Search Results for "competitive programming"

CodeGen is a family of open-source large language models designed specifically for program synthesis and code generation tasks. Developed by Salesforce Research, the models are trained on large datasets containing both natural language and programming language content. This allows them to translate natural language descriptions into functional code across a variety of programming languages. CodeGen supports multi-turn program synthesis, meaning it can generate complex programs through a...

TorchCode is an interactive learning and practice platform designed to help developers master PyTorch by implementing core machine learning operations and architectures from scratch. It is structured similarly to competitive programming platforms like LeetCode but focuses specifically on tensor operations and deep learning concepts. The platform provides a collection of curated problems that cover fundamental topics such as activation functions, normalization layers, attention mechanisms, and full transformer architectures. It runs in a Jupyter-based environment, allowing users to write, test, and debug their code interactively while receiving immediate feedback. ...

...These models range from tens of billions to smaller footprints and are trained on a novel code-flow multi-stage paradigm that captures how real software evolves over time — not just static code snapshots — giving them a deeper semantic understanding of programming logic. They support native long contexts up to 128K tokens, enabling them to reason across large codebases and multi-file interactions without context fragmentation, and include “Thinking” variants optimized for complex reasoning and “Loop” variants with recurrent mechanisms to improve inference efficiency. IQuest-Coder-V1 delivers state-of-the-art performance on multiple coding benchmarks, demonstrating strong results in competitive programming, tool use, and agentic code generation.

CodeContests, developed by Google DeepMind, is a large-scale competitive programming dataset designed for training and evaluating machine learning models on code generation and problem solving. This dataset played a central role in the development of AlphaCode, DeepMind’s model for solving programming problems at a human-competitive level, as published in Science. CodeContests aggregates problems and human-written solutions from multiple programming competition platforms, including AtCoder, Codeforces, CodeChef, Aizu, and HackerEarth. ...

...While the base model is not fine-tuned for downstream tasks, it is designed to be easily adapted through supervised fine-tuning (SFT) or reinforcement learning (RL). Benchmarks on RepoBench, SAFIM, and HumanEval demonstrate its competitive performance, with specialized fine-tuned versions for Python already showing strong improvements.