Cover Image

On Understanding of the Dynamics of Model Capacity in Continual Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chakraborty, Supriyo, Raghavan, Krishnan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning
by: Mircea, Andrei, et al.
Published: (2025)

The Impossibility of Inverse Permutation Learning in Transformer Models
by: Alur, Rohan, et al.
Published: (2025)

Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
by: Zhao, Bo, et al.
Published: (2025)

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
by: Panda, Ashwinee, et al.
Published: (2025)

SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation
by: Kapusuzoglu, Berkcan, et al.
Published: (2025)

Self-Controlled Dynamic Expansion Model for Continual Learning
by: Wu, Runqing, et al.
Published: (2025)

The Effect of Architecture During Continual Learning
by: Hahn, Allyson, et al.
Published: (2026)

Capacity-Constrained Continual Learning
by: Wen, Zheng, et al.
Published: (2025)

LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
by: Veldanda, Akshaj Kumar, et al.
Published: (2024)

Understanding the Dynamics of Demonstration Conflict in In-Context Learning
by: Jiao, Difan, et al.
Published: (2026)

Understanding the Learning Dynamics of Alignment with Human Feedback
by: Im, Shawn, et al.
Published: (2024)

Learning Regularizers: Learning Optimizers that can Regularize
by: Sahoo, Suraj Kumar, et al.
Published: (2025)

Dynamic Graph Structure Estimation for Learning Multivariate Point Process using Spiking Neural Networks
by: Chakraborty, Biswadeep, et al.
Published: (2025)

Condensation-Concatenation Framework for Dynamic Graph Continual Learning
by: Yan, Tingxu, et al.
Published: (2025)

CLeAN: Continual Learning Adaptive Normalization in Dynamic Environments
by: Marasco, Isabella, et al.
Published: (2026)

An Effective Dynamic Gradient Calibration Method for Continual Learning
by: Lin, Weichen, et al.
Published: (2024)

Calibration of Continual Learning Models
by: Li, Lanpei, et al.
Published: (2024)

Divide And Conquer: Learning Chaotic Dynamical Systems With Multistep Penalty Neural Ordinary Differential Equations
by: Chakraborty, Dibyajyoti, et al.
Published: (2024)

SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs
by: Jayasuriya, Dinithi, et al.
Published: (2025)

DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning
by: Guo, Haiyang, et al.
Published: (2024)

Continual Learning for Adaptable Car-Following in Dynamic Traffic Environments
by: Chen, Xianda, et al.
Published: (2024)

Information as Structural Alignment: A Dynamical Theory of Continual Learning
by: Negulescu, Radu
Published: (2026)

Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics
by: Ren, Yi, et al.
Published: (2024)

Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models
by: Araujo, Vladimir, et al.
Published: (2024)

Recasting Continual Learning as Sequence Modeling
by: Lee, Soochan, et al.
Published: (2023)

Energy-Based Models for Continual Learning
by: Li, Shuang, et al.
Published: (2020)

Measurement Scheduling for ICU Patients with Offline Reinforcement Learning
by: Ji, Zongliang, et al.
Published: (2024)

Noise-Tolerant Coreset-Based Class Incremental Continual Learning
by: Mucllari, Edison, et al.
Published: (2025)

Goal Discovery with Causal Capacity for Efficient Reinforcement Learning
by: Yu, Yan, et al.
Published: (2025)

Learning Dynamics in Continual Pre-Training for Large Language Models
by: Wang, Xingjin, et al.
Published: (2025)

Fast and Featureless Node Representation Learning with Partial Pairwise Supervision
by: Chakraborty, Sujan, et al.
Published: (2026)

Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation
by: Angelini, Christopher, et al.
Published: (2025)

Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs
by: Horoi, Stefan, et al.
Published: (2025)

Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
by: Balef, Amir Rezaei, et al.
Published: (2026)

Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs
by: Vijayaraj, Raj Krishnan
Published: (2025)

A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks
by: Chakraborty, Biswadeep, et al.
Published: (2024)

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off
by: Lai, Song, et al.
Published: (2025)

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
by: Zhao, Chongyang, et al.
Published: (2026)

STX-Search: Explanation Search for Continuous Dynamic Spatio-Temporal Models
by: Anwar, Saif, et al.
Published: (2025)

ED2: Environment Dynamics Decomposition World Models for Continuous Control
by: Hao, Jianye, et al.
Published: (2021)