Top Tweets for #Continuallearning
We see events like this as a way to bring researchers and builders together around hard technical questions and turn new ideas into companies.
Thank you to @Sierra_Ventures and SVB for helping make the evening possible. @Techweek_ #ContinualLearning #OpenSourceAI #SFTechWeek
@jerrywliu and team build MLPs that store facts at the information-theoretic limit with zero training. Can a constructed MLP take in new facts later without overwriting the old ones? #COLM2026 #ContinualLearning
At #COLM2026 this week! 👋
Come find us Wed @ 11am! We’ll be presenting our work on constructing MLPs that store facts at the information-theoretic limit, without training.
And if you’re interested in memory, continual learning, or recurrent/long-context models, I’d love to chat!
Our paper was selected to receive the 2027 IEEE TCDS Outstanding Paper Award by the #IEEE Computational Intelligence Society.
Title: Continual Robot Learning Using Self-Supervised Task Inference
Link: https://t.co/dzzNS4BzJu
#ContinualLearning #IEEECIS #Robotics #PaperAward
Everyone's turning harnesses into RL environments for the model
Meanwhile I still type "pls fix it" like it's 2024 😂
Be honest: in your setup, who's actually learning faster, you or the agent?
#AIAgents #ContinualLearning
Export it. Self-host it. Update it continually without catastrophic forgetting.
That’s exactly what we built at ModelBrew.
Own the model. Own the knowledge. Kill the learning loop.
Try it free → https://t.co/QYMW9Gy4Hm
#AI #OpenWeight #FineTuning #ContinualLearning
We are pleased to present three papers at #Interspeech 2026 in Australia this week. Our team is sharing new research advancing robust speech recognition and continual learning. Below an overview of the work we are presenting.
#Interspeech2026 #ContinualLearning #ASR
Fascinating take on incremental learning, @JagersbergKnut. Using metaplasticity as adaptive gradient preconditioning is a compelling way to tackle catastrophic forgetting. Thank you for the mention.
#AI #MachineLearning #ContinualLearning #Neuroscience #WomenInTech
Metaplasticity as adaptive gradient preconditioning for incremental learning
@bimedotcom @Khulood_Almani @Eli_Krumova @sulefati7 @NathaliaLeHen @IanLJones98 @TheAIObserverX
https://t.co/WPX4pB5aaw
@JagersbergKnut @bimedotcom @Khulood_Almani @sulefati7 @NathaliaLeHen @IanLJones98 @TheAIObserverX Fascinating take on incremental learning, @JagersbergKnut. Using metaplasticity as adaptive gradient preconditioning is a compelling way to tackle catastrophic forgetting. Thank you for the mention.
#AI #MachineLearning #ContinualLearning #Neuroscience #WomenInTech
Anyone going to YC startup school tomorrow and interested in multimodality/continual learning, hmu for lunch.
#startupschool #yc #multimodal #posttraining #continuallearning
🙌Welcome to the AReaL community. First tweet.💥Big release.
We are excited to announce the release of AReaL 2.0: RL as Micro-Service! Thanks to the great efforts from the AReaL community and collaborators❤️
In AReaL 2.0, we rebuilt online agent RL around four decoupled components: Training Service, Inference Serivce, WeightUpdate Service and Agent Service.
Change one URL in your existing agent, start learning from production traffic.
#AIAgent #agenticRL #AReaL #LLM
💻 GitHub: https://t.co/RbwexnGixj
📢 Call for papers: Continual RL Workshop @ RLC 2026, Montreal
🗓️ Submission deadline: May 22, 2026 (AoE)
🔗 Website & CFP: https://t.co/JmNXyeyPSL
#ReinforcementLearning #ContinualLearning #MachineLearning #RLC2026 #ContinualRL
@I_Am_The_ICT yes agree, i always have trouble with my stop loss placement. fighting the urge to move too quickly as well. strangling my trade as you would say. #continuallearning
In the era of continued pretraining and continued fine-tuning, loss of plasticity means leaving future gains on the table. We need a better theoretical understanding of loss of plasticity. See a great thread unpacking the dynamics. 👇
#ICLR2026 #ContinualLearning #DeepLearning
Neural nets don’t just forget. Sometimes, after long training, they lose the ability to learn at all.
In our #ICLR2026 poster, we model Loss of Plasticity as gradient dynamics trapped in invariant manifolds: 🔴 frozen units, 🔵 cloned units.
The video makes the traps visible.
Giulia Lanzillotta is presenting this today at #ICLR2026:
📍 Poster Session 6, Pavilion 4, Board #4202
🕒 Sat Apr 25, 3:15–5:45 PM local time
Paper/code/demo in replies.
#ContinualLearning #DeepLearning #LearningTheory
In #ContinualLearning, we have long assumed extreme memory constraints. But in today's era of large models where compute is the real bottleneck, is catastrophic forgetting still our biggest problem?
Our #ICLR2026 paper, "Forget Forgetting: Continual Learning in a World of Abundant Memory", challenges this view. We found that in practical settings with abundant memory, models actually struggle more with a loss of plasticity rather than forgetting. They become biased toward past data and fail to absorb new knowledge.
To address this, we introduce Weight Space Consolidation. This lightweight method uses rank-based parameter initialization (using merging) to restore plasticity and weight averaging to maintain stability. The result is high efficiency and performance in both #LLM continual instruction tuning and vision models, avoiding the massive cost of full retraining.
While I cannot attend the conference in Rio de Janeiro in person, the first author will be presenting our poster. If you are working on the practical limits of Continual Learning or LLMs, please stop by our session for a discussion.
Presentation Details: ICLR 2026, Poster Session 5, Pavilion 3 (Saturday, April 25 at 09:30 EDT)
Project Page: https://t.co/zJFQgZoHDb
GitHub: https://t.co/L4EoPWlZNw
Star if it clicks ⭐
Feedback/extensions welcome.
Let’s solve forgetting for real.
#ContinualLearning #LLM #KnowledgeEditing #MQuAKE
@karpathy @askalphaxiv @hwchase17 @goodside @jeremyphoward @isaachan_ai
Star if it clicks ⭐
Feedback/extensions welcome.
Let’s solve forgetting for real.
#ContinualLearning #LLM #KnowledgeEditing #MQuAKE
@karpathy @askalphaxiv @hwchase17 @goodside @jeremyphoward @isaachan_ai
60-sample codegen, just passed 100% across the board
- Language match: 100%
- Specialized stub rate: 100%
- JavaScript/Python/Rust: 100%
Our organism has achieved zero-forget MNIST, perfect action generation & now writes fully specialized code!
#NeuroAI #ContinualLearning #AI
At SWTCH Labs, we've created a new kind of AI.
A tiny artificial brain that grows, organizes itself, and keeps learning without forgetting.
Not a transformer. Not an LLM. A new substrate.
#NeuroAI #ContinualLearning #AI
Zero forgetting. Confirmed.
Fresh continual MNIST run → saved checkpoint → reloaded and re-tested all 5 tasks.
Result: 97.3% average accuracy.
Zero degradation. Zero hallucinations from interference.
This is a continually learning substrate that actually remembers.
Our organism is actually learning like a living brain.
- XOR: 100%
- Spirals: 94.5%
- Concentric Circles: 97.9%
Trained on spirals → saved checkpoint → adapted to circles with zero full retraining.
We don’t code intelligence.
We grow it.
#NeuroAI #ContinualLearning #AI
Last Seen Hashtags on Sotwe
Caught
Seen from United States
سليمه
Seen from Germany
gachansfw harem
unexpected (((()))) + filter:media() -filter:images
Seen from Sweden
snapchat video
Seen from Turkey
braces blowjob
Seen from France
ai短剧
Seen from Malaysia
MichelleRabitt
إعجابها
Seen from Algeria
cuckoldtürkiye
Seen from Turkey
Most Popular Users
Elon Musk 
@elonmusk
241.7M followers
Barack Obama
@barackobama
119M followers
Cristiano Ronaldo
@cristiano
114.6M 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
90.1M followers
Taylor Swift
@taylorswift13
84M followers
Lady Gaga
@ladygaga
75.5M followers
Virat Kohli
@imvkohli
73.5M followers
Kim Kardashian
@kimkardashian
70.9M followers
YouTube
@youtube
68.8M followers
Neymar Jr
@neymarjr
66.5M followers
Bill Gates
@billgates
65.2M followers
Selena Gomez
@selenagomez
63.1M followers
The Ellen Show
@theellenshow
62.3M followers
CNN
@cnn
61.8M followers
X
@x
60.7M followers