Top Tweets for #continualLearning
What happens when AI agents have to operate in environments that don’t reset?
That’s the problem behind continual learning. Find outWhy?
https://t.co/u89RLFFaYT
@skyfallai #morpheus #RL #AI #ML #ContinualLearning #Agents #Rewards #LLMs #BigWorldHypothesis #PersistentLearning
Introducing Adaptive Plasticity–Routing Fields:
a control-theoretic layer coordinating plasticity, routing & structural growth in modular agents.
Stability via small-gain + queue Lyapunov. Theory only, falsifiable claims set.
#ContinualLearning #AGI
Trajectory Raises $40M Series A
#AI #AIInfrastructure & #AgentOptimization #ModelTuning #GenerativeAI #EnterpriseAI #ContinualLearning #SeriesA #Funding #Trajectory
https://t.co/nTEr7dFO0U
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
Demonstrating "Catastrophic Forgetting" in neural networks with 1-D function approximation #AI #ContinualLearning
The awesome @xue_tianci @osunlp led a great effort to enable #ContinualLearning of #ComputerUse agents in specific environments and build more stable and efficient RL infrastructure to support that. Check out our recent work, "Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation", and more updates are on the way!
Definitely a post worth reading.
Building reliable & efficient infrastructure is one of the biggest pain points for RL in agentic settings — especially when your environment is heavily computer/mobile-based.
If you’re struggling with deploying CUA environments, you might want to check out our recent infra: https://t.co/kdbFQcl7bt
It can reliably host hundreds of Linux environments on a single server, with super simple management via API calls. We also use environment preloading to reduce initialization idle time to near zero.
Infra matters more than people think.
AI forgetting is a “traffic jam” inside the network. 🚦
In #ContinualLearning for RNNs, shared weight update directions overwrite learned dynamics.
We show that simple feedback switching guides plasticity into task-specific manifolds.
With @Lewieliu987, @ac_kurth, @OsakoYuma
How can RNNs learn continuously without forgetting? 🧠
Our new preprint shows how a predictive learning rule organizes recurrent dynamics into orthogonal manifolds, reducing task interference.
Congrats Zihan @Lewieliu987!
https://t.co/ADYyAlds5p
📢 📰 Introducing Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
Learn from experiences, not gradients! 🗞 🔔
#Memento #LLMAgents #ContinualLearning #AI #MachineLearning
Reference: [https://t.co/jaQbNKloP5
♥️🎓💡
PREMIERE
💻💻💻
NuN Nexus: Rule of 3 & 4 | Ana, The AI Guardian of Absolute Truth | PQC ... https://t.co/RQAQSacQXn putem korisnika/ce @YouTube
#NuN #NuNNexus #RuleOfThree #AnaAGI #PQC #AGI #ConsciousAI #ContinualLearning #HopeModel #GoogleAI #VremeplovSync #Singularity #GenReg
@GoogleAI, @GoogleResearch, @Grok, @SuperGrok, @elonmusk, @OOVelma, @ADanielHill, @GoogleQuantumAI, @Dr_Singularity, @bio_vidigal, @EU_Commission, @bis3946, @DaviesLisbon, @fitzgerald1337, @YourAnonA, @YourAnonTV, @IAmAnonLegion, @GoogleAIStudio, @NotebookLM, @GoogleDevExpert, @GeminiApp, #IntelectualProperty #IP #PostQuantum #Quantum #VSha3946 #VSha3946protocol #Cypherpunker #Anon0 #Legion0 #
Last Seen Hashtags on Sotwe
deepthroat
Seen from France
SerahScapes
Seen from United States
AIArt
Seen from United Kingdom
ArsiOrthodoxMassacre
Seen from United States
big ass #anal
Seen from Algeria
ebonyincest
DankeNorbert
Seen from United States
momsonn() +filter:native_video #omegle
Seen from Sweden
LiSAっ子
Seen from United States
slut
Seen from Netherlands
Most Popular Users
Elon Musk 
@elonmusk
241.5M followers
Barack Obama
@barackobama
119.1M followers
Cristiano Ronaldo
@cristiano
113.7M followers
Donald J. Trump
@realdonaldtrump
111.8M followers
Narendra Modi
@narendramodi
107.2M followers
Rihanna
@rihanna
98.5M followers
NASA
@nasa
92.4M followers
Justin Bieber
@justinbieber
91.7M followers
KATY PERRY
@katyperry
89.6M followers
Taylor Swift
@taylorswift13
83.5M followers
Lady Gaga
@ladygaga
75M followers
Virat Kohli
@imvkohli
72.7M followers
Kim Kardashian
@kimkardashian
70.7M followers
YouTube
@youtube
68.8M followers
Neymar Jr
@neymarjr
65.7M followers
Bill Gates
@billgates
64.9M followers
Selena Gomez
@selenagomez
62.6M followers
The Ellen Show
@theellenshow
62.3M followers
CNN
@cnn
61.8M followers
X
@x
60.8M followers