CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization
Paper
• 2310.10134 • Published
• 1
Continual learning
-
-
TiC-CLIP: Continual Training of CLIP Models
Paper • 2310.16226 • Published • 10 -
In-Context Pretraining: Language Modeling Beyond Document Boundaries
Paper • 2310.10638 • Published • 30 -
Controlled Decoding from Language Models
Paper • 2310.17022 • Published • 15 -
Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verification
Paper • 2212.05276 • Published • 1 -
Memorizing Transformers
Paper • 2203.08913 • Published • 2 -
Commonsense Knowledge Transfer for Pre-trained Language Models
Paper • 2306.02388 • Published • 1 -
Towards Adversarially Robust Continual Learning
Paper • 2303.17764 • Published • 1 -
Visual Programming: Compositional visual reasoning without training
Paper • 2211.11559 • Published • 1 -
Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation
Paper • 2310.18628 • Published • 8 -
TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
Paper • 2310.19019 • Published • 9 -
LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning
Paper • 2305.18169 • Published • 1 -
Augmented Large Language Models with Parametric Knowledge Guiding
Paper • 2305.04757 • Published • 2 -
Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
Paper • 2305.18395 • Published • 1 -
Continual Learning via Neural Pruning
Paper • 1903.04476 • Published • 1 -
A Deep Learning Framework for Lifelong Machine Learning
Paper • 2105.00157 • Published • 1 -
Continual Lifelong Learning with Neural Networks: A Review
Paper • 1802.07569 • Published • 1 -
Lifelong Inverse Reinforcement Learning
Paper • 2207.00461 • Published • 1 -
Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt
Paper • 2310.13024 • Published • 1 -
Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey
Paper • 2308.08234 • Published • 1 -
Multi-task Active Learning for Pre-trained Transformer-based Models
Paper • 2208.05379 • Published • 1 -
Ziya2: Data-centric Learning is All LLMs Need
Paper • 2311.03301 • Published • 20 -
Continual Pre-training of Language Models
Paper • 2302.03241 • Published • 2 -
Towards Continual Knowledge Learning of Language Models
Paper • 2110.03215 • Published • 1 -
Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora
Paper • 2110.08534 • Published • 1 -
Guiding Pretraining in Reinforcement Learning with Large Language Models
Paper • 2302.06692 • Published • 1 -
AF Adapter: Continual Pretraining for Building Chinese Biomedical Language Model
Paper • 2211.11363 • Published • 1 -
Improving Language Plasticity via Pretraining with Active Forgetting
Paper • 2307.01163 • Published • 6 -
The Life Cycle of Knowledge in Big Language Models: A Survey
Paper • 2303.07616 • Published • 1 -
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
Paper • 2311.04898 • Published • 1 -
CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning
Paper • 2211.13218 • Published • 1 -
When Prompt-based Incremental Learning Does Not Meet Strong Pretraining
Paper • 2308.10445 • Published • 1 -
PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
Paper • 2309.07117 • Published • 2 -
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
Paper • 2303.05118 • Published • 1 -
A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning
Paper • 2210.04428 • Published • 1 -
A soft nearest-neighbor framework for continual semi-supervised learning
Paper • 2212.05102 • Published • 1 -
Avalanche: an End-to-End Library for Continual Learning
Paper • 2104.00405 • Published • 2 -
SequeL: A Continual Learning Library in PyTorch and JAX
Paper • 2304.10857 • Published • 1 -
Architecture Matters in Continual Learning
Paper • 2202.00275 • Published • 1 -
Accelerating Batch Active Learning Using Continual Learning Techniques
Paper • 2305.06408 • Published • 1 -
ExpeL: LLM Agents Are Experiential Learners
Paper • 2308.10144 • Published • 3 -
ConPET: Continual Parameter-Efficient Tuning for Large Language Models
Paper • 2309.14763 • Published • 1 -
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
Paper • 2303.10070 • Published • 1 -
A Comprehensive Empirical Evaluation on Online Continual Learning
Paper • 2308.10328 • Published • 1 -
Generative Models from the perspective of Continual Learning
Paper • 1812.09111 • Published • 1 -
Continual Learning for Monolingual End-to-End Automatic Speech Recognition
Paper • 2112.09427 • Published • 1 -
Efficient Model Adaptation for Continual Learning at the Edge
Paper • 2308.02084 • Published • 1 -
SHARP: Sparsity and Hidden Activation RePlay for Neuro-Inspired Continual Learning
Paper • 2305.18563 • Published • 1 -
On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning
Paper • 2305.03648 • Published • 1 -
HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning
Paper • 2309.15038 • Published • 1 -
Rethinking Momentum Knowledge Distillation in Online Continual Learning
Paper • 2309.02870 • Published • 1 -
Continual Learning with Strong Experience Replay
Paper • 2305.13622 • Published • 1 -
Does Continual Learning Equally Forget All Parameters?
Paper • 2304.04158 • Published • 1 -
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning
Paper • 2009.01797 • Published • 1 -
Overcoming the Stability Gap in Continual Learning
Paper • 2306.01904 • Published • 2 -
Improving Online Continual Learning Performance and Stability with Temporal Ensembles
Paper • 2306.16817 • Published • 1 -
Neural Architecture for Online Ensemble Continual Learning
Paper • 2211.14963 • Published • 1 -
Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform
Paper • 2307.05399 • Published • 1 -
ICICLE: Interpretable Class Incremental Continual Learning
Paper • 2303.07811 • Published • 1 -
Energy-Based Models for Continual Learning
Paper • 2011.12216 • Published • 2 -
Revisiting Softmax Masking for Stability in Continual Learning
Paper • 2309.14808 • Published • 1 -
Model Zoo: A Growing "Brain" That Learns Continually
Paper • 2106.03027 • Published • 1 -
TAME: Task Agnostic Continual Learning using Multiple Experts
Paper • 2210.03869 • Published • 1 -
Incremental Task Learning with Incremental Rank Updates
Paper • 2207.09074 • Published • 1 -
Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer
Paper • 2211.00789 • Published • 1 -
IF2Net: Innately Forgetting-Free Networks for Continual Learning
Paper • 2306.10480 • Published • 1 -
Preserving Linear Separability in Continual Learning by Backward Feature Projection
Paper • 2303.14595 • Published • 2 -
Continual Learning with Pretrained Backbones by Tuning in the Input Space
Paper • 2306.02947 • Published • 1 -
Continual Learning with Dependency Preserving Hypernetworks
Paper • 2209.07712 • Published • 1 -
GateON: an unsupervised method for large scale continual learning
Paper • 2306.01690 • Published • 1 -
Loss of Plasticity in Deep Continual Learning
Paper • 2306.13812 • Published • 1 -
Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning
Paper • 2302.03281 • Published • 1 -
CLR: Channel-wise Lightweight Reprogramming for Continual Learning
Paper • 2307.11386 • Published • 1 -
On Sequential Bayesian Inference for Continual Learning
Paper • 2301.01828 • Published • 1 -
IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning
Paper • 2305.14782 • Published • 1 -
Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning
Paper • 2211.03186 • Published • 2 -
Big-model Driven Few-shot Continual Learning
Paper • 2309.00862 • Published • 1 -
Learn the Time to Learn: Replay Scheduling in Continual Learning
Paper • 2209.08660 • Published • 1 -
PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning
Paper • 2304.04408 • Published • 1 -
DualMix: Unleashing the Potential of Data Augmentation for Online Class-Incremental Learning
Paper • 2303.07864 • Published • 1 -
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks
Paper • 2305.13547 • Published • 1 -
Robust Active Distillation
Paper • 2210.01213 • Published • 1 -
Continual Learning with Adaptive Weights (CLAW)
Paper • 1911.09514 • Published • 1 -
Continual Semi-Supervised Learning through Contrastive Interpolation Consistency
Paper • 2108.06552 • Published • 1 -
Sy-CON: Symmetric Contrastive Loss for Continual Self-Supervised Representation Learning
Paper • 2306.05101 • Published • 1 -
Contrastive Learning for Online Semi-Supervised General Continual Learning
Paper • 2207.05615 • Published • 1 -
UER: A Heuristic Bias Addressing Approach for Online Continual Learning
Paper • 2309.04081 • Published • 1 -
Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery
Paper • 2307.10943 • Published • 1 -
Improving Continual Relation Extraction through Prototypical Contrastive Learning
Paper • 2210.04513 • Published • 1 -
BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning
Paper • 2305.04769 • Published • 1 -
Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship
Paper • 2112.15402 • Published • 2 -
Offline Experience Replay for Continual Offline Reinforcement Learning
Paper • 2305.13804 • Published • 2 -
Continual evaluation for lifelong learning: Identifying the stability gap
Paper • 2205.13452 • Published • 1 -
A multifidelity approach to continual learning for physical systems
Paper • 2304.03894 • Published • 1 -
Statistical mechanics of continual learning: variational principle and mean-field potential
Paper • 2212.02846 • Published • 1 -
A Closer Look at Rehearsal-Free Continual Learning
Paper • 2203.17269 • Published • 1 -
On Anytime Learning at Macroscale
Paper • 2106.09563 • Published • 1 -
Learning an evolved mixture model for task-free continual learning
Paper • 2207.05080 • Published • 1 -
MASIL: Towards Maximum Separable Class Representation for Few Shot Class Incremental Learning
Paper • 2304.05362 • Published • 1 -
On the Soft-Subnetwork for Few-shot Class Incremental Learning
Paper • 2209.07529 • Published • 1 -
Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
Paper • 2304.05288 • Published • 1 -
Progressive Learning without Forgetting
Paper • 2211.15215 • Published • 1 -
Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation
Paper • 2211.12292 • Published • 1 -
Dynamic Y-KD: A Hybrid Approach to Continual Instance Segmentation
Paper • 2303.06015 • Published • 1 -
Forget-free Continual Learning with Soft-Winning SubNetworks
Paper • 2303.14962 • Published • 2 -
Exclusive Supermask Subnetwork Training for Continual Learning
Paper • 2210.10209 • Published • 1 -
Continual Task Allocation in Meta-Policy Network via Sparse Prompting
Paper • 2305.18444 • Published • 1 -
SparCL: Sparse Continual Learning on the Edge
Paper • 2209.09476 • Published • 2 -
Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates
Paper • 2308.14831 • Published • 2 -
Plug-and-Play Knowledge Injection for Pre-trained Language Models
Paper • 2305.17691 • Published • 1 -
Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models
Paper • 2307.14430 • Published • 3 -
Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
Paper • 2310.02304 • Published • 1 -
Towards Teachable Conversational Agents
Paper • 2102.10387 • Published • 1 -
When Giant Language Brains Just Aren't Enough! Domain Pizzazz with Knowledge Sparkle Dust
Paper • 2305.07230 • Published • 2 -
Bayesian active learning for production, a systematic study and a reusable library
Paper • 2006.09916 • Published • 1 -
Continual Learning: Applications and the Road Forward
Paper • 2311.11908 • Published • 1 -
Continual Learning with Low Rank Adaptation
Paper • 2311.17601 • Published • 1 -
Continual Model-Based Reinforcement Learning with Hypernetworks
Paper • 2009.11997 • Published • 1 -
Continual learning with hypernetworks
Paper • 1906.00695 • Published • 1 -
Orthogonal Subspace Learning for Language Model Continual Learning
Paper • 2310.14152 • Published • 2 -
Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting
Paper • 2308.07939 • Published • 1 -
On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code
Paper • 2305.04106 • Published • 1 -
ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale
Paper • 2207.09078 • Published • 1 -
Deep Lifelong Cross-modal Hashing
Paper • 2304.13357 • Published • 1 -
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Paper • 2403.08763 • Published • 51 -
Hard ASH: Sparsity and the right optimizer make a continual learner
Paper • 2404.17651 • Published -
HyperInterval: Hypernetwork approach to training weight interval regions in continual learning
Paper • 2405.15444 • Published -
On Sequential Loss Approximation for Continual Learning
Paper • 2405.16498 • Published -
Learning Continually by Spectral Regularization
Paper • 2406.06811 • Published -
Lifelong Machine Learning Potentials
Paper • 2303.05911 • Published