Image de couverture de livre

Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Puccioni, Laura, Farshin, Alireza, Scazzariello, Mariano, Wang, Changjie, Chiesa, Marco, Kostic, Dejan
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Software Engineering I.2.2; I.2.6; D.1.2
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

From Scientific Texts to Verifiable Code: Automating the Process with Transformers
par: Wang, Changjie, et autres
Publié: (2025)

Scattered Forest Search: Smarter Code Space Exploration with LLMs
par: Light, Jonathan, et autres
Publié: (2024)

LLM Agents for Generating Microservice-based Applications: how complex is your specification?
par: Yellin, Daniel M.
Publié: (2025)

SiliconMind-V1: Multi-Agent Distillation and Debug-Reasoning Workflows for Verilog Code Generation
par: Chen, Mu-Chi, et autres
Publié: (2026)

Optimizing Large Language Models for OpenAPI Code Completion
par: Petryshyn, Bohdan, et autres
Publié: (2024)

EyeLayer: Integrating Human Attention Patterns into LLM-Based Code Summarization
par: Zhang, Jiahao, et autres
Publié: (2026)

Can AI Assist in Olympiad Coding
par: Ren, Samuel
Publié: (2025)

AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation
par: He, Kaifeng, et autres
Publié: (2025)

Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis
par: Sharma, Vansh, et autres
Publié: (2025)

AI-assisted JSON Schema Creation and Mapping
par: Neubauer, Felix, et autres
Publié: (2025)

Vision-Guided Iterative Refinement for Frontend Code Generation
par: Sansford, Hannah, et autres
Publié: (2026)

Automated Bug Triaging using Instruction-Tuned Large Language Models
par: Kiashemshaki, Kiana, et autres
Publié: (2025)

VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs
par: Daneshvar, Seyed Shayan, et autres
Publié: (2024)

CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement
par: Borra, Ajay Krishna, et autres
Publié: (2026)

Exploring LLM-based Verilog Code Generation with Data-Efficient Fine-Tuning and Testbench Automation
par: Chen, Mu-Chi, et autres
Publié: (2026)

RelRepair: Enhancing Automated Program Repair by Retrieving Relevant Code
par: Liu, Shunyu, et autres
Publié: (2025)

Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code
par: Haseeb, Muhammad
Publié: (2025)

Survey Transfer Learning: Recycling Data with Silicon Responses
par: Amini, Ali
Publié: (2025)

The Limits of Obliviate: Evaluating Unlearning in LLMs via Stimulus-Knowledge Entanglement-Behavior Framework
par: Shah, Aakriti, et autres
Publié: (2025)

CIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research
par: Savenkov, Vladislav
Publié: (2026)

L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
par: Holt, Samuel, et autres
Publié: (2023)

The Specification as Quality Gate: Three Hypotheses on AI-Assisted Code Review
par: Zietsman, Christo
Publié: (2026)

CIFE: Code Instruction-Following Evaluation
par: Gunnu, Sravani, et autres
Publié: (2025)

RoboGrind: Intuitive and Interactive Surface Treatment with Industrial Robots
par: Alt, Benjamin, et autres
Publié: (2024)

Recurrent Memory-Augmented Transformers with Chunked Attention for Long-Context Language Modeling
par: Kashyap, Ankit
Publié: (2025)

StepScorer: Accelerating Reinforcement Learning with Step-wise Scoring and Psychological Regret Modeling
par: Xu, Zhe
Publié: (2026)

4OPS: Structural Difficulty Modeling in Integer Arithmetic Puzzles
par: Zeytuncu, Yunus E.
Publié: (2026)

PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation
par: Wang, Yuchen, et autres
Publié: (2026)

Review Beats Planning: Dual-Model Interaction Patterns for Code Synthesis
par: Miller, Jan
Publié: (2026)

Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
par: Trooskens, Geert, et autres
Publié: (2026)

DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming
par: Malarkkan, Arun Vignesh, et autres
Publié: (2025)

Grammatically-Guided Sparse Attention for Efficient and Interpretable Transformers
par: Pratyush, Spandan
Publié: (2026)

Examination of Code generated by Large Language Models
par: Beer, Robin, et autres
Publié: (2024)

Evaluating the Limitations of Local LLMs in Solving Complex Programming Challenges
par: Matotek, Kadin, et autres
Publié: (2025)

TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning
par: Beck, Florentin, et autres
Publié: (2025)

Plan with Code: Comparing approaches for robust NL to DSL generation
par: Bassamzadeh, Nastaran, et autres
Publié: (2024)

AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs
par: Ahmed, Sheikh Nazib, et autres
Publié: (2026)

AgentSpawn: Adaptive Multi-Agent Collaboration Through Dynamic Spawning for Long-Horizon Code Generation
par: Costa, Igor
Publié: (2026)

Software Defined Vehicle Code Generation: A Few-Shot Prompting Approach
par: Nguyen, Quang-Dung, et autres
Publié: (2025)

Contrastive Learning-Enhanced Large Language Models for Monolith-to-Microservice Decomposition
par: Sellami, Khaled, et autres
Publié: (2025)