Papers Continual Learning
“Continual Learning” 태그가 달린 논문 3,531편 · 필터 해제
PaLoRA: Paced Low-Rank Adaptation for Continual Learning
LoRA-based continual learning methods mitigate catastrophic forgetting through various mechanisms, yet nearly all complement these with small learning rates as a heuristic to restrict gradient scaling magnitude. Such fix…
Continual LearningTask-Oriented Rank Adaptation for Continual Learning in Text Classification
Continual learning (CL) in text classification faces two critical challenges: catastrophic forgetting and negative transfer across sequential tasks. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA enable effi…
parameter-efficient fine-tuningText ClassificationContinual LearningContinual Reinforcement Learning with Neuroevolution
Despite many studies about causes and remedies of plasticity loss in Reinforcement Learning (RL) under continual task changes, no RL method has yet consistently achieved a good balance between adaptation and forgetting. …
Reinforcement LearningContinual LearningLearning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
Modern language models are likely to be updated throughout their lifetime rather than trained once and frozen. Each update therefore participates in a recurring cycle: decide which experience to learn from, understand wh…
Continual LearningACLArena: Agent Continue Learning in Multi-stage Post-training
Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of training. Yet there is currently no well-established recipe for Agent C…
Continual LearningScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying …
Reinforcement LearningContinual LearningContinual Learning for Traversability Prediction with Uncertainty-Aware Adaptation
Traversability prediction is a critical component of autonomous navigation in unstructured environments, where complex and uncertain robot-terrain interactions pose significant challenges such as traction loss and dynami…
Continual LearningCLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework
Continual learning must balance the learning of new knowledge with the retention of previously learned knowledge to incrementally learn tasks from a data stream without catastrophic forgetting. While leveraging pretraine…
Continual LearningArtificial Intelligence-Enabled Space Robot Operations: Technologies, Challenges and Prospects
Space robots are increasingly expected to perform long-duration, contact-rich, and multi-stage operations with limited human intervention. Recent advances in artificial intelligence (AI), robot learning, and embodied fou…
Continual LearningWhen Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis
Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to stop. This test-time strategy makes it difficult to measure how agent …
Continual LearningContinual Learning Mechanisms Compose for Long-Horizon Memorization
Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we introduce long-horizon memorization, a setting in which a model learns…
Continual LearningMePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning
General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous data, making it a realistic yet challenging setting for continual int…
Continual LearningEfficient Online Continual Foundation Model Fine-Tuning for Predictive Process Monitoring
Predictive Process Monitoring (PPM) models are increasingly deployed in dynamic environments where concept drift causes the underlying process distribution to shift over time. While recent work has moved toward online co…
Continual LearningThomson: Continual Learning of Frontier Models for SovereignAI
The development of frontier models is commonly perceived to be the exclusive remit of a small number of heavily funded players, creating an information, economic and power asymmetry between developers and the diverse use…
Continual LearningPrompt EngineeringDomain AdaptationUnifying Detection and Adaptation in Task-Free Continual Learning
To mitigate catastrophic forgetting in downstream continual learning (CL) for large language models (LLMs), existing methods typically constrain parameter updates or introduce task-specific adaptation modules. However, t…
Continual LearningGeo-LoRA: Geometry-Aware Subspace Evolution for Low-Rank Adaptation in Continual Learning
Rehearsal-free class-incremental learning (CIL) with LoRA adapters remains challenging because the low-rank subspaces updated across tasks evolve without geometric control, causing unstable shared representations and rep…
class-incremental learningContinual LearningParameter Efficient Continual Learning for Sparse Event-Based Transformers
Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previously learned knowledge under strict memory and energy constraints. W…
parameter-efficient fine-tuningclass-incremental learningContinual LearningEvent-based visionFast Weight Attention for Continual Learning
Recurrent fast-weight memories and selective state-space models compress an expanding context into a fixed-size recurrent state, making the state transition an online learning rule. We study this rule under read-after-wr…
Continual LearningContinually learning neural-operator surrogate for three-dimensional airborne electromagnetic Bayesian inversion
Three-dimensional probabilistic inversion of time-domain airborne electromagnetic (AEM) data is limited by the cost of the forward solve. Even though one simulation takes only tens of seconds, a Bayesian inversion of a s…
Continual LearningAdvantage-Driven Explicit Memory for Social Navigation
Robot policies are predominantly learned with classical parametric variants of imitation learning or RL, where training stores the agent's behavior exclusively in the policy's network parameters, putting a heavy burden o…
Representation LearningContinual LearningDecision Making