Copertina

SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Le, Feng, Erhu, Xia, Yubin, Chen, Haibo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MobiFlow: Real-World Mobile Agent Benchmarking through Trajectory Fusion
di: Feng, Yunfei, et al.
Pubblicazione: (2026)

Revisiting the Plastic Surgery Hypothesis via Large Language Models
di: Xia, Chunqiu Steven, et al.
Pubblicazione: (2023)

Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation
di: Chen, Le, et al.
Pubblicazione: (2023)

Fuzz4All: Universal Fuzzing with Large Language Models
di: Xia, Chunqiu Steven, et al.
Pubblicazione: (2023)

LEGION: Harnessing Pre-trained Language Models for GitHub Topic Recommendations with Distribution-Balance Loss
di: Dang, Yen-Trang, et al.
Pubblicazione: (2024)

Applying Large Language Models to Issue Classification: Revisiting with Extended Data and New Models
di: Aracena, Gabriel, et al.
Pubblicazione: (2025)

SkillScope: A Tool to Predict Fine-Grained Skills Needed to Solve Issues on GitHub
di: Carter, Benjamin C., et al.
Pubblicazione: (2025)

Toward Automated Hypervisor Scenario Generation Based on VM Workload Profiling for Resource-Constrained Environments
di: Kim, Hyunwoo, et al.
Pubblicazione: (2025)

SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories
di: Soni, Aditya Bharat, et al.
Pubblicazione: (2026)

DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilities
di: Zhang, Tiehua, et al.
Pubblicazione: (2023)

PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)
di: Nazzal, Mahmoud, et al.
Pubblicazione: (2024)

Revisiting Process versus Product Metrics: a Large Scale Analysis
di: Majumder, Suvodeep, et al.
Pubblicazione: (2020)

RAHN: A Reputation Based Hourglass Network for Web Service QoS Prediction
di: Chen, Xia, et al.
Pubblicazione: (2025)

One Model, Many Skills: Parameter-Efficient Fine-Tuning for Multitask Code Analysis
di: Akli, Amal, et al.
Pubblicazione: (2026)

Disproving Program Equivalence with LLMs
di: Allamanis, Miltiadis, et al.
Pubblicazione: (2025)

Signature in Code Backdoor Detection, how far are we?
di: Le, Quoc Hung, et al.
Pubblicazione: (2025)

Teaching Code Refactoring Using LLMs
di: Khairnar, Anshul, et al.
Pubblicazione: (2025)

Towards Verified Code Reasoning by LLMs
di: Sistla, Meghana, et al.
Pubblicazione: (2025)

MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks
di: Li, Jingyao, et al.
Pubblicazione: (2023)

LLMs as Compiler for Arabic Programming Language
di: Sibaee, Serry, et al.
Pubblicazione: (2024)

OSS-Bench: Benchmark Generator for Coding LLMs
di: Jiang, Yuancheng, et al.
Pubblicazione: (2025)

Understanding Robustness of Model Editing in Code LLMs
di: Chhetri, Vinaik, et al.
Pubblicazione: (2025)

It's LIT! Reliability-Optimized LLMs with Inspectable Tools
di: Zhang, Ruixin, et al.
Pubblicazione: (2025)

Breaking the Silence: the Threats of Using LLMs in Software Engineering
di: Sallou, June, et al.
Pubblicazione: (2023)

CigaR: Cost-efficient Program Repair with LLMs
di: Hidvégi, Dávid, et al.
Pubblicazione: (2024)

Automating API Documentation with LLMs: A BERTopic Approach
di: Naghshzan, AmirHossein
Pubblicazione: (2025)

ThrowBench: Benchmarking LLMs by Predicting Runtime Exceptions
di: Prenner, Julian Aron, et al.
Pubblicazione: (2025)

Unsupervised Evaluation of Code LLMs with Round-Trip Correctness
di: Allamanis, Miltiadis, et al.
Pubblicazione: (2024)

iServe: An Intent-based Serving System for LLMs
di: Liakopoulos, Dimitrios, et al.
Pubblicazione: (2025)

RLHGNN: Reinforcement Learning-driven Heterogeneous Graph Neural Network for Next Activity Prediction in Business Processes
di: Wang, Jiaxing, et al.
Pubblicazione: (2025)

Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
di: Tahimic, Kriz, et al.
Pubblicazione: (2025)

SPELL: Synthesis of Programmatic Edits using LLMs
di: Ramos, Daniel, et al.
Pubblicazione: (2026)

TritonRL: Training LLMs to Think and Code Triton Without Cheating
di: Woo, Jiin, et al.
Pubblicazione: (2025)

K-ASTRO: Structure-Aware Adaptation of LLMs for Code Vulnerability Detection
di: Zhang, Yifan, et al.
Pubblicazione: (2022)

Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs
di: Haque, Mirazul, et al.
Pubblicazione: (2025)

Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT
di: Xia, Chunqiu Steven, et al.
Pubblicazione: (2023)

ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents
di: Rafique, Mofasshara, et al.
Pubblicazione: (2026)

Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks
di: Sharifloo, Amir Molzam, et al.
Pubblicazione: (2025)

CPP-UT-Bench: Can LLMs Write Complex Unit Tests in C++?
di: Bhargava, Vaishnavi, et al.
Pubblicazione: (2024)

Leveraging LLMs for Legacy Code Modernization: Challenges and Opportunities for LLM-Generated Documentation
di: Diggs, Colin, et al.
Pubblicazione: (2024)