February 8, 2025 at 3:35 PM
We were thrilled to host @mtutek.bsky.social at our lab last week.
His talk "From Internals to Integrity: How Insights into Transformer LMs Improve Safety, Interpretability, and Explanation Faithfulness" led to great discussions! 👏
#Transformers #AISafety #ExplainableAI #MLResearch #NLProc
His talk "From Internals to Integrity: How Insights into Transformer LMs Improve Safety, Interpretability, and Explanation Faithfulness" led to great discussions! 👏
#Transformers #AISafety #ExplainableAI #MLResearch #NLProc
February 24, 2026 at 2:05 PM
We were thrilled to host @mtutek.bsky.social at our lab last week.
His talk "From Internals to Integrity: How Insights into Transformer LMs Improve Safety, Interpretability, and Explanation Faithfulness" led to great discussions! 👏
#Transformers #AISafety #ExplainableAI #MLResearch #NLProc
His talk "From Internals to Integrity: How Insights into Transformer LMs Improve Safety, Interpretability, and Explanation Faithfulness" led to great discussions! 👏
#Transformers #AISafety #ExplainableAI #MLResearch #NLProc
if it doesn't have pretty pictures I don't want it.
#mlresearch #academicsky #machinelearning #research
#mlresearch #academicsky #machinelearning #research
February 9, 2025 at 6:02 PM
if it doesn't have pretty pictures I don't want it.
#mlresearch #academicsky #machinelearning #research
#mlresearch #academicsky #machinelearning #research
I see so many new people joining BlueSky! Super excited to see this place growing. Looking forward to a stable #ml and #mlresearch community here 🤖
November 13, 2024 at 9:53 PM
I see so many new people joining BlueSky! Super excited to see this place growing. Looking forward to a stable #ml and #mlresearch community here 🤖
🚀 We're hiring a Research Scientist, Machine Learning Research (MLR), Barcelona ☀️
👉 Apply here: jobs.apple.com/en-us/detail...
#MachineLearning #MLResearch #AI #Hiring #Apple #Barcelona #ResearchScientist #DeepLearning
👉 Apply here: jobs.apple.com/en-us/detail...
#MachineLearning #MLResearch #AI #Hiring #Apple #Barcelona #ResearchScientist #DeepLearning
AIML - Machine Learning Researcher - MLR - Jobs - Careers at Apple
Apply for a AIML - Machine Learning Researcher - MLR job at Apple. Read about the role and find out if it’s right for you.
jobs.apple.com
June 29, 2026 at 2:31 PM
🚀 We're hiring a Research Scientist, Machine Learning Research (MLR), Barcelona ☀️
👉 Apply here: jobs.apple.com/en-us/detail...
#MachineLearning #MLResearch #AI #Hiring #Apple #Barcelona #ResearchScientist #DeepLearning
👉 Apply here: jobs.apple.com/en-us/detail...
#MachineLearning #MLResearch #AI #Hiring #Apple #Barcelona #ResearchScientist #DeepLearning
[AI] Propose, Solve, Verify: Self-Play Through Formal Verification
A Wilf, P Aggarwal, B Parno, D Fried... [CMU] (2025)
arxiv.org/abs/2512.18160
#AI
#MachineLearning
#DeepLearning
#ArtificialIntelligence
#DataScience
#NeuralNetworks
#MLResearch
#AIResearch
A Wilf, P Aggarwal, B Parno, D Fried... [CMU] (2025)
arxiv.org/abs/2512.18160
#AI
#MachineLearning
#DeepLearning
#ArtificialIntelligence
#DataScience
#NeuralNetworks
#MLResearch
#AIResearch
December 25, 2025 at 1:24 PM
[AI] Propose, Solve, Verify: Self-Play Through Formal Verification
A Wilf, P Aggarwal, B Parno, D Fried... [CMU] (2025)
arxiv.org/abs/2512.18160
#AI
#MachineLearning
#DeepLearning
#ArtificialIntelligence
#DataScience
#NeuralNetworks
#MLResearch
#AIResearch
A Wilf, P Aggarwal, B Parno, D Fried... [CMU] (2025)
arxiv.org/abs/2512.18160
#AI
#MachineLearning
#DeepLearning
#ArtificialIntelligence
#DataScience
#NeuralNetworks
#MLResearch
#AIResearch
🎉Hats off to Dr. Stefan Blücher! He defended his PhD yesterday🎓
Thesis: "Towards Scalable and Transparent ML Algorithms with Applications in Explainable AI and Quantum Chemistry"
Thanks to all supporters!
#XAI #QuantumML #MLResearch #PhDCompleted @tuberlin.bsky.social @fraunhoferhhi.bsky.social
Thesis: "Towards Scalable and Transparent ML Algorithms with Applications in Explainable AI and Quantum Chemistry"
Thanks to all supporters!
#XAI #QuantumML #MLResearch #PhDCompleted @tuberlin.bsky.social @fraunhoferhhi.bsky.social
May 13, 2025 at 3:41 PM
🎉Hats off to Dr. Stefan Blücher! He defended his PhD yesterday🎓
Thesis: "Towards Scalable and Transparent ML Algorithms with Applications in Explainable AI and Quantum Chemistry"
Thanks to all supporters!
#XAI #QuantumML #MLResearch #PhDCompleted @tuberlin.bsky.social @fraunhoferhhi.bsky.social
Thesis: "Towards Scalable and Transparent ML Algorithms with Applications in Explainable AI and Quantum Chemistry"
Thanks to all supporters!
#XAI #QuantumML #MLResearch #PhDCompleted @tuberlin.bsky.social @fraunhoferhhi.bsky.social
September 16, 2025 at 5:14 PM
Interesting paper on fairness in remote proctoring decisions for the Duolingo English Test. It also reveals a bit about the logistics of remote proctoring, including proctors based in the US, Philippines, and India.
raw.githubusercontent.com/mlresearch/v...
raw.githubusercontent.com/mlresearch/v...
raw.githubusercontent.com
May 23, 2025 at 1:58 AM
Interesting paper on fairness in remote proctoring decisions for the Duolingo English Test. It also reveals a bit about the logistics of remote proctoring, including proctors based in the US, Philippines, and India.
raw.githubusercontent.com/mlresearch/v...
raw.githubusercontent.com/mlresearch/v...
This is #MLresearch. (Not even being sarcastic too.)
November 20, 2024 at 7:24 PM
This is #MLresearch. (Not even being sarcastic too.)
#DigitalBehavior #MLResearch #NLPResearch #SocialMediaData
#CallForPapers: Our full-day workshop at The Web Conference 2026 #TheWebConf2026 invites submissions on reproducible and reusable computational approaches for social and #WebData.
👉 easychair.org/cfp/r2...
Deadline: Dec 18th, 2025
#CallForPapers: Our full-day workshop at The Web Conference 2026 #TheWebConf2026 invites submissions on reproducible and reusable computational approaches for social and #WebData.
👉 easychair.org/cfp/r2...
Deadline: Dec 18th, 2025
November 25, 2025 at 9:00 AM
#DigitalBehavior #MLResearch #NLPResearch #SocialMediaData
#CallForPapers: Our full-day workshop at The Web Conference 2026 #TheWebConf2026 invites submissions on reproducible and reusable computational approaches for social and #WebData.
👉 easychair.org/cfp/r2...
Deadline: Dec 18th, 2025
#CallForPapers: Our full-day workshop at The Web Conference 2026 #TheWebConf2026 invites submissions on reproducible and reusable computational approaches for social and #WebData.
👉 easychair.org/cfp/r2...
Deadline: Dec 18th, 2025
DeepMind's new AI literally dreams about its past tries, turning failures into fresh insights. The breakthrough could reshape how we benchmark learning. Curious? Dive into the details! #DeepMind #DreamingAI #MLResearch
🔗 aidailypost.com/news/google-...
🔗 aidailypost.com/news/google-...
September 19, 2026 at 11:39 AM
DeepMind's new AI literally dreams about its past tries, turning failures into fresh insights. The breakthrough could reshape how we benchmark learning. Curious? Dive into the details! #DeepMind #DreamingAI #MLResearch
🔗 aidailypost.com/news/google-...
🔗 aidailypost.com/news/google-...
How do you handle imbalance in your ML workflows?
Drop your thoughts in the comments! Let's start a conversation about responsible and effective machine learning practices. 💬👇
onlinelibrary.wiley....
#MachineLearning #DataScience #AI #SMOTE #ImbalancedData #MLResearch #PredictiveModeling
Drop your thoughts in the comments! Let's start a conversation about responsible and effective machine learning practices. 💬👇
onlinelibrary.wiley....
#MachineLearning #DataScience #AI #SMOTE #ImbalancedData #MLResearch #PredictiveModeling
March 6, 2025 at 1:36 PM
How do you handle imbalance in your ML workflows?
Drop your thoughts in the comments! Let's start a conversation about responsible and effective machine learning practices. 💬👇
onlinelibrary.wiley....
#MachineLearning #DataScience #AI #SMOTE #ImbalancedData #MLResearch #PredictiveModeling
Drop your thoughts in the comments! Let's start a conversation about responsible and effective machine learning practices. 💬👇
onlinelibrary.wiley....
#MachineLearning #DataScience #AI #SMOTE #ImbalancedData #MLResearch #PredictiveModeling
👏 Proud to share that the paper that Ahmed Heakl authored during his internship at Parameter Lab was accepted at #ICLR2026!
See how 🩺Dr.LLM increases accuracy and decreases inference computations of frozen LLMs: www.linkedin.com/posts/ahmed-...
See how 🩺Dr.LLM increases accuracy and decreases inference computations of frozen LLMs: www.linkedin.com/posts/ahmed-...
#llm #ai #efficientai #nlp #mlresearch #reasoning #adaptivecompute | Ahmed Heakl | 19 comments
Super excited to share the last work from my internship in Germany 🇩🇪!
🚀 Dr.LLM: Dynamic Layer Routing for LLMs
> What if we can reduce computation AND increase accuracy? 🤯
Most prompts don’t need ev...
www.linkedin.com
January 28, 2026 at 2:04 PM
👏 Proud to share that the paper that Ahmed Heakl authored during his internship at Parameter Lab was accepted at #ICLR2026!
See how 🩺Dr.LLM increases accuracy and decreases inference computations of frozen LLMs: www.linkedin.com/posts/ahmed-...
See how 🩺Dr.LLM increases accuracy and decreases inference computations of frozen LLMs: www.linkedin.com/posts/ahmed-...
I have been asked to respond to the prompt below:
1. What, as you see it, are the most important potential benefits of #generativeAI technology? (List at least 2)
My response:
- Giving my partner a job in AI/MLresearch and development.
- Something to be destroyed in the #butlerianJihad
1. What, as you see it, are the most important potential benefits of #generativeAI technology? (List at least 2)
My response:
- Giving my partner a job in AI/MLresearch and development.
- Something to be destroyed in the #butlerianJihad
March 11, 2025 at 7:51 PM
I have been asked to respond to the prompt below:
1. What, as you see it, are the most important potential benefits of #generativeAI technology? (List at least 2)
My response:
- Giving my partner a job in AI/MLresearch and development.
- Something to be destroyed in the #butlerianJihad
1. What, as you see it, are the most important potential benefits of #generativeAI technology? (List at least 2)
My response:
- Giving my partner a job in AI/MLresearch and development.
- Something to be destroyed in the #butlerianJihad
Let’s demand real comparisons and rigorous benchmarks.
Otherwise, we’re just building castles in the air.
#TimeSeries #Transformers #NBEATS #MLResearch #DataScience #IntegrityMatters
Otherwise, we’re just building castles in the air.
#TimeSeries #Transformers #NBEATS #MLResearch #DataScience #IntegrityMatters
March 3, 2025 at 4:31 PM
Let’s demand real comparisons and rigorous benchmarks.
Otherwise, we’re just building castles in the air.
#TimeSeries #Transformers #NBEATS #MLResearch #DataScience #IntegrityMatters
Otherwise, we’re just building castles in the air.
#TimeSeries #Transformers #NBEATS #MLResearch #DataScience #IntegrityMatters
🚀 Plenary Speaker Spotlight: ICMLAI-2027! 🚀
🔗https://artificialintelligence2027.pagesconferences.org/
📧icmlai2027@pagesconferences.org
#ICMLAI2027 #MachineLearning #ArtificialIntelligence #AI #DataScience #AIResearch #MLResearch #DeepLearning #GenerativeAI #NeuralNetworks #NLP #ComputerVision
🔗https://artificialintelligence2027.pagesconferences.org/
📧icmlai2027@pagesconferences.org
#ICMLAI2027 #MachineLearning #ArtificialIntelligence #AI #DataScience #AIResearch #MLResearch #DeepLearning #GenerativeAI #NeuralNetworks #NLP #ComputerVision
August 11, 2026 at 12:22 PM
🚀 Plenary Speaker Spotlight: ICMLAI-2027! 🚀
🔗https://artificialintelligence2027.pagesconferences.org/
📧icmlai2027@pagesconferences.org
#ICMLAI2027 #MachineLearning #ArtificialIntelligence #AI #DataScience #AIResearch #MLResearch #DeepLearning #GenerativeAI #NeuralNetworks #NLP #ComputerVision
🔗https://artificialintelligence2027.pagesconferences.org/
📧icmlai2027@pagesconferences.org
#ICMLAI2027 #MachineLearning #ArtificialIntelligence #AI #DataScience #AIResearch #MLResearch #DeepLearning #GenerativeAI #NeuralNetworks #NLP #ComputerVision
[9/9]
Appreciate any advice, pointers to relevant papers, or even “don’t do this” cautionary tales.
Thanks in advance!
#transformers #sparsity #maskedmodeling #deeplearning #symbolicAI #mlresearch #attentionmodels #structureddata
Appreciate any advice, pointers to relevant papers, or even “don’t do this” cautionary tales.
Thanks in advance!
#transformers #sparsity #maskedmodeling #deeplearning #symbolicAI #mlresearch #attentionmodels #structureddata
June 14, 2025 at 5:22 AM
[9/9]
Appreciate any advice, pointers to relevant papers, or even “don’t do this” cautionary tales.
Thanks in advance!
#transformers #sparsity #maskedmodeling #deeplearning #symbolicAI #mlresearch #attentionmodels #structureddata
Appreciate any advice, pointers to relevant papers, or even “don’t do this” cautionary tales.
Thanks in advance!
#transformers #sparsity #maskedmodeling #deeplearning #symbolicAI #mlresearch #attentionmodels #structureddata
Excited to welcome Aditya Grover, UCLA, as a keynote speaker at #IJCAI2025 in #Montreal. He is the winner of the IJCAI-25 Computers and Thought Award: aditya-grover.github.io
#AI #GenerativeAI #MLResearch
#AI #GenerativeAI #MLResearch
August 2, 2025 at 3:21 PM
Excited to welcome Aditya Grover, UCLA, as a keynote speaker at #IJCAI2025 in #Montreal. He is the winner of the IJCAI-25 Computers and Thought Award: aditya-grover.github.io
#AI #GenerativeAI #MLResearch
#AI #GenerativeAI #MLResearch
Until then, let’s call this what it is: intellectual laziness masquerading as empirical rigor.
📄 Read the paper if you must
#TimeSeries #MachineLearning #BadScience #SyntheticData #AISnakeOil #GPDelusions #MLResearch
📄 Read the paper if you must
#TimeSeries #MachineLearning #BadScience #SyntheticData #AISnakeOil #GPDelusions #MLResearch
June 19, 2025 at 3:03 PM
Until then, let’s call this what it is: intellectual laziness masquerading as empirical rigor.
📄 Read the paper if you must
#TimeSeries #MachineLearning #BadScience #SyntheticData #AISnakeOil #GPDelusions #MLResearch
📄 Read the paper if you must
#TimeSeries #MachineLearning #BadScience #SyntheticData #AISnakeOil #GPDelusions #MLResearch
Feature normalization in Ijepa helps stabilize training and improve performance in self-supervised learning. This project explores its impact on real-world vision tasks. Discover the insights: https://github.com/theAdamColton/elucidating-featurenorm-ijepa #MLResearch #OpenSource
August 16, 2025 at 3:27 AM
Feature normalization in Ijepa helps stabilize training and improve performance in self-supervised learning. This project explores its impact on real-world vision tasks. Discover the insights: https://github.com/theAdamColton/elucidating-featurenorm-ijepa #MLResearch #OpenSource
Two weeks left! Submit a 1-page overview for our AAAI “Perspectives from the Community” session alongside the workshop on the Rashomon Effect (Jan 27, 2026) ✨ Selected contributors will give 5–15 min talks.
Deadline Nov 30
➡️ forms.gle/h4Dj2MfVqYpa...
#AAAI26 #MLResearch #Uncertainty
Deadline Nov 30
➡️ forms.gle/h4Dj2MfVqYpa...
#AAAI26 #MLResearch #Uncertainty
November 15, 2025 at 2:45 AM
Two weeks left! Submit a 1-page overview for our AAAI “Perspectives from the Community” session alongside the workshop on the Rashomon Effect (Jan 27, 2026) ✨ Selected contributors will give 5–15 min talks.
Deadline Nov 30
➡️ forms.gle/h4Dj2MfVqYpa...
#AAAI26 #MLResearch #Uncertainty
Deadline Nov 30
➡️ forms.gle/h4Dj2MfVqYpa...
#AAAI26 #MLResearch #Uncertainty
NoProp: Training Neural Nets Without Backprop or Forwardprop
A new paper proposes "NoProp"—a radical approach to training neural networks without traditional back/forward propagation.
arxiv.org/abs/2503.24322
#AI #NeuralNetworks #MLResearch
A new paper proposes "NoProp"—a radical approach to training neural networks without traditional back/forward propagation.
arxiv.org/abs/2503.24322
#AI #NeuralNetworks #MLResearch
NoProp: Training Neural Networks without Back-propagation or Forward-propagation
The canonical deep learning approach for learning requires computing a gradient term at each layer by back-propagating the error signal from the output towards each learnable parameter. Given the…
arxiv.org
April 17, 2025 at 7:06 PM
NoProp: Training Neural Nets Without Backprop or Forwardprop
A new paper proposes "NoProp"—a radical approach to training neural networks without traditional back/forward propagation.
arxiv.org/abs/2503.24322
#AI #NeuralNetworks #MLResearch
A new paper proposes "NoProp"—a radical approach to training neural networks without traditional back/forward propagation.
arxiv.org/abs/2503.24322
#AI #NeuralNetworks #MLResearch
New on arXiv: “Learning Dynamics of LLM Finetuning.” A unified view of SFT & DPO reveals a squeezing effect driving confidence decay in off-policy DPO—and a simple SFT tweak that boosts downstream wins. arxiv.org/abs/2407.10490 #LLM #RLHF #MLResearch @arxiv
Learning Dynamics of LLM Finetuning
Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding the behavior of deep…
arxiv.org
December 21, 2025 at 8:42 AM
New on arXiv: “Learning Dynamics of LLM Finetuning.” A unified view of SFT & DPO reveals a squeezing effect driving confidence decay in off-policy DPO—and a simple SFT tweak that boosts downstream wins. arxiv.org/abs/2407.10490 #LLM #RLHF #MLResearch @arxiv