Cover Image

FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Isaac, Park, Sangyeon, Oh, Seungwon, Kim, Donghu, Lee, Hojoon, Kim, Kyung-Joong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
by: Park, Sangyeon, et al.
Published: (2025)

Recovering Plasticity of Neural Networks via Soft Weight Rescaling
by: Oh, Seungwon, et al.
Published: (2025)

Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning
by: Kim, Kyungbeom, et al.
Published: (2026)

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
by: Lee, Hojoon, et al.
Published: (2024)

Do's and Don'ts: Learning Desirable Skills with Instruction Videos
by: Kim, Hyunseung, et al.
Published: (2024)

Dynamic Mixture of Experts Against Severe Distribution Shifts
by: Kim, Donghu
Published: (2025)

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
by: Kim, Donghu, et al.
Published: (2024)

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning
by: Lee, Hojoon, et al.
Published: (2024)

Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity
by: Su, Zhiyuan, et al.
Published: (2025)

Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL
by: Kim, Sung-Hyun, et al.
Published: (2025)

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess
by: Hwang, Dongyoon, et al.
Published: (2025)

IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation
by: Baek, In-Chang, et al.
Published: (2025)

AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents
by: Kim, Hojoon, et al.
Published: (2026)

Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation
by: Baek, In-Chang, et al.
Published: (2026)

Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning
by: Lan, Jiahua, et al.
Published: (2025)

Frictional Q-Learning
by: Kim, Hyunwoo, et al.
Published: (2025)

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
by: Oh, YongKyung, et al.
Published: (2024)

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
by: Oh, YongKyung, et al.
Published: (2025)

DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis
by: Oh, YongKyung, et al.
Published: (2024)

Alternating Approach-Putt Models for Multi-Stage Speech Enhancement
by: Jeong, Iksoon, et al.
Published: (2025)

Asymptotic Midpoint Mixup for Margin Balancing and Moderate Broadening
by: Kim, Hoyong, et al.
Published: (2024)

A Scalable and Transferable Time Series Prediction Framework for Demand Forecasting
by: Park, Young-Jin, et al.
Published: (2024)

Stability Analysis of Sharpness-Aware Minimization
by: Kim, Hoki, et al.
Published: (2023)

CUBE: Contrastive Understanding by Balanced Experiments
by: Kim, Dongseok, et al.
Published: (2025)

Position: State-of-the-Art Claims Require State-of-the-Art Evidence
by: Oh, YongKyung
Published: (2026)

Attention-Based Neural-Augmented Kalman Filter for Legged Robot State Estimation
by: Lee, Seokju, et al.
Published: (2026)

Hyperspherical Normalization for Scalable Deep Reinforcement Learning
by: Lee, Hojoon, et al.
Published: (2025)

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
by: Qiu, Haomiao, et al.
Published: (2025)

TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
by: Oh, YongKyung, et al.
Published: (2025)

Isometry pursuit
by: Koelle, Samson, et al.
Published: (2024)

Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative Decoding
by: Park, Jihoon, et al.
Published: (2025)

Comprehensive Review of Neural Differential Equations for Time Series Analysis
by: Oh, YongKyung, et al.
Published: (2025)

Grouped Differential Attention
by: Lim, Junghwan, et al.
Published: (2025)

Subgraph Federated Learning for Local Generalization
by: Kim, Sungwon, et al.
Published: (2025)

Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation
by: Elenter, Juan, et al.
Published: (2023)

Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysis
by: Oh, YongKyung, et al.
Published: (2025)

JPmHC Dynamical Isometry via Orthogonal Hyper-Connections
by: Sengupta, Biswa, et al.
Published: (2026)

Adversarial Environment Design via Regret-Guided Diffusion Models
by: Chung, Hojun, et al.
Published: (2024)

Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement
by: Lee, Sanghyun, et al.
Published: (2025)

Importance Analysis for Dynamic Control of Balancing Parameter in a Simple Knowledge Distillation Setting
by: Kim, Seongmin, et al.
Published: (2025)