LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
hub Mixed citations
Efficient Lifelong Learning with A-GEM
Mixed citation behavior. Most common role is background (67%).
21
Pith papers citing it
Background
67% of classified citations
abstract
In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost. Towards this end, we first introduce a new and a more realistic evaluation protocol, whereby learners observe each example only once and hyper-parameter selection is done on a small and disjoint set of tasks, which is not used for the actual learning experience and evaluation. Second, we introduce a new metric measuring how quickly a learner acquires a new skill. Third, we propose an improved version of GEM (Lopez-Paz & Ranzato, 2017), dubbed Averaged GEM (A-GEM), which enjoys the same or even better performance as GEM, while being almost as computationally and memory efficient as EWC (Kirkpatrick et al., 2016) and other regularization-based methods. Finally, we show that all algorithms including A-GEM can learn even more quickly if they are provided with task descriptors specifying the classification tasks under consideration. Our experiments on several standard lifelong learning benchmarks demonstrate that A-GEM has the best trade-off between accuracy and efficiency.
hub tools
citation-role summary
background 5
method 1
citation-polarity summary
representative citing papers
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
MIST fixes unreliable splits in streaming decision trees for class-incremental learning by replacing Hoeffding-style bounds with a K-independent McDiarmid radius on Gini, plus Bayesian parent-to-child inheritance and per-leaf quantile sketches.
SLE-FNO achieves zero forgetting and strong plasticity-stability balance in continual learning for FNO surrogate models of pulsatile blood flow by adding minimal single-layer extensions across four out-of-distribution tasks.
SeqMem-Eval reveals that high final accuracy in sequential LLM memory tasks often coexists with substantial forgetting and negative transfer, exposing stability-adaptability trade-offs hidden by standard aggregate metrics.
DRIFT benchmark shows substantial performance degradation for continual graph learning methods under task-free continuous distribution shifts modeled via Gaussian mixtures.
Muon-OGD introduces a spectral-norm constrained orthogonal projection method solved via dual iterations and Newton-Schulz approximations to improve stability-plasticity trade-off in sequential LLM adaptation.
Routing architecture for MLLMs enables continual learning with constant compute, matching multi-task learning performance and supporting cross-modal transfer.
A hypernetwork generates clock-augmented stable neural ODEs (sNODEs) for scalable continual learning from demonstration, achieving O(N) training time via stochastic regularization while outperforming baselines on LfD tasks up to 26 skills and 32 dimensions.
Sharpness-aware pretraining and related flat-minima interventions reduce catastrophic forgetting by up to 80% after post-training across 20M-150M models and by 31-40% at 1B scale.
Three complementary metrics are introduced to distinguish model adaptation from intrinsic data difficulty under temporal distribution shift.
SHARP separates memory accumulation from pattern recognition and uses accelerated offline replay of structured traces to achieve exponentially growing effective context at linear compute cost while learning non-stationary streams.
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.
CP-MoE uses a transient expert, consistency-preserving routing bias, and guided regularization to reduce catastrophic forgetting in MoE-based LLMs and VLMs while preserving cross-task transfer, reporting SOTA on SuperNI and gains on VQA v2.
BRAIN uses bias-mitigation continual learning with a new de-bias contrastive loss and angular forgetting mitigation to achieve SOTA performance on vision-brain understanding benchmarks despite brain signal inconsistencies across sessions.
MDM-OC encodes fine-tuned models as deltas, projects them into orthogonal subspaces, and merges via gradient optimization to enable interference-free continual learning with reversible unmerging.
HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigating catastrophic forgetting.
CRAFT is a continual learning method for LLMs that learns low-rank interventions on hidden representations, using a unified KL-divergence objective to handle task routing by output divergence, forgetting control via prior-state regularization, and intervention merging.
citing papers explorer
-
LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
-
Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
-
MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
MIST fixes unreliable splits in streaming decision trees for class-incremental learning by replacing Hoeffding-style bounds with a K-independent McDiarmid radius on Gini, plus Bayesian parent-to-child inheritance and per-leaf quantile sketches.
-
SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
SLE-FNO achieves zero forgetting and strong plasticity-stability balance in continual learning for FNO surrogate models of pulsatile blood flow by adding minimal single-layer extensions across four out-of-distribution tasks.
-
Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory
SeqMem-Eval reveals that high final accuracy in sequential LLM memory tasks often coexists with substantial forgetting and negative transfer, exposing stability-adaptability trade-offs hidden by standard aggregate metrics.
-
DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
DRIFT benchmark shows substantial performance degradation for continual graph learning methods under task-free continuous distribution shifts modeled via Gaussian mixtures.
-
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Muon-OGD introduces a spectral-norm constrained orthogonal projection method solved via dual iterations and Newton-Schulz approximations to improve stability-plasticity trade-off in sequential LLM adaptation.
-
Routing-Based Continual Learning for Multimodal Large Language Models
Routing architecture for MLLMs enables continual learning with constant compute, matching multi-task learning performance and supporting cross-modal transfer.
-
Scalable and Efficient Continual Learning from Demonstration via a Hypernetwork-generated Stable Dynamics Model
A hypernetwork generates clock-augmented stable neural ODEs (sNODEs) for scalable continual learning from demonstration, achieving O(N) training time via stochastic regularization while outperforming baselines on LfD tasks up to 26 skills and 32 dimensions.
-
Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
Sharpness-aware pretraining and related flat-minima interventions reduce catastrophic forgetting by up to 80% after post-training across 20M-150M models and by 31-40% at 1B scale.
-
Tracking Adaptation Time: Metrics for Temporal Distribution Shift
Three complementary metrics are introduced to distinguish model adaptation from intrinsic data difficulty under temporal distribution shift.
-
SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition
SHARP separates memory accumulation from pattern recognition and uses accelerated offline replay of structured traces to achieve exponentially growing effective context at linear compute cost while learning non-stationary streams.
-
Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.
-
CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
CP-MoE uses a transient expert, consistency-preserving routing bias, and guided regularization to reduce catastrophic forgetting in MoE-based LLMs and VLMs while preserving cross-task transfer, reporting SOTA on SuperNI and gains on VQA v2.
-
BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding
BRAIN uses bias-mitigation continual learning with a new de-bias contrastive loss and angular forgetting mitigation to achieve SOTA performance on vision-brain understanding benchmarks despite brain signal inconsistencies across sessions.
-
Modular Delta Merging with Orthogonal Constraints: A Scalable Framework for Continual and Reversible Model Composition
MDM-OC encodes fine-tuned models as deltas, projects them into orthogonal subspaces, and merges via gradient optimization to enable interference-free continual learning with reversible unmerging.
-
HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning
HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigating catastrophic forgetting.
-
CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning
CRAFT is a continual learning method for LLMs that learns low-rank interventions on hidden representations, using a unified KL-divergence objective to handle task routing by output divergence, forgetting control via prior-state regularization, and intervention merging.
- TACO: Temporal Consensus Optimization for Continual Neural Mapping
- Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
- Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning