Copertina

Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Muttakhiroh, Iing, Fevens, Thomas
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation
di: Muttakhiroh, Iing, et al.
Pubblicazione: (2025)

Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learning
di: Kong, Jiangtao, et al.
Pubblicazione: (2024)

Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks
di: Pink, Mathis, et al.
Pubblicazione: (2024)

Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
di: Liu, Jinyi, et al.
Pubblicazione: (2023)

Non-Uniform Memory Sampling in Experience Replay
di: Krutsylo, Andrii
Pubblicazione: (2025)

Efficient RL Training for LLMs with Experience Replay
di: Arnal, Charles, et al.
Pubblicazione: (2026)

Graph Continual Learning with Debiased Lossless Memory Replay
di: Niu, Chaoxi, et al.
Pubblicazione: (2024)

SMR: State Memory Replay for Long Sequence Modeling
di: Qi, Biqing, et al.
Pubblicazione: (2024)

FETCH: A Memory-Efficient Replay Approach for Continual Learning in Image Classification
di: Weißflog, Markus, et al.
Pubblicazione: (2024)

MGSER-SAM: Memory-Guided Soft Experience Replay with Sharpness-Aware Optimization for Enhanced Continual Learning
di: Li, Xingyu, et al.
Pubblicazione: (2024)

Autoencoder-Based Hybrid Replay for Class-Incremental Learning
di: Nori, Milad Khademi, et al.
Pubblicazione: (2025)

FullRecall: A Semantic Search-Based Ranking Approach for Maximizing Recall in Patent Retrieval
di: Ali, Amna, et al.
Pubblicazione: (2025)

Continual Learning for non-stationary regression via Memory-Efficient Replay
di: García-Santaclara, Pablo, et al.
Pubblicazione: (2026)

Exploring Precision and Recall to assess the quality and diversity of LLMs
di: Bronnec, Florian Le, et al.
Pubblicazione: (2024)

Adaptive Memory Replay for Continual Learning
di: Smith, James Seale, et al.
Pubblicazione: (2024)

COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs
di: Liu, Liming, et al.
Pubblicazione: (2025)

Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs
di: Lei, Ge, et al.
Pubblicazione: (2025)

Understanding Factual Recall in Transformers via Associative Memories
di: Nichani, Eshaan, et al.
Pubblicazione: (2024)

LongRecall: A Structured Approach for Robust Recall Evaluation in Long-Form Text
di: Ardestani, MohamamdJavad, et al.
Pubblicazione: (2025)

Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
di: Chughtai, Bilal, et al.
Pubblicazione: (2024)

Dynamic Proxy-Mixing: Transferring Replay Controllers from Small to Large Models for Continual Instruction Tuning
di: Shihab, Ibne Farabi, et al.
Pubblicazione: (2026)

Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion
di: Cheng, Shaoxu, et al.
Pubblicazione: (2024)

AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning
di: Li, Xingyu, et al.
Pubblicazione: (2023)

Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
di: Zhang, Kongcheng, et al.
Pubblicazione: (2025)

On Enhancing Root Cause Analysis with SQL Summaries for Failures in Database Workload Replays at SAP HANA
di: Jambigi, Neetha, et al.
Pubblicazione: (2024)

Self-generated Replay Memories for Continual Neural Machine Translation
di: Resta, Michele, et al.
Pubblicazione: (2024)

Associative Memory Based Experience Replay for Deep Reinforcement Learning
di: Li, Mengyuan, et al.
Pubblicazione: (2022)

Replay-Free Continual Low-Rank Adaptation with Dynamic Memory
di: Chen, Huancheng, et al.
Pubblicazione: (2024)

Prioritized Generative Replay
di: Wang, Renhao, et al.
Pubblicazione: (2024)

Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems
di: Minhas, Mishal Fatima, et al.
Pubblicazione: (2025)

Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall
di: Yuan, Jiaqing, et al.
Pubblicazione: (2024)

GaussDetect-LiNGAM:Causal Direction Identification without Gaussianity test
di: Ding, Ziyi, et al.
Pubblicazione: (2025)

Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
di: Niu, Chaoxi, et al.
Pubblicazione: (2024)

RePO: Replay-Enhanced Policy Optimization
di: Li, Siheng, et al.
Pubblicazione: (2025)

Why Can't I See My Clusters? A Precision-Recall Approach to Dimensionality Reduction Validation
di: van der Hoorn, Diede P. M., et al.
Pubblicazione: (2025)

MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
di: Lu, Yiyang, et al.
Pubblicazione: (2026)

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
di: Yu, Yongcan, et al.
Pubblicazione: (2024)

CoMemNet: Contrastive Sampling with Memory Replay Network for Continual Traffic Prediction
di: Wu, Mei, et al.
Pubblicazione: (2026)

Uncertainty Prioritized Experience Replay
di: Carrasco-Davis, Rodrigo, et al.
Pubblicazione: (2025)

Revisiting Experience Replayable Conditions
di: Kobayashi, Taisuke
Pubblicazione: (2024)