IRIS-14B is the first LLM trained explicitly for GIMPLE-to-LLVM IR translation and outperforms much larger models by up to 44 percentage points on real-world C code.
arXiv preprint arXiv:2309.07062 , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7roles
background 2polarities
background 2representative citing papers
TensorBench is a new benchmark of 199 tasks on a tensor framework used to evaluate seven coding agents, yielding pass rates from 22.1% to 64.8% with low inter-agent agreement.
Step-TP is a dataset providing grounded, atomic step-level IR transitions and CoT supervision to enable reliable multi-step LLM-guided tensor program optimization instead of end-to-end imitation.
JETO-Mine is a reusable three-phase pipeline that mines 1.8 million Java commits to produce JETO-Bench containing 91 verified executable ETIPs, on which OpenHands succeeds at 14.3%.
AgentCompile is an LLM-guided CUDA compiler that reports 4-5.7x speedups over PyTorch eager for small transformer models by treating LLM suggestions as search metadata while relying on compiler validation and measured latency.
InCoder-32B-Thinking uses error-feedback synthesized thinking traces and a code world model to reach top open-source scores on general and industrial code benchmarks including 81.3% on LiveCodeBench and 84.0% on CAD-Coder.
Fine-tuning LLMs on structured tasks inspired by maladaptive behaviors produces stable, context-general shifts in next-token distributions and response tendencies consistent with altered behavioral priors.
citing papers explorer
-
JETO-Bench: A Reproducible Benchmark for Execution Time Improvement Patches in Java
JETO-Mine is a reusable three-phase pipeline that mines 1.8 million Java commits to produce JETO-Bench containing 91 verified executable ETIPs, on which OpenHands succeeds at 14.3%.