collasconf.bsky.social
@collasconf.bsky.social
👏 Join us in celebrating these early-career researchers at #CoLLAs2025!

📍 Aug 11–14 @ University of Pennsylvania

🔗 lifelong-ml.cc/Conferences/...

#AI #ML #LifelongLearning #ContinualLearning #CoLLAs2025
CoLLAs
Collas
lifelong-ml.cc
August 5, 2025 at 5:17 PM
🧩 @jmendezm.bsky.social (Stony Brook University)

Talk: Unlocking Lifelong Robot Learning With Modularity

Jorge shows how modularity in robotics enables scalable lifelong learning for robots.

#RobotLearning #Modularity #EmbodiedAI
August 5, 2025 at 5:17 PM
🔍 @tylerlhayes.bsky.social (Georgia Tech)

Talk: Adapting to the Unknown: Lifelong Learning, Novelty Discovery, & Beyond

Tyler presents two complementary paradigms for enabling adaptation in neural networks: dynamic adaptation and static adaptation.

#NoveltyDiscovery #OpenWorld #LifelongLearning
August 5, 2025 at 5:17 PM
🤖 Jaehong Yoon (NTU Singapore)

Talk: Toward Continually Growing Embodied AIs via Selective and Purposeful Experience

From multimodal LLMs to LLM-generated training environments, Jaehong shows how purposeful experience helps agents grow efficiently.

#EmbodiedAI #ContinualLearning #LLMs
August 5, 2025 at 5:17 PM
🧠 @khimya.bsky.social (Google DeepMind)

Talk: Navigating the Affordance Landscape for Continual Agent Adaptation

She propose rethinking the agent-environment interaction through the lens of affordances and using that to develop data-efficient agents.

#RL #Affordances #ContinualLearning
August 5, 2025 at 5:17 PM
📘 Mathematics of Continual Learning
by Liangzu Peng & René Vidal

A deep dive into the mathematical principles behind continual learning and adaptive filtering. Highlights connections between the two fields and proposes directions grounded in rigorous theory.

🔗 arxiv.org/abs/2504.17963
July 31, 2025 at 6:04 PM
🔍 Information-Theoretic Measures for Multi-Expert FM Adaptation by Yang Li & Shao-Lun Huang

How much should we transfer from each expert model? This tutorial explores info-theoretic tools (KL, HGR, entropy, etc.) to measure and guide expert utility in multi-source & continual learning.
July 31, 2025 at 6:04 PM