Introducing Nova (ICLR’25), foundation models for binary/assembly code. We have also released fine-tuned models for binary code decompilation. Preprint: arxiv.org/pdf/2311.13721

#LLM4Code #LLM #BinaryAnalysis #Security

@cerias.bsky.social @iclr-conf.bsky.social

Thrilled to share that my PhD student, Nan Jiang, is on the academic job market! 👏 Working on SE+AI, Nan has papers in ICSE, FSE, NeurIPS, AAAI, and more. Nan is the ideal kind of PhD student one can ask for. I’m confident he will be a great professor!
jiang719.github.io

#LLM4Code #security

Excited to announce the 3rd LLM4Code workshop collocated with ICSE26 @icseconf.bsky.social in Rio de Janeiro, Brazil 🇧🇷!

🌟Website: llm4code.github.io
🌟Deadline: Oct 20, 2025
🌟8-page research paper / 4-page position paper (including references)
@llingming.bsky.social @devanbu.bsky.social

2/5

Smaller 1.3B models huggingface.co/lt-asset/nov... huggingface.co/lt-asset/nov...

Binaries are a form of code. Do not forget about binaries when you work on #LLM4Code.

4. Smaller 1.3B models huggingface.co/lt-asset/nov... huggingface.co/lt-asset/nov...
Binaries are a form of code.

Do not forget about binaries when you work on #LLM4Code.

arXiv:2503.16771v1 Announce Type: new
Abstract: In recent years, Language Models for Code (LLM4Code) have significantly changed the landscape of software engineering (SE) on downstream tasks, such as code generation, by making software development [1/8 of https://arxiv.org/abs/2503.16771v1]

Do you use local LLM with Android Studio and IntelliJ IDEA? If yes, which one? 👀 I am thinking to use DeepSeek Coder V2 32B for "VocabKit" Kotlin Multiplatform project 🤔 Feel free to share your experience or opinion about it 🤝 #KMP #Kotlin #aicodingassistant #LLM4Code #androiddev #iosdev

Implication of different #AI models in #AutonomousVehicles

www.listentoyourmuse.com/implication-...

#Vehicles #DeepLearning #ContextualAI #llm4code #machinelearning

Défi Inria LLM4Code : une dizaine d’équipes de recherche tentent d’améliorer les IA qui assistent les développeurs dans l’écriture des programmes. www.inria.fr/fr/meilleure...

Yang Liu, Da Song, Armstrong Foundjem, Heng Li, Foutse Khomh: Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code https://arxiv.org/abs/2604.12214 https://arxiv.org/pdf/2604.12214 https://arxiv.org/html/2604.12214

practitioners often seek methods to interpret LLM4Code outputs beyond canonical benchmarks. While the majority of research reports on code generation effectiveness in terms of expected ground truth, scant attention has been paid to LLMs' explanations. [3/8 of https://arxiv.org/abs/2503.16771v1]