Top Tweets for #machineUnlearning
A week after I talked about GatherEasy at UvAโs IRLab, future SEA Talks will now also be listed on GatherEasy! ๐ Thanks @mdr & @yubaotang2024 for the support!
Next up: Machine Unlearning, this Friday ๐
https://t.co/Q1DghWstBq
#GatherEasy #MachineUnlearning #AmsterdamTech
How hard can #MachineUnlearning be? ๐ตโ๐ซ
Tap on the image to find out!
Come check us out #ICML2026!
๐ Join us (@chenjiangw @xinyuan3142 @RachaelSim2 Zhengyuan Liu, Nancy Chen @bryanklow) at our @icmlconf poster!
๐
Date: Wed July 8
โฐ 2:30-4:15 PM
๐ข Location: Hall A #3116
๐ Paper: https://t.co/oYZliwFlBF
๐ป Code: https://t.co/0qQOKTukdC
How hard can #MachineUnlearning be? ๐ตโ๐ซ
Tap on the image to find out!
Come check us out #ICML2026!
๐ Join us (@chenjiangw @xinyuan3142 @RachaelSim2 Zhengyuan Liu, Nancy Chen @bryanklow) at our @icmlconf poster!
๐
Date: Wed July 8
โฐ 2:30-4:15 PM
๐ข Location: Hall A #3116
๐ Paper: https://t.co/oYZliwFlBF
๐ป Code: https://t.co/0qQOKTukdC
#MachineUnlearning is notoriously difficult, but how hard is it to unlearn different data?
In our #ICML2026 paper, we show that unlearning is harder when the forget and retain data are more similar.
Introducing HAMU: a hardness-aware unlearning algorithm that
1. quantifies unlearning hardness,
2. updates the model based on per-iteration hardness,
3. stops when better forgetting would inevitably hurt retain utility, and
4. is scalable and practical for large, non-convex models such as LLMs.
HAMU achieves stronger retainโforget trade-offs than existing methods across image and text tasks.
๐ Join us (@chenjiangw @xinyuan3142 @RachaelSim2 Zhengyuan Liu, Nancy Chen @bryanklow) at our @icmlconf poster!
๐
Date: Wed July 8
โฐ Time: 2:30-4:15 PM
๐ข Location: Hall A #3116
๐ Paper: https://t.co/oYZliwENM7
๐ป Code: https://t.co/0qQOKTtMo4
#MachineUnlearning is notoriously difficult, but how hard is it to unlearn different data?
In our #ICML2026 paper, we show that unlearning is harder when the forget and retain data are more similar.
Introducing HAMU: a hardness-aware unlearning algorithm that
1. quantifies unlearning hardness,
2. updates the model based on per-iteration hardness,
3. stops when better forgetting would inevitably hurt retain utility, and
4. is scalable and practical for large, non-convex models such as LLMs.
HAMU achieves stronger retainโforget trade-offs than existing methods across image and text tasks.
๐ Join us (@chenjiangw @xinyuan3142 @RachaelSim2 Zhengyuan Liu, Nancy Chen @bryanklow) at our @icmlconf poster!
๐
Date: Wed July 8
โฐ Time: 2:30-4:15 PM
๐ข Location: Hall A #3116
๐ Paper: https://t.co/oYZliwENM7
๐ป Code: https://t.co/0qQOKTtMo4
๐ผ ๐ต ๐ถ... Time to party @icmlconf #ICML2026? Let's go! Wait, I'm the last to depart from ๐ธ๐ฌ ???
Don't miss out on the ๐๐๐ ๐ฑ ๐๐๐ง๐ ๐๐ญ๐ซ๐๐๐ญ ๐๐ฎ๐ฆ๐ฆ๐ข๐ญ ๐จ๐ง ๐๐๐ฅ๐-๐๐ฏ๐จ๐ฅ๐ฎ๐ญ๐ข๐จ๐ง ๐จ๐ ๐๐ ๐๐ ๐๐ง๐ญ๐ฌ ๐๐ง๐ ๐๐ฎ๐ฅ๐ญ๐ข๐๐ ๐๐ง๐ญ ๐๐ฒ๐ฌ๐ญ๐๐ฆ๐ฌ (9 Jul)! See link below:
https://t.co/0mHbUKNEFD
#LLMs #AgenticAI #AIAgents #AgenticMemory #DataSelection #ShapleyValue #MachineUnlearning #BayesianOptimization #SpeculativeDecoding
[1/5] ๐จ #MachineUnlearning aims to remove certain data from an #LLM. Current methods rely on maximizing prediction loss on the forget set, but they often break the model's utility entirely. ๐ฑ
๐ค Dare you forget my data without causing the model to spit out gibberish? In our new #ICML2026 paper, we completely flip the script with DareU by introducing a brand new unlearning objective.
๐ Paper "De-attribute to Forget for LLM Unlearning" (๐https://t.co/iMkFAct8eK) - co-led by @lululu0082, Jiabao Pan & our wonderful collaborators @RachaelSim2, See-Kiong Ng, Anthony Kum Hoe Tung, @bryanklow โค๏ธ.
Catch our poster @icmlconf on 8 Jul 2:30 PM Hall A #3216! ๐ฐ๐ท
See the thread below ๐งต๐
๐ผ ๐ต ๐ถ... Time to party @icmlconf #ICML2026? Let's go! Wait, I'm the last to depart from ๐ธ๐ฌ ???
Don't miss out on the ๐๐๐ ๐ฑ ๐๐๐ง๐ ๐๐ญ๐ซ๐๐๐ญ ๐๐ฎ๐ฆ๐ฆ๐ข๐ญ ๐จ๐ง ๐๐๐ฅ๐-๐๐ฏ๐จ๐ฅ๐ฎ๐ญ๐ข๐จ๐ง ๐จ๐ ๐๐ ๐๐ ๐๐ง๐ญ๐ฌ ๐๐ง๐ ๐๐ฎ๐ฅ๐ญ๐ข๐๐ ๐๐ง๐ญ ๐๐ฒ๐ฌ๐ญ๐๐ฆ๐ฌ (9 Jul)! See link below:
https://t.co/0mHbUKNEFD
#LLMs #AgenticAI #AIAgents #AgenticMemory #DataSelection #ShapleyValue #MachineUnlearning #BayesianOptimization #SpeculativeDecoding
Public posts, AI training, and the right to be forgotten: why your decade-old tweets may still be influencing AI systems today.
#dataprivacy #machineunlearning...Show more
๐ข๐ NPTEL Course Alert 2026!
Excited to co-teach #ResponsibleAI this July with Profs. @ravi_iitm @arunrajkumar485 ! ๐
Covers: #Fairness #transparency #Interpretability #MachineUnlearning & more.
Register: https://t.co/H8tUeW9HHY
#CFBR #ProfGiri #Teaching @nptel_official
Everything is ready for MUV @CVPR 2026! ๐ง โ
Join us in Denver on June 3 for the Machine Unlearning for Vision Workshop.
๐ Room 1AB
๐ Afternoon session
Program, speakers, and details:
https://t.co/QEZkX9tNnj
#CVPR2026 #MachineUnlearning #ComputerVision #AI
Presenting Today at #AISTATS2026
An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations (1/3)
#MachineUnlearning #NeuralCollapse
๐งต [6/5] It was nice to know from the industry folks visiting our poster yesterday that #MachineUnlearning has many practical use cases! Also attracted many 2nd order optimization folks looking for use cases, such as unlearning. @lululu0082
![bryanklow's tweet photo. ๐งต [6/5] It was nice to know from the industry folks visiting our poster yesterday that #MachineUnlearning has many practical use cases! Also attracted many 2nd order optimization folks looking for use cases, such as unlearning. @lululu0082 https://t.co/V2x1kjg4Vd](https://pbs.twimg.com/media/HGrZM69WgAAgU9T.jpg)
![bryanklow's tweet photo. ๐งต [6/5] It was nice to know from the industry folks visiting our poster yesterday that #MachineUnlearning has many practical use cases! Also attracted many 2nd order optimization folks looking for use cases, such as unlearning. @lululu0082 https://t.co/V2x1kjg4Vd](https://pbs.twimg.com/media/HGrZM69WIAA7ohM.jpg)
Interested in #MechanisticInterpretability #MachineUnlearning #PrivacyLeakage #MultiAgentSafety and more? ๐ค๐
Join CS7.405 Responsible & Safe AI Systems course project posters (21!) ๐โจ
๐๏ธ 25 April โฐ 3:30 PM @iiit_hyderabad
Open to allโฆ do join ๐๐ฝ #ResponsibleAI #SafeAI
[1/5] Making AI โforgetโ without damaging its โbrainโ ๐ง ๐ป is notoriously hard, but vital!
An AI model provider should give users the right to โownโ and remove their data from its AI model in real time ๐ while retaining its performance. This is the core of โ#MachineUnlearningโ.
In our #ICLR2026 paper, we put one of the competitive unlearning algorithms known as Newton unlearning to the test, reveal where it fails on modern AI models (#LLMs included!), and turn those failures around with a rigorous fix ๐ ๏ธโ
.
Ready for us to spill the tea? More below โ ๐งต๐
=============
๐๐Paper โHow to Cure Newton for Unlearning Neural Networks? An Empirical Study from the Hessian Perspectiveโ (๐https://t.co/NAv5EsJUjx) โ a joint work with @nhungbui1299 @lululu0082 @RachaelSim2 See-Kiong Ng.
๐
๐ฃ๏ธMeet us @iclr_conf ๐ง๐ท Poster Session 2 Thurs Apr 23 3:15PM Pavilion 4 P4-#5304.
When a company claims that your personal data has been removed from their model, have you ever wondered whether they've indeed done so? ๐ค
If a new paper on arXiv claims that its proposed #MachineUnlearning algorithm can unlearn your personal data from an #LLM, how do we know if it can indeed do so?
๐ข๏ธWaterDrum is the first data-centric LLM unlearning metric based on watermarking that is calibrated, requires no retraining, works for blackbox models and when forget/retain sets have similar data.
Let the (Water)Drums roll at Rio! @iclr_conf #ICLR2026
Introducing WaterDrum๐ข๏ธ, the first data-centric #LLM #unlearning metric that leverages robust text #watermarking๐งto provide an effective, practical, and resilient way to evaluate LLM unlearning performance๐! (1/n)
#MachineUnlearning #LLMs
Is your unlearned model truly forgetting, or is it just hiding the evidence? For years, #MachineUnlearning evaluation has relied heavily onย logit-based metricsย (like accuracy). But in our new paper, "Are we truly forgetting? A critical re-examination of machine unlearning evaluation protocols", accepted toย #EAAI, we found that these metrics can be misleading.
We observed that while models appear to "forget" based on their outputs, they often merely modify the classifier head while preserving the original knowledge in theirย feature representations. Essentially, the model isn't unlearning; it's taking a shortcut.
To address this, we propose a holistic benchmark framework:
1. Representation-based metrics:๏ฟฝ๏ฟฝUsing CKA and k-NN to rigorously verify if the feature space has truly diverged from the original model.
2. Top Class-wise forgetting:ย A novel large-scale scenario where forgetting targets are semantically similar to downstream tasks, preventing the model from relying on residual knowledge.
Huge thanks to my co-authors Yongwoo Kim and Donghyun Kim.
Full paper available here: https://t.co/ALBvL9z3p6
Github code: https://t.co/b2iWYfcc9c
If you are interested in a rigorous reality check for #MachineUnlearning, please stop by our poster at the #NeurIPS2025 Workshop!
Current unlearning benchmarks often rely on reference-specific metrics, which can hide the truth about a model's retained knowledge.
We propose FADE (Functional Alignment for Distributional Equivalence), a new metric that measures how well an unlearned model aligns with a "retain-only" model that never saw the unwanted data.
- Paper: Reference-Specific Metrics Can Hide the Truth: A Reality Check (https://t.co/WHFRAVNkRO)
- Workshop: Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling (Sunday, Dec 7)
Participated at the India-France AI Policy Roundtable on bilateral AI collaboration and societal impact. Also, got the opportunity to share our machine unlearning work to Ms. Anne Bouverot
#IndiaAI #MachineUnlearning #AIPolicy @PrinSciAdvGoI @iiscbangalore @BangaloreFrance
The Office of @PrinSciAdvGoI, in collaboration with the @iiscbangalore and @BangaloreFrance, organised the Third IndiaโFrance AI Policy Roundtable on 7th November 2025 at the Council Chamber, IISc Bengaluru. The roundtable is a part of the pre-summit event for the upcoming AI Impact Summit 2026, being hosted by India in February.
The session was co-chaired by Ms. Anne Bouverot, Special Envoy of the President of the French Republic for AI, and Mr. @amit_a_shukla, Joint Secretary, Cyber Diplomacy Division, @MEAIndia.
This Track 1.5 dialogue continues the series of roundtables initiated during the Technology Dialogue 2025, at IISc Bengaluru, as a side event to the earlier AI Action Summit held in Paris on 10th Feb 2025, and reinforces the sustained collaboration between the two nations on AI policy and innovation.
The roundtable discussions will contribute valuable insights for the upcoming AI Impact Summit 2026 as well as the IndiaโFrance Year of Innovation 2026.
Read the PIB Press Release at: https://t.co/QqT2njVEvW
@PMOIndia @FranceinIndia @OfficialINDIAai @_DigitalIndia @PreetiBanzal @kavitabha @emilien @SabharwalAnkush @Ashhereon @jyotij0shi @MayankVatsa3 @danish037 @animesh07731362
๐ Proud to share that Side Effects of Erasing Concepts from Diffusion Models was accepted to EMNLP 2025 (Findings).
#EMNLP2025 #MachineUnlearning #ConceptErasure
๐จ Our paper โSide Effects of Erasing Concepts from Diffusion Modelsโ 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
เคฎเคนเคคเฅเคคเฅเคตเคชเฅเคฐเฅเคฃ เคถเคฌเฅเคฆเคพเคตเคฒเฅ:
เคฎเคถเฅเคจ เค
เคจเคฒเคฐเฅเคจเคฟเคเค (Machine Unlearning)
https://t.co/YkuLDlST2j
#MachineUnlearning #importantterminology #importantwords #prelims #importantconcepts #India #upsc #prelimssexam #pcs #sanskritiias
When a company claims that your personal data has been removed from their model, have you ever wondered whether they've indeed done so? ๐ค
If a new paper on arXiv claims that its proposed #MachineUnlearning algorithm can unlearn your personal data from an #LLM, how do we know if it can indeed do so?
๐ข๏ธWaterDrum is the first data-centric LLM unlearning metric based on watermarking that is calibrated, requires no retraining, works for blackbox models and when forget/retain sets have similar data.
Find out more about Waterdrum from @greglau at our poster today (18 July) in the #ICML2025 Machine Unlearning for #GenerativeAI (MUGen @icmlconf) workshop during 3-3.45pm in West Meeting Room 202-204!
Joint work with @lululu0082 xinyuan @greglau nhung @RachaelSim2 fanyu chuansheng seekiong.
Last Seen Hashtags on Sotwe
incesto padre y hija
Seen from Mexico
dog girl sex
Seen from Pakistan
pasifparlak
Seen from Turkey
minichat()()*()()******************** filter:videos
Seen from Chile
IndianLesbianSex
naruto #hentai video
Seen from Singapore
minichat
Seen from Canada
momsonn
Seen from United States
smno(*)**
Seen from United States
samanthahot
Seen from India
Most Popular Users
Elon Musk 
@elonmusk
241.7M followers
Barack Obama
@barackobama
119M followers
Cristiano Ronaldo
@cristiano
114.4M followers
Donald J. Trump
@realdonaldtrump
111.9M followers
Narendra Modi
@narendramodi
107.2M followers
Rihanna
@rihanna
98.7M followers
NASA
@nasa
92.4M followers
Justin Bieber
@justinbieber
91.8M followers
KATY PERRY
@katyperry
90M followers
Taylor Swift
@taylorswift13
83.9M followers
Lady Gaga
@ladygaga
75.4M followers
Virat Kohli
@imvkohli
73.3M followers
Kim Kardashian
@kimkardashian
70.9M followers
YouTube
@youtube
68.8M followers
Neymar Jr
@neymarjr
66.3M followers
Bill Gates
@billgates
65.1M followers
Selena Gomez
@selenagomez
63M followers
The Ellen Show
@theellenshow
62.3M followers
CNN
@cnn
61.8M followers
X
@x
60.7M followers