arXiv Machine Learning
Jun 10
CodeAlchemy: Synthetic Code Rewriting at Scale
arXiv:2606. 10087v1 Announce Type: cross Abstract: Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats.
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
arXiv:2607. 02512v1 Announce Type: cross Abstract: Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price.
Related stories
arXiv AI
Jul 16
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
arXiv:2607. 13921v1 Announce Type: cross Abstract: Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more difficult.
arXiv AI
Jul 7
Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning
arXiv:2607. 03574v1 Announce Type: cross Abstract: AI systems increasingly propose executable scientific models whose value depends on both their symbolic structure and their fitted continuous parameters.
arXiv AI
Jul 28
xMIx: High-Performance Serving-Time Platform for Mechanistic Interpretability Apps
arXiv:2607. 22595v1 Announce Type: new Abstract: Mechanistic interpretability (MI) has emerged as a powerful approach for analyzing and intervening in inference computations, with a growing number of applications such as jailbreak attempt detection, truthfulness evaluation, and hallucination detection.
arXiv Machine Learning
Jun 3
KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators
arXiv:2606. 02963v1 Announce Type: new Abstract: Production inference increasingly targets a heterogeneous mix of accelerators.
arXiv AI
Jun 17
ANEForge: Python for direct computation on the Apple Neural Engine
arXiv:2606. 17090v1 Announce Type: cross Abstract: ANEForge is a Python package that programs the Apple Neural Engine (ANE), the fixed-function neural accelerator on every recent Apple device, directly and without CoreML.
arXiv Machine Learning
Jul 10
Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation
arXiv:2607. 07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia.
arXiv AI
6d ago
RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks
arXiv:2608. 12004v1 Announce Type: cross Abstract: In modern AI frameworks, GPU kernels are key to overall system performance.
arXiv AI
Jun 6
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation
arXiv:2512. 03086v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA, where high-quality parallel data are scarce.
arXiv AI
Jul 22
FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis
arXiv:2607. 18260v1 Announce Type: new Abstract: We introduce FindStatBench, an execution benchmark for evaluating large language models on combinatorial code synthesis.
arXiv Machine Learning
Jul 30
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
arXiv:2607. 27146v1 Announce Type: cross Abstract: Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation.
arXiv AI
Jun 19
AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning
arXiv:2606. 20373v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements.