FullStack Bench: Evaluating LLMs as Full Stack Coders

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Seed-Coder: Let the Code Model Curate Data for Itself

Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs

LLM-Powered Test Case Generation for Detecting Tricky Bugs

Focused-dpo: Enhancing code generation through focused preference optimization on error-prone points

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code

SEAlign: Alignment training for software engineering agent

Deep learning for code generation: a survey

Poison Attack and Poison Detection on Deep Source Code Processing Models

Selene: Pioneering Automated Proof in Software Verification

TrickyBugs: A Dataset of Corner-case Bugs in Plausible Programs

HITS: High-coverage LLM-based Unit Test Generation via Method Slicing

Codeagent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges

HiRoPE: Length Extrapolation for Code Models Using Hierarchical Position

GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond

Retrieval-generation synergy augmented large language models

Improved Visual Story Generation with Adaptive Context Modeling

Who Judges the Judge: An Empirical Study on Online Judge Tests

Self-edit: Fault-aware code editor for code generation

Toolcoder: Teach code generation models to use api search tools

Towards Robustness of Deep Program Processing Models—Detection, Estimation, and Enhancement

Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words

One model, multiple modalities: A sparsely activated approach for text, sound, image, video and code

Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization

Iterative Utterance Segmentation for Neural Semantic Parsing

Hierarchical Poset Decoding for Compositional Generalization in Language

Fact-aware Sentence Split and Rephrase with Permutation Invariant Training

Generating Adversarial Examples for Holding Robustness of Source Code Processing Models

CodeBERT: A Pre-Trained Model for Programming and Natural Languages

Learning to represent programs with heterogeneous graphs

Generating Fluent Adversarial Examples for Natural Languages