Neural code synthesis has reached a point where snippet generation is accurate enough to be considered for integration into human software development workflows. Commercial products aim to increase programmers' productivity, without being able to measure it directly. In this case study, we asked users of GitHub Copilot about its impact on their productivity, and sought to find a reflection of their perception in directly measurable user data. We find that the rate with which shown suggestions are accepted, rather than more specific metrics regarding the persistence of completions in the code over time, drives developers' perception of productivity.
Retrieval-augmented generation (RAG) has recently emerged as a promising solution for incorporating up-to-date or domain-specific knowledge into large language models (LLMs) and improving LLM factuality, but is predominantly studied in English-only settings. In this work, we consider RAG in the multilingual setting (mRAG), i.e. with user queries and the datastore in 13 languages, and investigate which components and with which adjustments are needed to build a well-performing mRAG pipeline, that can be used as a strong baseline in future works. Our findings highlight that despite the availability of high-quality off-the-shelf multilingual retrievers and generators, task-specific prompt engineering is needed to enable generation in user languages. Moreover, current evaluation metrics need adjustments for multilingual setting, to account for variations in spelling named entities. The main limitations to be addressed in future works include frequent code-switching in non-Latin alphabet languages, occasional fluency errors, wrong reading of the provided documents, or irrelevant retrieval. We release the code for the resulting mRAG baseline pipeline at https://github.com/naver/bergen.
This paper presents an efficient implementation of the Wavenet generation process called Fast Wavenet. Compared to a naive implementation that has complexity O(2^L) (L denotes the number of layers in the network), our proposed approach removes redundant convolution operations by caching previous calculations, thereby reducing the complexity to O(L) time. Timing experiments show significant advantages of our fast implementation over a naive one. While this method is presented for Wavenet, the same scheme can be applied anytime one wants to perform autoregressive generation or online prediction using a model with dilated convolution layers. The code for our method is publicly available.
Large Language Models (LLMs) have transformed software development by enabling code generation, automated debugging, and complex reasoning. However, their continued advancement is constrained by the scarcity of high-quality, publicly available supervised fine-tuning (SFT) datasets tailored for coding tasks. To bridge this gap, we introduce OpenCodeInstruct, the largest open-access instruction tuning dataset, comprising 5 million diverse samples. Each sample includes a programming question, solution, test cases, execution feedback, and LLM-generated quality assessments. We fine-tune various base models, including LLaMA and Qwen, across multiple scales (1B+, 3B+, and 7B+) using our dataset. Comprehensive evaluations on popular benchmarks (HumanEval, MBPP, LiveCodeBench, and BigCodeBench) demonstrate substantial performance improvements achieved by SFT with OpenCodeInstruct. We also present a detailed methodology encompassing seed data curation, synthetic instruction and solution generation, and filtering.
We introduce Controller-Embedded Language Model Interactions (CELI), a framework that integrates control logic directly within language model (LM) prompts, facilitating complex, multi-stage task execution. CELI addresses limitations of existing prompt engineering and workflow optimization techniques by embedding control logic directly within the operational context of language models, enabling dynamic adaptation to evolving task requirements. Our framework transfers control from the traditional programming execution environment to the LMs, allowing them to autonomously manage computational workflows while maintaining seamless interaction with external systems and functions. CELI supports arbitrary function calls with variable arguments, bridging the gap between LMs' adaptive reasoning capabilities and conventional software paradigms' structured control mechanisms. To evaluate CELI's versatility and effectiveness, we conducted case studies in two distinct domains: code generation (HumanEval benchmark) and multi-stage content generation (Wikipedia-style articles). The results demonstrate notable performance improvements across a range of domains. CELI achieved a 4.9 percentage point improvement over the best reported score of the baseline GPT-4 model on the HumanEval code generation benchmark. In multi-stage content generation, 94.4% of CELI-produced Wikipedia-style articles met or exceeded first draft quality when optimally configured, with 44.4% achieving high quality. These outcomes underscore CELI's potential for optimizing AI-driven workflows across diverse computational domains.
Amidst the recent strides in evaluating Large Language Models for Code (Code LLMs), existing benchmarks have mainly focused on the functional correctness of generated code, neglecting the importance of their computational efficiency. To fill the gap, we present Mercury, the first code efficiency benchmark for Code LLMs. It comprises 1,889 Python tasks, each accompanied by adequate solutions that serve as real-world efficiency baselines, enabling a comprehensive analysis of the runtime distribution. Based on the distribution, we introduce a new metric Beyond, which computes a runtime-percentile-weighted Pass score to reflect functional correctness and code efficiency simultaneously. On Mercury, leading Code LLMs can achieve 65% on Pass, while less than 50% on Beyond. Given that an ideal Beyond score would be aligned with the Pass score, it indicates that while Code LLMs exhibit impressive capabilities in generating functionally correct code, there remains a notable gap in their efficiency. Finally, our empirical experiments reveal that Direct Preference Optimization (DPO) serves as a robust baseline for enhancing code efficiency compared with Supervised Fine Tuning (SFT), which paves a promising avenue for future exploration of efficient code generation. Our code and data are available on GitHub: https://github.com/Elfsong/Mercury.
We introduce BiGR, a novel conditional image generation model using compact binary latent codes for generative training, focusing on enhancing both generation and representation capabilities. BiGR is the first conditional generative model that unifies generation and discrimination within the same framework. BiGR features a binary tokenizer, a masked modeling mechanism, and a binary transcoder for binary code prediction. Additionally, we introduce a novel entropy-ordered sampling method to enable efficient image generation. Extensive experiments validate BiGR's superior performance in generation quality, as measured by FID-50k, and representation capabilities, as evidenced by linear-probe accuracy. Moreover, BiGR showcases zero-shot generalization across various vision tasks, enabling applications such as image inpainting, outpainting, editing, interpolation, and enrichment, without the need for structural modifications. Our findings suggest that BiGR unifies generative and discriminative tasks effectively, paving the way for further advancements in the field. We further enable BiGR to perform text-to-image generation, showcasing its potential for broader applications.
Modern video generation models like Sora have achieved remarkable success in producing high-quality videos. However, a significant limitation is their inability to offer interactive control to users, a feature that promises to open up unprecedented applications and creativity. In this work, we introduce the first solution to equip diffusion-based video generation models with spatio-temporal control. We present Peekaboo, a novel masked attention module, which seamlessly integrates with current video generation models offering control without the need for additional training or inference overhead. To facilitate future research, we also introduce a comprehensive benchmark for interactive video generation. This benchmark offers a standardized framework for the community to assess the efficacy of emerging interactive video generation models. Our extensive qualitative and quantitative assessments reveal that Peekaboo achieves up to a 3.8x improvement in mIoU over baseline models, all while maintaining the same latency. Code and benchmark are available on the webpage.
While a plethora of machine learning (ML) models are currently available, along with their implementation on disparate platforms, there is hardly any verifiable ML code which can be executed on public blockchains. We propose a novel approach named LMST that enables conversion of the inferencing path of an ML model as well as its weights trained off-chain into Solidity code using Large Language Models (LLMs). Extensive prompt engineering is done to achieve gas cost optimization beyond mere correctness of the produced code, while taking into consideration the capabilities and limitations of the Ethereum Virtual Machine. We have also developed a proof of concept decentralized application using the code so generated for verifying the accuracy claims of the underlying ML model. An extensive set of experiments demonstrate the feasibility of deploying ML models on blockchains through automated code translation using LLMs.
Structured code comments in docstring format are essential for code comprehension and maintenance, but existing machine learning models for their generation perform poorly for Russian compared to English. To bridge this gap, we present StRuCom - the first large-scale dataset (153K examples) specifically designed for Russian code documentation. Unlike machine-translated English datasets that distort terminology (e.g., technical loanwords vs. literal translations) and docstring structures, StRuCom combines human-written comments from Russian GitHub repositories with synthetically generated ones, ensuring compliance with Python, Java, JavaScript, C#, and Go standards through automated validation. Fine-tuning Qwen2.5-Coder models (0.5B-7B) on StRuCom shows statistically significant improvements of chrf++ and BERTScore over baseline models.
The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images to evaluate automatic program construction, focusing on sequence, selection, and iteration. This set of 600 tasks has resisted automated solutions. This paper presents a structured inductive programming approach with LLMs that successfully solves tasks across all IPARC categories. The controlled nature of IPARC reveals insights into LLM-based code generation, including the importance of prior structuring, LLMs' ability to aid structuring (requiring human refinement), the need to freeze correct code, the efficiency of code reuse, and how LLM-generated code can spark human creativity. These findings suggest valuable mechanisms for human-LLM collaboration in tackling complex program synthesis.
We introduce ${\rm C{\small LEVER}}$, a high-quality, curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task of generating a specification that matches a held-out ground-truth specification, and (2) the task of generating a Lean implementation that provably satisfies this specification. Unlike prior benchmarks, ${\rm C{\small LEVER}}$ avoids test-case supervision, LLM-generated annotations, and specifications that leak implementation logic or allow vacuous solutions. All outputs are verified post-hoc using Lean's type checker to ensure machine-checkable correctness. We use ${\rm C{\small LEVER}}$ to evaluate several few-shot and agentic approaches based on state-of-the-art language models. These methods all struggle to achieve full verification, establishing it as a challenging frontier benchmark for program synthesis and formal reasoning. Our benchmark can be found on GitHub(https://github.com/trishullab/clever) as well as HuggingFace(https://huggingface.co/datasets/amitayusht/clever). All our evaluation code is also available online(https://github.com/trishullab/clever-prover).
Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments. However, the evaluation of these models has often been performed in a scattered way on only one or two specific tasks, in a few languages, at a partial granularity (e.g., function) level, and in many cases without proper training data. Even more concerning is that in most cases the evaluation of generated codes has been done in terms of mere lexical overlap with a reference code rather than actual execution. We introduce xCodeEval, the largest executable multilingual multitask benchmark to date consisting of $25$M document-level coding examples ($16.5$B tokens) from about $7.5$K unique problems covering up to $11$ programming languages with execution-level parallelism. It features a total of $7$ tasks involving code understanding, generation, translation and retrieval. xCodeEval adopts an execution-based evaluation and offers a multilingual code execution engine, ExecEval that supports unit test based execution in all the $11$ languages. To address the challenge of balancing the distributions of text-code samples over multiple attributes in validation/test sets, we propose a novel data splitting and a data selection schema based on the geometric mean and graph-theoretic principle. Our experiments with OpenAI's LLMs (zero-shot) and open-LLMs (zero-shot and fine-tuned) on the tasks and languages demonstrate **xCodeEval** to be quite challenging as per the current advancements in language models.
Multi-head-self-attention (MHSA) mechanisms achieve state-of-the-art (SOTA) performance across natural language processing and vision tasks. However, their quadratic dependence on sequence lengths has bottlenecked inference speeds. To circumvent this bottleneck, researchers have proposed various sparse-MHSA models, where a subset of full attention is computed. Despite their promise, current sparse libraries and compilers do not support high-performance implementations for diverse sparse-MHSA patterns due to the underlying sparse formats they operate on. These formats, which are typically designed for high-performance & scientific computing applications, are either curated for extreme amounts of random sparsity (<1% non-zero values), or specific sparsity patterns. However, the sparsity patterns in sparse-MHSA are moderately sparse (10-50% non-zero values) and varied, resulting in existing sparse-formats trading off generality for performance. We bridge this gap, achieving both generality and performance, by proposing a novel sparse format: affine-compressed-sparse-row (ACSR) and supporting code-generation scheme, SPLAT, that generates high-performance implementations for diverse sparse-MHSA patterns on GPUs. Core to our proposed format and code generation algorithm is the observation that common sparse-MHSA patterns have uniquely regular geometric properties. These properties, which can be analyzed just-in-time, expose novel optimizations and tiling strategies that SPLAT exploits to generate high-performance implementations for diverse patterns. To demonstrate SPLAT's efficacy, we use it to generate code for various sparse-MHSA models, achieving geomean speedups of 2.05x and 4.05x over hand-written kernels written in triton and TVM respectively on A100 GPUs. Moreover, its interfaces are intuitive and easy to use with existing implementations of MHSA in JAX.
Recently, DeepSeek-R1 (671B) (DeepSeek-AIet al., 2025) has demonstrated its excellent reasoning ability in complex tasks and has publiclyshared its methodology. This provides potentially high-quality chain-of-thought (CoT) data for stimulating the reasoning abilities of small-sized large language models (LLMs). To generate high-quality CoT data for different LLMs, we seek an efficient method for generating high-quality CoT data with LLM-Adaptive questiondifficulty levels. First, we grade the difficulty of the questions according to the reasoning ability of the LLMs themselves and construct a LLM-Adaptive question database. Second, we sample the problem database based on a distribution of difficulty levels of the questions and then use DeepSeek-R1 (671B) (DeepSeek-AI et al., 2025) to generate the corresponding high-quality CoT data with correct answers. Thanks to the construction of CoT data with LLM-Adaptive difficulty levels, we have significantly reduced the cost of data generation and enhanced the efficiency of model supervised fine-tuning (SFT). Finally, we have validated the effectiveness and generalizability of the proposed method in the fields of complex mathematical competitions and code generation tasks. Notably, with only 2k high-quality mathematical CoT data, our ZMath-32B surpasses DeepSeek-Distill-32B in math reasoning task. Similarly, with only 2k high-quality code CoT data, our ZCode-32B surpasses DeepSeek-Distill-32B in code reasoning tasks.
In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent neural networks (RNNs). However, it is non-trivial to impose constraints on RNNs while maintaining generation quality, since RNNs generate sentences sequentially (or with beam search) from the first word to the last. In this paper, we propose CGMH, a novel approach using Metropolis-Hastings sampling for constrained sentence generation. CGMH allows complicated constraints such as the occurrence of multiple keywords in the target sentences, which cannot be handled in traditional RNN-based approaches. Moreover, CGMH works in the inference stage, and does not require parallel corpora for training. We evaluate our method on a variety of tasks, including keywords-to-sentence generation, unsupervised sentence paraphrasing, and unsupervised sentence error correction. CGMH achieves high performance compared with previous supervised methods for sentence generation. Our code is released at https://github.com/NingMiao/CGMH
Data-driven engineering refers to systematic data collection and processing using machine learning to improve engineering systems. Currently, the implementation of data-driven engineering relies on fundamental data science and software engineering skills. At the same time, model-based engineering is gaining relevance for the engineering of complex systems. In previous work, a model-based engineering approach integrating the formalization of machine learning tasks using the general-purpose modeling language SysML is presented. However, formalized machine learning tasks still require the implementation in a specialized programming languages like Python. Therefore, this work aims to facilitate the implementation of data-driven engineering in practice by extending the previous work of formalizing machine learning tasks by integrating model transformation to generate executable code. The method focuses on the modifiability and maintainability of the model transformation so that extensions and changes to the code generation can be integrated without requiring modifications to the code generator. The presented method is evaluated for feasibility in a case study to predict weather forecasts. Based thereon, quality attributes of model transformations are assessed and discussed. Results demonstrate the flexibility and the simplicity of the method reducing efforts for implementation. Further, the work builds a theoretical basis for standardizing data-driven engineering implementation in practice.
We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination. In particular, the proposed method -- *retrieval-augmented thoughts* (RAT) -- revises each thought step one by one with retrieved information relevant to the task query, the current and the past thought steps, after the initial zero-shot CoT is generated. Applying RAT to GPT-3.5, GPT-4, and CodeLLaMA-7b substantially improves their performances on various long-horizon generation tasks; on average of relatively increasing rating scores by 13.63% on code generation, 16.96% on mathematical reasoning, 19.2% on creative writing, and 42.78% on embodied task planning. The demo page can be found at https://craftjarvis.github.io/RAT
Estimating three-dimensional conformations of a molecular graph allows insight into the molecule's biological and chemical functions. Fast generation of valid conformations is thus central to molecular modeling. Recent advances in graph-based deep networks have accelerated conformation generation from hours to seconds. However, current network architectures do not scale well to large molecules. Here we present ConfFlow, a flow-based model for conformation generation based on transformer networks. In contrast with existing approaches, ConfFlow directly samples in the coordinate space without enforcing any explicit physical constraints. The generative procedure is highly interpretable and is akin to force field updates in molecular dynamics simulation. When applied to the generation of large molecule conformations, ConfFlow improve accuracy by up to $40\%$ relative to state-of-the-art learning-based methods. The source code is made available at https://github.com/IntelLabs/ConfFlow.
Current text-to-image generation models often struggle to follow textual instructions, especially the ones requiring spatial reasoning. On the other hand, Large Language Models (LLMs), such as GPT-4, have shown remarkable precision in generating code snippets for sketching out text inputs graphically, e.g., via TikZ. In this work, we introduce Control-GPT to guide the diffusion-based text-to-image pipelines with programmatic sketches generated by GPT-4, enhancing their abilities for instruction following. Control-GPT works by querying GPT-4 to write TikZ code, and the generated sketches are used as references alongside the text instructions for diffusion models (e.g., ControlNet) to generate photo-realistic images. One major challenge to training our pipeline is the lack of a dataset containing aligned text, images, and sketches. We address the issue by converting instance masks in existing datasets into polygons to mimic the sketches used at test time. As a result, Control-GPT greatly boosts the controllability of image generation. It establishes a new state-of-art on the spatial arrangement and object positioning generation and enhances users' control of object positions, sizes, etc., nearly doubling the accuracy of prior models. Our work, as a first attempt, shows the potential for employing LLMs to enhance the performance in computer vision tasks.