Cover Image

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Joudaki, Amir, Lanzillotta, Giulia, Razlighi, Mohammad Samragh, Mirzadeh, Iman, Alizadeh, Keivan, Hofmann, Thomas, Farajtabar, Mehrdad, Faghri, Fartash
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

Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
by: Samragh, Mohammad, et al.
Published: (2024)

Computational Bottlenecks of Training Small-scale Large Language Models
by: Ashkboos, Saleh, et al.
Published: (2024)

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
by: Mirzadeh, Iman, et al.
Published: (2024)

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
by: Shojaee, Parshin, et al.
Published: (2025)

SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
by: Chegini, Atoosa, et al.
Published: (2024)

LLM in a flash: Efficient Large Language Model Inference with Limited Memory
by: Alizadeh, Keivan, et al.
Published: (2023)

Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models
by: Alizadeh, Keivan, et al.
Published: (2024)

TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
by: Li, Jeffrey, et al.
Published: (2025)

Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
by: Vemulapalli, Raviteja, et al.
Published: (2023)

Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
by: Alizadeh, Keivan, et al.
Published: (2026)

MoE-PHDS: One MoE checkpoint for flexible runtime sparsity
by: Hannah, Lauren. A, et al.
Published: (2025)

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
by: Mehta, Sachin, et al.
Published: (2024)

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
by: Wang, Haoxiang, et al.
Published: (2023)

TiC-CLIP: Continual Training of CLIP Models
by: Garg, Saurabh, et al.
Published: (2023)

Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential
by: Samragh, Mohammad, et al.
Published: (2025)

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
by: Huang, Chen, et al.
Published: (2025)

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
by: Armandpour, Mohammadreza, et al.
Published: (2026)

Heads collapse, features stay: Why Replay needs big buffers
by: Lanzillotta, Giulia, et al.
Published: (2025)

Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations
by: Joudaki, Amir, et al.
Published: (2024)

The hybrid dilemma -- do hybrid technologies play a transitionary or stationary role in transitions processes?
by: Phirouzabadi, Amir Mirzadeh
Published: (2025)

The Importance of Being Lazy: Scaling Limits of Continual Learning
by: Graldi, Jacopo, et al.
Published: (2025)

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2024)

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2023)

Local vs Global continual learning
by: Lanzillotta, Giulia, et al.
Published: (2024)

Revisiting Knowledge Distillation: The Hidden Role of Dataset Size
by: Lanzillotta, Giulia, et al.
Published: (2025)

Algunas consideraciones heurísticas en torno a la formación de grupos intelectuales en el Territorio Nacional de la Pampa
by: María Lanzillotta
Published: (2010)

The path towards contact-based physical human-robot interaction
by: Farajtabar, Mohammad, et al.
Published: (2024)

AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
by: Chowdhury, Sanjoy, et al.
Published: (2025)

SpecMD: A Comprehensive Study On Speculative Expert Prefetching
by: Hoang, Duc, et al.
Published: (2026)

SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
by: Saberi, Mehrdad, et al.
Published: (2026)

MobileCLIP2: Improving Multi-Modal Reinforced Training
by: Faghri, Fartash, et al.
Published: (2025)

MUSCLE: A Model Update Strategy for Compatible LLM Evolution
by: Echterhoff, Jessica, et al.
Published: (2024)

Mathematical Approach in Hybrid Beamforming for ISAC Systems
by: Khosroshahi, Keivan, et al.
Published: (2025)

Test Time Training for AC Power Flow Surrogates via Physics and Operational Constraint Refinement
by: Dogoulis, Panteleimon, et al.
Published: (2025)

Achieving Fine‐Grained Microstructure in Low‐Alloy Steel: A Study on Static Recrystallization Using Experimental and Simulation Approaches
by: Mahdiyeh Baharvand, et al.
Published: (2025)

Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions
by: Razlighi, AmirHossein Naghi, et al.
Published: (2025)

Towards the net zero carbon future: A review of blockchain‐enabled peer‐to‐peer carbon trading
by: Mohammad Parhamfar, et al.
Published: (2024)

Harnessing the Ecological and Genomic Adaptability of the Bacterial Genus Massilia for Environmental and Industrial Applications
by: Kamyar Amirhosseini, et al.
Published: (2025)

Reactivation: Empirical NTK Dynamics Under Task Shifts
by: Liu, Yuzhi, et al.
Published: (2025)

Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder
by: Bittar, Alexandre, et al.
Published: (2023)