#ContinualLearning
I found a fun way to broaden my skills in Cybersecurity and I absolutely love their platform. If you are looking to learn something new and have a blast while doing it, I really suggest giving it a try. #continuallearning
tryhackme.com/r/recapme/20...
TryHackMe | Cyber Security Training
tryhackme.com
January 5, 2025 at 2:09 PM Everybody can reply
A blend of simulation, reflection and theory… based on real life cases…. #ContinualLearning #fy #fyp #pov #medicaleducation #criticalcare #MERIT @yorksambulance #HART
August 19, 2025 at 9:24 PM Everybody can reply
A noise‑curvature framework uses noise and curvature bounds to set a threshold that detects trainability loss; a scheduler using threshold improves accuracy. Read more: https://getnews.me/unified-noise-curvature-framework-boosts-trainability-in-continual-learning/ #continuallearning #machinelearning
September 26, 2025 at 4:16 PM Everybody can reply
1 likes
SMoPE uses a sparse mixture‑of‑experts for prompts, activating only experts per input, reducing interference and compute compared to task‑specific prompts. Read more: https://getnews.me/sparse-mixture-of-experts-boosts-prompt-based-continual-learning/ #continuallearning #promptbased
September 30, 2025 at 9:33 PM Everybody can reply
🚨 Call for Reviewers! 🚨

Want to contribute to advancing #LifelongLearning research? #CoLLAs2025 is looking for expert reviewers! 📝

Help shape the field by reviewing cutting-edge research in continual and lifelong learning.

🔗 Apply here: forms.gle/z1VFR4FRCbHj...

#ContinualLearning
CoLLAs 2025 Reviewer Self-nomination
Thank you for your interest in reviewing for CoLLAs 2025. Please fill this form and we will invite you as a reviewer.
forms.gle
February 13, 2025 at 3:01 PM Everybody can reply
1 reposts 3 likes
📢 Only 8 weeks to #CoLLAs2025!

Tackle the real-world challenges of ML: catastrophic forgetting, dist. shift, continual RL, lifelong learning & more.

📍 Aug 11–14 @upenn.edu
🧠 Talks, workshops, posters, tutorials & community

🔗 lifelong-ml.cc/Conferences/...

#ContinualLearning #AI #MachineLearning
CoLLAs
Collas
lifelong-ml.cc
June 17, 2025 at 1:53 PM Everybody can reply
2 reposts 4 likes
VidCLearn adds a student‑teacher setup so the student learns new data while the teacher provides replay videos, and a temporal‑consistency loss improves motion smoothness. https://getnews.me/vidclearn-enables-continual-learning-for-text-to-video-generation/ #vidclearn #continuallearning
September 24, 2025 at 3:42 PM Everybody can reply
🎉 Announcing the winners of the #CoLLAs2025 Early-Career Spotlight Program!

These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI.

👇 A thread introducing their work & talks.

#AI #MachineLearning #ContinualLearning #LifelongLearning
August 5, 2025 at 5:17 PM Everybody can reply
4 reposts 2 quotes 4 likes
PeCL applies token‑level differential privacy and memory sculpting to shield sensitive tokens while retaining accuracy; privacy loss is lower than baselines. Read more: https://getnews.me/token-level-differential-privacy-boosts-privacy-in-continual-learning/ #privacy #continuallearning
September 18, 2025 at 1:30 PM Everybody can reply
We’re inviting applications for our Early-Career Spotlight Program—a chance for rising researchers to present their vision & trajectory in #lifelonglearning.

📅 Apply by May 26, 2025
📢 30-min invited talk + blog feature

🔗 lifelong-ml.cc/Conferences/...

#AI #MachineLearning #ContinualLearning
CoLLAs
Collas
lifelong-ml.cc
April 7, 2025 at 3:01 PM Everybody can reply
1 quotes 2 likes
UnCLe uses a hypernetwork to forget tasks by aligning generated parameters with random noise, needing no original data. Tests on vision datasets kept accuracy and showed no task relapse. https://getnews.me/uncle-enables-data-free-unlearning-for-continual-learning-models/ #uncle #continuallearning
September 24, 2025 at 11:31 PM Everybody can reply
Researchers turned dialogue state tracking into question answering, using a 60‑million‑parameter language model with memory replay to keep prior skills. Read more: https://getnews.me/example-guided-question-answering-boosts-continual-dialogue-state-tracking/ #dialoguestate #continuallearning
October 1, 2025 at 7:18 AM Everybody can reply
GPLASC splits the representation hypersphere into non‑overlapping ETF regions, boosting retention on benchmark continual‑learning tasks. Read more: https://getnews.me/gplasc-contrastive-strategy-boosts-continual-learning-performance/ #continuallearning #contrastive
September 22, 2025 at 5:40 AM Everybody can reply
Got ongoing work or a paper under review? Submit to the #CoLLAs2025 Workshop Track! This year, we’re also highlighting Lifelong Learning in Cognitive Science 🧠✨

🔹 Deadline: May 22, 2025 (AoE)
🔗 lifelong-ml.cc/Conferences/...

#ContinualLearning #LifelongLearning #AI #CognitiveScience
CoLLAs
Collas
lifelong-ml.cc
March 19, 2025 at 1:38 PM Everybody can reply
1 likes
From strength to strength – a simple phrase with profound meaning.

For more, see episode 299 of Paper Napkin Wisdom here: bit.ly/4hzcFp7

#Leadership #PersonalGrowth #Legacy #ContinualLearning #Mentorship #ProfessionalDevelopment
September 29, 2025 at 8:01 PM Everybody can reply
2 likes
🚀 Ready to push the boundaries of #AI & #ML? We're hiring 7(!) brilliant PhDs, PostDocs, and Engineers to work on cutting-edge #LLMs #AutoML #ContinualLearning
@TUeindhoven

🌟 Think big and shape the future of AI!
🧑‍💻 Apply now! openml-labs.github.io/website/join...
❣️Please share❣️
December 6, 2024 at 4:25 PM Everybody can reply
7 reposts 14 likes
Meta-weight-ensembler uses meta‑learning to set layer‑wise mixing coefficients, fusing task models and reducing forgetting. Benchmarks show top results (24 Sep 2025). https://getnews.me/adaptive-model-ensemble-reduces-forgetting-in-continual-learning/ #continuallearning #metaweightensembler
September 26, 2025 at 5:29 PM Everybody can reply
#Shakespere, like #ToniMorrison, #JamesBaldwin, #MarkTwain, is part of the global Literary canon. It is NOT “gaslighting” people to encourage them to understand his Works in sync with a Wide historical output by Black/White/Asian/Latino, etc., writers. #ReadWidely #ContinualLearning 💯
June 2, 2025 at 4:28 AM Everybody can reply
📢 Reminder: Submit to the #CoLLAs2025 Workshop Track!

Great venue for early work & papers under review. This year’s spotlight: Lifelong Learning in Cognitive Science 🧠✨

🗓 Deadline: May 22, 2025 (AoE)

🔗 openreview.net/group?id=lif...

#ContinualLearning #LifelongLearning #AI #CognitiveScience
CoLLAs 2025 Workshop Track
Welcome to the OpenReview homepage for CoLLAs 2025 Workshop Track
openreview.net
May 4, 2025 at 2:32 PM Everybody can reply
1 likes
EvoAgent reports a 105% average success‑rate gain over prior methods and cut ineffective actions by more than sixfold in Minecraft and Atair tests. Read more: https://getnews.me/evoagent-unveils-self-evolving-agent-with-continual-world-model/ #evoagent #continuallearning
October 1, 2025 at 11:03 AM Everybody can reply
📢 1 week left! Submit to the #CoLLAs2025 Workshop Track — ideal for early work & papers under review.

🧠 Spotlight: #LifelongLearning in Cognitive Science
🗓 Deadline: May 22, 2025 (AoE)

🔗 openreview.net/group?id=lifelong-ml.cc/CoLLAs/2025/Workshop_Track

#ContinualLearning #WorkshopCFP
CoLLAs 2025 Workshop Track
Welcome to the OpenReview homepage for CoLLAs 2025 Workshop Track
openreview.net
May 15, 2025 at 3:04 PM Everybody can reply
1 reposts 1 likes
A study released on Oct 1, 2025 introduces rehearsal‑free, task‑free online continual learning with contrastive prompts and a nearest‑class‑mean classifier, eliminating data storage. https://getnews.me/rehearsal-free-online-continual-learning-using-contrastive-prompt/ #continuallearning #privacy
October 2, 2025 at 10:29 PM Everybody can reply
📢 Present your published work at #CoLLAs2025!

Submit recent papers (JMLR, TMLR, NeurIPS, etc.) on lifelong/continual learning, LLMs, online learning & more.

🗓 Deadline: July 5
🔗 lifelong-ml.cc/Conferences/...

#AI #MachineLearning #LifelongLearning #ContinualLearning
CoLLAs
Collas
lifelong-ml.cc
June 28, 2025 at 2:11 AM Everybody can reply
2 reposts 3 likes