Copertina

Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Baroian, Andrei, Notebomer, Kasper
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Supervised Fine-Tuning or In-Context Learning? Evaluating LLMs for Clinical NER
di: Baroian, Andrei
Pubblicazione: (2025)

Towards Transparency: Exploring LLM Trainings Datasets through Visual Topic Modeling and Semantic Frame
di: de Dampierre, Charles, et al.
Pubblicazione: (2024)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
di: Taniguchi, Rei, et al.
Pubblicazione: (2026)

How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization
di: Song, Shezheng, et al.
Pubblicazione: (2025)

Scaling LLM Pre-training with Vocabulary Curriculum
di: Yu, Fangyuan
Pubblicazione: (2025)

Beyond Public Access in LLM Pre-Training Data
di: Rosenblat, Sruly, et al.
Pubblicazione: (2025)

Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts
di: Baroian, Andrei, et al.
Pubblicazione: (2026)

Reverse Training to Nurse the Reversal Curse
di: Golovneva, Olga, et al.
Pubblicazione: (2024)

LLMCache: Layer-Wise Caching Strategies for Accelerated Reuse in Transformer Inference
di: Bansal, Harsh Vardhan
Pubblicazione: (2025)

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
di: Shu, Huizhen, et al.
Pubblicazione: (2025)

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
di: Hu, Chenhui, et al.
Pubblicazione: (2024)

A Study on Hidden Layer Distillation for Large Language Model Pre-Training
di: Guigon, Maxime, et al.
Pubblicazione: (2026)

Investigating Cost-Efficiency of LLM-Generated Training Data for Conversational Semantic Frame Analysis
di: Matta, Shiho, et al.
Pubblicazione: (2024)

Layer-Wise Evolution of Representations in Fine-Tuned Transformers: Insights from Sparse AutoEncoders
di: Nadipalli, Suneel
Pubblicazione: (2025)

Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?
di: Ghahroodi, Omid, et al.
Pubblicazione: (2024)

LPCD: Unified Framework from Layer-Wise to Submodule Quantization
di: Ichikawa, Yuma, et al.
Pubblicazione: (2025)

AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs
di: Kang, Feiyang, et al.
Pubblicazione: (2024)

Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities
di: Fujii, Kazuki, et al.
Pubblicazione: (2024)

KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
di: Li, Xing, et al.
Pubblicazione: (2025)

LESA: Learnable LLM Layer Scaling-Up
di: Yang, Yifei, et al.
Pubblicazione: (2025)

Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training
di: Jiang, Changhao, et al.
Pubblicazione: (2025)

Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
di: Du, Wenyu, et al.
Pubblicazione: (2024)

Rethinking Reflection in Pre-Training
di: AI, Essential, et al.
Pubblicazione: (2025)

Adaptive Layer-skipping in Pre-trained LLMs
di: Luo, Xuan, et al.
Pubblicazione: (2025)

LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation
di: Wu, Haihang
Pubblicazione: (2024)

Evaluating Expert Contributions in a MoE LLM for Quiz-Based Tasks
di: Chernov, Andrei
Pubblicazione: (2025)

Memory Layers at Scale
di: Berges, Vincent-Pierre, et al.
Pubblicazione: (2024)

Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance
di: Zheng, Weihua, et al.
Pubblicazione: (2026)

DataFrame QA: A Universal LLM Framework on DataFrame Question Answering Without Data Exposure
di: Ye, Junyi, et al.
Pubblicazione: (2024)

Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
di: Sim, Woo Seob, et al.
Pubblicazione: (2026)

KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing
di: Yang, Yifei, et al.
Pubblicazione: (2024)

Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers
di: Ye, Donald
Pubblicazione: (2026)

Unraveling Emotions with Pre-Trained Models
di: Pajón-Sanmartín, Alejandro, et al.
Pubblicazione: (2025)

When Wording Steers the Evaluation: Framing Bias in LLM judges
di: Hwang, Yerin, et al.
Pubblicazione: (2026)

SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
di: Djuhera, Aladin, et al.
Pubblicazione: (2025)

NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoning
di: Zhang, Yulong, et al.
Pubblicazione: (2025)

ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training
di: Zhuo, Le, et al.
Pubblicazione: (2024)

Less is More: Pre-Training Cross-Lingual Small-Scale Language Models with Cognitively-Plausible Curriculum Learning Strategies
di: Salhan, Suchir, et al.
Pubblicazione: (2024)

Evolution of Concepts in Language Model Pre-Training
di: Ge, Xuyang, et al.
Pubblicazione: (2025)

Reversing Large Language Models for Efficient Training and Fine-Tuning
di: Gal, Eshed, et al.
Pubblicazione: (2025)