Image de couverture de livre

On the Limits of Layer Pruning for Generative Reasoning in Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shrestha, Safal, Shrestha, Anubhav, Nepal, Aadim, Kim, Minwu, Ross, Keith
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training
par: Nepal, Aadim, et autres
Publié: (2025)

Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings
par: Shrestha, Safal, et autres
Publié: (2025)

Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning
par: Kim, Minwu, et autres
Publié: (2025)

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning
par: Kim, Minwu, et autres
Publié: (2026)

Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges
par: Shrestha, Safal, et autres
Publié: (2025)

Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
par: Datta, Shrestha, et autres
Publié: (2026)

Distribution Matching via Generalized Consistency Models
par: Shrestha, Sagar, et autres
Publié: (2025)

The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
par: Lu, Yao, et autres
Publié: (2025)

Content-Style Learning from Unaligned Domains: Identifiability under Unknown Latent Dimensions
par: Shrestha, Sagar, et autres
Publié: (2024)

Diversified Flow Matching with Translation Identifiability
par: Shrestha, Sagar, et autres
Publié: (2025)

Properties that allow or prohibit transferability of adversarial attacks among quantized networks
par: Shrestha, Abhishek, et autres
Publié: (2024)

Beyond Linear Surrogates: High-Fidelity Local Explanations for Black-Box Models
par: Shrestha, Sanjeev, et autres
Publié: (2025)

Trust-Based Incentive Mechanisms in Semi-Decentralized Federated Learning Systems
par: Shrestha, Ajay Kumar
Publié: (2026)

Symmetric Pruning of Large Language Models
par: Yi, Kai, et autres
Publié: (2025)

GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
par: Liu, Xiaoyun, et autres
Publié: (2026)

SwiftPrune: Hessian-Free Weight Pruning for Large Language Models
par: Kang, Yuhan, et autres
Publié: (2025)

Exploring Federated Pruning for Large Language Models
par: Guo, Pengxin, et autres
Publié: (2025)

Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
par: Timilsina, Subash, et autres
Publié: (2024)

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
par: Mirzadeh, Iman, et autres
Publié: (2024)

COPAL: Continual Pruning in Large Language Generative Models
par: Malla, Srikanth, et autres
Publié: (2024)

Large Language Model Pruning
par: Huang, Hanjuan, et autres
Publié: (2024)

Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2
par: Abreu, Steven, et autres
Publié: (2025)

E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data
par: Azizpour, Aref, et autres
Publié: (2024)

A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models
par: Lu, Yao, et autres
Publié: (2024)

Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning
par: Ioannou, Antreas, et autres
Publié: (2025)

Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models
par: Wang, Ziyan, et autres
Publié: (2025)

DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
par: Shrestha, Aayam, et autres
Publié: (2020)

Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
par: Shrestha, Susav, et autres
Publié: (2025)

On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning
par: Kurz, Simon, et autres
Publié: (2024)

Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
par: Shrestha, Rajesh, et autres
Publié: (2026)

Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
par: Shrestha, Sagar, et autres
Publié: (2024)

LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models
par: Mozaffari, Mohammad, et autres
Publié: (2026)

Measuring Sample Importance in Data Pruning for Language Models based on Information Entropy
par: Kim, Minsang, et autres
Publié: (2024)

Token-Driven GammaTune: Adaptive Calibration for Enhanced Speculative Decoding
par: Gautam, Aayush, et autres
Publié: (2025)

ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models
par: Wu, Zixuan, et autres
Publié: (2025)

Pruning and Distilling Mixture-of-Experts into Dense Language Models
par: Kim, Junhyuck, et autres
Publié: (2026)

LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models
par: Hoffmann, David, et autres
Publié: (2024)

Content-Style Identification via Differential Independence
par: Timilsina, Subash, et autres
Publié: (2026)

Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization
par: Shrestha, Jatan, et autres
Publié: (2026)

IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining
par: Li, Yixiao, et autres
Publié: (2025)