Copertina

Towards Understanding What State Space Models Learn About Code

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Jiali, Anand, Abhinav, Verma, Shweta, Mezini, Mira
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CodeSSM: Towards State Space Models for Code Understanding
di: Verma, Shweta, et al.
Pubblicazione: (2025)

Analysis of Long Range Dependency Understanding in State Space Models
di: Ravikumar, Srividya, et al.
Pubblicazione: (2026)

A Critical Study of What Code-LLMs (Do Not) Learn
di: Anand, Abhinav, et al.
Pubblicazione: (2024)

Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning
di: Wu, Mingze, et al.
Pubblicazione: (2026)

Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs
di: Sakharova, Marina, et al.
Pubblicazione: (2025)

Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards
di: Jolfaei, Erfan Aghadavoodi, et al.
Pubblicazione: (2026)

Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown
di: Derstroff, Cedric, et al.
Pubblicazione: (2024)

Adaptable Hindsight Experience Replay for Search-Based Learning
di: Vazaios, Alexandros, et al.
Pubblicazione: (2025)

DeepCodeProbe: Towards Understanding What Models Trained on Code Learn
di: Majdinasab, Vahid, et al.
Pubblicazione: (2024)

From What to Why: Thought-Space Recommendation with Small Language Models
di: Biswas, Prosenjit, et al.
Pubblicazione: (2025)

Can Large Language Models Understand, Reason About, and Generate Code-Switched Text?
di: Winata, Genta Indra, et al.
Pubblicazione: (2026)

Automating the Refinement of Reinforcement Learning Specifications
di: Ambadkar, Tanmay, et al.
Pubblicazione: (2025)

CODESTRUCT: Code Agents over Structured Action Spaces
di: Kim, Myeongsoo, et al.
Pubblicazione: (2026)

Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning
di: Lin, Jiayi, et al.
Pubblicazione: (2024)

Deep Reinforcement Learning for Interference Suppression in RIS-Aided Space-Air-Ground Integrated Networks
di: Mamillapalli, Pujitha, et al.
Pubblicazione: (2026)

What Machine Learning Tells Us About the Mathematical Structure of Concepts
di: Otsuka, Jun
Pubblicazione: (2024)

The Code Barrier: What LLMs Actually Understand?
di: Nikiema, Serge Lionel, et al.
Pubblicazione: (2025)

Learning Lifted Action Models from Traces with Minimal Information About Actions and States
di: Gösgens, Jonas, et al.
Pubblicazione: (2026)

What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding
di: Liu, Siyuan, et al.
Pubblicazione: (2026)

Theory of Code Space: Do Code Agents Understand Software Architecture?
di: Sapunov, Grigory
Pubblicazione: (2026)

Application of artificial intelligence in clinical trials and drug development
di: Addepalli Lakshmi Abhishek, Rachna Varma, Shweta Anand
Pubblicazione: (2026)

What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis
di: Wang, Peiran, et al.
Pubblicazione: (2025)

Celo2: Towards Learned Optimization Free Lunch
di: Moudgil, Abhinav, et al.
Pubblicazione: (2026)

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations
di: Hoang, Huy, et al.
Pubblicazione: (2025)

Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning
di: Wei, Yibing, et al.
Pubblicazione: (2024)

What We Talk About When We Talk About LMs: Implicit Paradigm Shifts and the Ship of Language Models
di: Zhu, Shengqi, et al.
Pubblicazione: (2024)

Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
di: Ambadkar, Tanmay, et al.
Pubblicazione: (2026)

CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance
di: Kim, Myeongsoo, et al.
Pubblicazione: (2025)

Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures
di: Wang, Shenran, et al.
Pubblicazione: (2025)

Scaling Strategy, Not Compute: A Stand-Alone, Open-Source StarCraft II Benchmark for Accessible Reinforcement Learning Research
di: Panda, Sourav, et al.
Pubblicazione: (2026)

Understanding the User: An Intent-Based Ranking Dataset
di: Anand, Abhijit, et al.
Pubblicazione: (2024)

Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints
di: Mishra, Shweta
Pubblicazione: (2026)

Neural-Guided Equation Discovery
di: Brugger, Jannis, et al.
Pubblicazione: (2025)

What an Autonomous Agent Discovers About Molecular Transformer Design: Does It Transfer?
di: Wijaya, Edward
Pubblicazione: (2026)

Toward Agents That Reason About Their Computation
di: Orenstein, Adrian, et al.
Pubblicazione: (2025)

Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
di: Siththaranjan, Anand, et al.
Pubblicazione: (2023)

Slot State Space Models
di: Jiang, Jindong, et al.
Pubblicazione: (2024)

Bi-Mamba: Towards Accurate 1-Bit State Space Models
di: Tang, Shengkun, et al.
Pubblicazione: (2024)

Towards an Understanding of Context Utilization in Code Intelligence
di: Wang, Yanlin, et al.
Pubblicazione: (2025)

What LLMs Think When You Don't Tell Them What to Think About?
di: Kwon, Yongchan, et al.
Pubblicazione: (2026)