Cover Image

TNT: Improving Chunkwise Training for Test-Time Memorization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zeman, Behrouz, Ali, Deng, Yuan, Zhong, Peilin, Kacham, Praneeth, Karami, Mahdi, Razaviyayn, Meisam, Mirrokni, Vahab
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

ATLAS: Learning to Optimally Memorize the Context at Test Time
by: Behrouz, Ali, et al.
Published: (2025)

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
by: Behrouz, Ali, et al.
Published: (2025)

Memory Caching: RNNs with Growing Memory
by: Behrouz, Ali, et al.
Published: (2026)

Nested Learning: The Illusion of Deep Learning Architectures
by: Behrouz, Ali, et al.
Published: (2025)

Titans: Learning to Memorize at Test Time
by: Behrouz, Ali, et al.
Published: (2024)

Trellis: Learning to Compress Key-Value Memory in Attention Models
by: Karami, Mahdi, et al.
Published: (2025)

Sampling and Loss Weights in Multi-Domain Training
by: Salmani, Mahdi, et al.
Published: (2025)

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
by: Li, Zeman, et al.
Published: (2025)

PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels
by: Kacham, Praneeth, et al.
Published: (2023)

Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models
by: Li, Zeman, et al.
Published: (2024)

PolarQuant: Quantizing KV Caches with Polar Transformation
by: Han, Insu, et al.
Published: (2025)

Lattice: Learning to Efficiently Compress the Memory
by: Karami, Mahdi, et al.
Published: (2025)

MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling
by: Karami, Mahdi, et al.
Published: (2025)

Understanding the Role of Training Data in Test-Time Scaling
by: Javanmard, Adel, et al.
Published: (2025)

Synthetic Text Generation for Training Large Language Models via Gradient Matching
by: Nguyen, Dang, et al.
Published: (2025)

ECO: Quantized Training without Full-Precision Master Weights
by: Nikdan, Mahdi, et al.
Published: (2026)

Less is More: Convergence Benefits of Fewer Data Weight Updates over Longer Horizon
by: Das, Rudrajit, et al.
Published: (2026)

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
by: Javanmard, Adel, et al.
Published: (2026)

High-Dimensional Geometric Streaming for Nearly Low Rank Data
by: Esfandiari, Hossein, et al.
Published: (2024)

Optimal Communication for Classic Functions in the Coordinator Model and Beyond
by: Esfandiari, Hossein, et al.
Published: (2024)

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
by: Behrouz, Ali, et al.
Published: (2024)

Early Stopping for Large Reasoning Models via Confidence Dynamics
by: Hosseini, Parsa, et al.
Published: (2026)

SubGen: Token Generation in Sublinear Time and Memory
by: Zandieh, Amir, et al.
Published: (2024)

Optimal Differentially Private Model Training with Public Data
by: Lowy, Andrew, et al.
Published: (2023)

Optimistic Rates for Learning from Label Proportions
by: Li, Gene, et al.
Published: (2024)

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
by: Zhang, Xinwei, et al.
Published: (2024)

Differentially Private Synthetic Data Release for Topics API Outputs
by: Dick, Travis, et al.
Published: (2025)

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
by: Zandieh, Amir, et al.
Published: (2025)

Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
by: Javanmard, Adel, et al.
Published: (2024)

Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
by: Behrouz, Ali, et al.
Published: (2024)

Memorization Sinks: Isolating Memorization during LLM Training
by: Ghosal, Gaurav R., et al.
Published: (2025)

Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation
by: Chen, Hong, et al.
Published: (2026)

Understanding Transformer Reasoning Capabilities via Graph Algorithms
by: Sanford, Clayton, et al.
Published: (2024)

f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
by: Panda, Subhodip, et al.
Published: (2025)

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling
by: Rodkin, Ivan, et al.
Published: (2025)

Test Time Training for Supervised Causal Learning
by: Deng, Zizhen, et al.
Published: (2026)

Output Perturbation for Differentially Private Convex Optimization: Faster and More General
by: Lowy, Andrew, et al.
Published: (2021)

Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize
by: Ali, Sarwan
Published: (2026)

Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
by: Epasto, Alessandro, et al.
Published: (2022)

Membership and Memorization in LLM Knowledge Distillation
by: Zhang, Ziqi, et al.
Published: (2025)