
7 months
I am happy to share that our paper, "Towards Robust and Cost-Efficient Knowledge Unlearning for Large Language Models", has been accepted to #ICLR2025! Stay tuned for the camera-ready version and the code release! #MachineUnlearning #LLMs
Tweet media one
1
3
25
@bryanklow
Bryan Kian Hsiang Low
4 months
Introducing WaterDrum🛢️, the first data-centric #LLM #unlearning metric that leverages robust text #watermarking💧to provide an effective, practical, and resilient way to evaluate LLM unlearning performance😉! (1/n). #MachineUnlearning #LLMs
Tweet media one
1
3
19
@sourajitCS
SOURAJIT SAHA
13 days
🎉 Proud to share that Side Effects of Erasing Concepts from Diffusion Models was accepted to EMNLP 2025 (Findings). #EMNLP2025 #MachineUnlearning #ConceptErasure.
@_Shaswati
Shaswati
13 days
🚨 Our paper “Side Effects of Erasing Concepts from Diffusion Models” has been accepted to EMNLP 2025 (Findings)! #EMNLP2025.We investigate the vulnerabilities of Concept Erasure Techniques (CETs).Big shoutout to my amazing collaborators @sourajitCS @manasgaur90 @trgokhale .1/n.
0
0
1