XStack: A Benchmark for ML Repo Migration
cs.LG, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/ax-ml/jax
Terminology
Sources
- SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- GLM-5: from Vibe Coding to Agentic Engineering
- AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- 94% on CIFAR-10 in 3.29 Seconds on a Single GPU
- CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation
- Ivy: Templated Deep Learning for Inter-Framework Portability
- RepoMod-Bench: A Benchmark for Code Repository Modernization via Implementation-Agnostic Testing
- The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason
- MigrationBench: Repository-Level Code Migration Benchmark from Java 8
- RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust
- KernelBench: Can LLMs Write Efficient GPU Kernels?
- Learning Bug Context for PyTorch-to-JAX Translation with LLMs
- Temporal Graph Networks for Deep Learning on Dynamic Graphs
- Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
- CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
- T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis