Imagen de Portada

A Collision-Free Hot-Tier Extension for Engram-Style Conditional Memory: A Controlled Study of Training Dynamics

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Lin, Tao
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
por: Zhang, Haozhen, et al.
Publicado: (2026)

AdaFRUGAL: Adaptive Memory-Efficient Training with Dynamic Control
por: Bui, Quang-Hung, et al.
Publicado: (2025)

Training-Free Exponential Context Extension via Cascading KV Cache
por: Willette, Jeffrey, et al.
Publicado: (2024)

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
por: Xiao, Chaojun, et al.
Publicado: (2024)

UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models
por: Gu, Xiaojie, et al.
Publicado: (2025)

Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
por: Song, Haobo, et al.
Publicado: (2024)

ThermoQA: A Three-Tier Benchmark for Evaluating Thermodynamic Reasoning in Large Language Models
por: Düzkar, Kemal
Publicado: (2026)

StyleRec: A Benchmark Dataset for Prompt Recovery in Writing Style Transformation
por: Liu, Shenyang, et al.
Publicado: (2025)

TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference
por: Dzikanyanga, Gradwell, et al.
Publicado: (2026)

2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings
por: Wang, Yumeng, et al.
Publicado: (2025)

Memory-Efficient LLM Training with Online Subspace Descent
por: Liang, Kaizhao, et al.
Publicado: (2024)

Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
por: Zhang, Jun, et al.
Publicado: (2025)

Echo: A Large Language Model with Temporal Episodic Memory
por: Liu, WenTao, et al.
Publicado: (2025)

LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems
por: Wang, Zhiyuan, et al.
Publicado: (2025)

A Framework for Inference Inspired by Human Memory Mechanisms
por: Zeng, Xiangyu, et al.
Publicado: (2023)

Cold-Start Personalization via Training-Free Priors from Structured World Models
por: Bose, Avinandan, et al.
Publicado: (2026)

POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
por: Qiu, Zeju, et al.
Publicado: (2026)

Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control
por: Rezazadeh, Alireza, et al.
Publicado: (2025)

Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB
por: Ren, Xingyu, et al.
Publicado: (2025)

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
por: Lin, Weizhe, et al.
Publicado: (2025)

ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer
por: Liu, Dongqi, et al.
Publicado: (2023)

Query-Conditioned Test-Time Self-Training for Large Language Models
por: Song, Chaehee, et al.
Publicado: (2026)

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning
por: Kim, Minwu, et al.
Publicado: (2026)

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit
por: Goddard, Charles, et al.
Publicado: (2025)

ELSA: A Style Aligned Dataset for Emotionally Intelligent Language Generation
por: Gandhi, Vishal, et al.
Publicado: (2025)

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
por: Liu, Yang, et al.
Publicado: (2026)

LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs
por: Kim, Taeho, et al.
Publicado: (2024)

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
por: Nguyen, Dang, et al.
Publicado: (2024)

Improving Autoregressive Training with Dynamic Oracles
por: Yang, Jianing, et al.
Publicado: (2024)

Diagnosing Medical Datasets with Training Dynamics
por: Wenderoth, Laura
Publicado: (2024)

Probing the Limits of Compressive Memory: A Study of Infini-Attention in Small-Scale Pretraining
por: Huang, Ruizhe, et al.
Publicado: (2025)

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
por: Shi, Haizhou, et al.
Publicado: (2024)

Memory-efficient Energy-adaptive Inference of Pre-Trained Models on Batteryless Embedded Systems
por: Farina, Pietro, et al.
Publicado: (2024)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
por: Deiseroth, Björn, et al.
Publicado: (2024)

Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers
por: Gong, Zixuan, et al.
Publicado: (2025)

DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing
por: Ma, Xinyu, et al.
Publicado: (2025)

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
por: Liu, Wei, et al.
Publicado: (2025)

Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training
por: Mistry, Deven Mahesh, et al.
Publicado: (2025)

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training
por: Shivagunde, Namrata, et al.
Publicado: (2026)

Enhancing NLP Robustness and Generalization through LLM-Generated Contrast Sets: A Scalable Framework for Systematic Evaluation and Adversarial Training
por: Lin, Hender
Publicado: (2025)