The rapid pace of large-scale software development places increasing demands on traditional testing methodologies, often leading to bottlenecks in efficiency, accuracy, and coverage. We propose a novel perspective on software testing by positing bug detection and coding with fewer bugs as two interconnected problems that share a common goal, which is reducing bugs with limited resources. We extend our previous work on AI-assisted programming, which supports code auto-completion and chatbot-powered Q&A, to the realm of software testing. We introduce Copilot for Testing, an automated testing system that synchronizes bug detection with codebase updates, leveraging context-based Retrieval Augmented Generation (RAG) to enhance the capabilities of large language models (LLMs). Our evaluation demonstrates a 31.2% improvement in bug detection accuracy, a 12.6% increase in critical test coverage, and a 10.5% higher user acceptance rate, highlighting the transformative potential of AI-driven technologies in modern software development practices.
In this work we propose a novel end-to-end multi-stage Knowledge Graph (KG) generation system from textual inputs, separating the overall process into two stages. The graph nodes are generated first using pretrained language model, followed by a simple edge construction head, enabling efficient KG extraction from the text. For each stage we consider several architectural choices that can be used depending on the available training resources. We evaluated the model on a recent WebNLG 2020 Challenge dataset, matching the state-of-the-art performance on text-to-RDF generation task, as well as on New York Times (NYT) and a large-scale TekGen datasets, showing strong overall performance, outperforming the existing baselines. We believe that the proposed system can serve as a viable KG construction alternative to the existing linearization or sampling-based graph generation approaches. Our code can be found at https://github.com/IBM/Grapher
We present TEGCER, an automated feedback tool for novice programmers. TEGCER uses supervised classification to match compilation errors in new code submissions with relevant pre-existing errors, submitted by other students before. The dense neural network used to perform this classification task is trained on 15000+ error-repair code examples. The proposed model yields a test set classification Pred@3 accuracy of 97.7% across 212 error category labels. Using this model as its base, TEGCER presents students with the closest relevant examples of solutions for their specific error on demand.
The task of automated code review has recently gained a lot of attention from the machine learning community. However, current review comment evaluation metrics rely on comparisons with a human-written reference for a given code change (also called a diff). Furthermore, code review is a one-to-many problem, like generation and summarization, with many "valid reviews" for a diff. Thus, we develop CRScore - a reference-free metric to measure dimensions of review quality like conciseness, comprehensiveness, and relevance. We design CRScore to evaluate reviews in a way that is grounded in claims and potential issues detected in the code by LLMs and static analyzers. We demonstrate that CRScore can produce valid, fine-grained scores of review quality that have the greatest alignment with human judgment among open source metrics (0.54 Spearman correlation) and are more sensitive than reference-based metrics. We also release a corpus of 2.9k human-annotated review quality scores for machine-generated and GitHub review comments to support the development of automated metrics.
Dance plays an important role as an artistic form and expression in human culture, yet the creation of dance remains a challenging task. Most dance generation methods primarily rely solely on music, seldom taking into consideration intrinsic attributes such as music style or genre. In this work, we introduce Flexible Dance Generation with Style Description Prompts (DGSDP), a diffusion-based framework suitable for diversified tasks of dance generation by fully leveraging the semantics of music style. The core component of this framework is Music-Conditioned Style-Aware Diffusion (MCSAD), which comprises a Transformer-based network and a music Style Modulation module. The MCSAD seemly integrates music conditions and style description prompts into the dance generation framework, ensuring that generated dances are consistent with the music content and style. To facilitate flexible dance generation and accommodate different tasks, a spatial-temporal masking strategy is effectively applied in the backward diffusion process. The proposed framework successfully generates realistic dance sequences that are accurately aligned with music for a variety of tasks such as long-term generation, dance in-betweening, dance inpainting, and etc. We hope that this work has the potential to inspire dance generation and creation, with promising applications in entertainment, art, and education. Code is available on Github: https://github.com/mucunzhuzhu/DGSDP.
Grasp generation aims to create complex hand-object interactions with a specified object. While traditional approaches for hand generation have primarily focused on visibility and diversity under scene constraints, they tend to overlook the fine-grained hand-object interactions such as contacts, resulting in inaccurate and undesired grasps. To address these challenges, we propose a controllable grasp generation task and introduce ClickDiff, a controllable conditional generation model that leverages a fine-grained Semantic Contact Map (SCM). Particularly when synthesizing interactive grasps, the method enables the precise control of grasp synthesis through either user-specified or algorithmically predicted Semantic Contact Map. Specifically, to optimally utilize contact supervision constraints and to accurately model the complex physical structure of hands, we propose a Dual Generation Framework. Within this framework, the Semantic Conditional Module generates reasonable contact maps based on fine-grained contact information, while the Contact Conditional Module utilizes contact maps alongside object point clouds to generate realistic grasps. We evaluate the evaluation criteria applicable to controllable grasp generation. Both unimanual and bimanual generation experiments on GRAB and ARCTIC datasets verify the validity of our proposed method, demonstrating the efficacy and robustness of ClickDiff, even with previously unseen objects. Our code is available at https://github.com/adventurer-w/ClickDiff.
Large language models (LLMs) have shown remarkable progress in code generation, but their generated code often suffers from inefficiency, resulting in longer execution times and higher memory consumption. To address this issue, we propose \textbf{EffiLearner}, a self-optimization framework that utilizes execution overhead profiles to improve the efficiency of LLM-generated code. EffiLearner first generates code using an LLM, then executes it locally to capture execution time and memory usage profiles. These profiles are fed back to the LLM, which then revises the code to reduce overhead. To evaluate the effectiveness of EffiLearner, we conduct extensive experiments on the EffiBench, HumanEval, and MBPP with 16 open-source and 6 closed-source models. Our evaluation results demonstrate that through iterative self-optimization, EffiLearner significantly enhances the efficiency of LLM-generated code. For example, the execution time (ET) of StarCoder2-15B for the EffiBench decreases from 0.93 (s) to 0.12 (s) which reduces 87.1% the execution time requirement compared with the initial code. The total memory usage (TMU) of StarCoder2-15B also decreases from 22.02 (Mb*s) to 2.03 (Mb*s), which decreases 90.8% of total memory consumption during the execution process. The source code of EffiLearner was released in https://github.com/huangd1999/EffiLearner
Diffusion Models (DMs) have achieved State-Of-The-Art (SOTA) results in the Lidar point cloud generation task, benefiting from their stable training and iterative refinement during sampling. However, DMs often fail to realistically model Lidar raydrop noise due to their inherent denoising process. To retain the strength of iterative sampling while enhancing the generation of raydrop noise, we introduce LidarGRIT, a generative model that uses auto-regressive transformers to iteratively sample the range images in the latent space rather than image space. Furthermore, LidarGRIT utilises VQ-VAE to separately decode range images and raydrop masks. Our results show that LidarGRIT achieves superior performance compared to SOTA models on KITTI-360 and KITTI odometry datasets. Code available at:https://github.com/hamedhaghighi/LidarGRIT.
We introduce a novel resampling criterion using lift scores, for improving compositional generation in diffusion models. By leveraging the lift scores, we evaluate whether generated samples align with each single condition and then compose the results to determine whether the composed prompt is satisfied. Our key insight is that lift scores can be efficiently approximated using only the original diffusion model, requiring no additional training or external modules. We develop an optimized variant that achieves relatively lower computational overhead during inference while maintaining effectiveness. Through extensive experiments, we demonstrate that lift scores significantly improved the condition alignment for compositional generation across 2D synthetic data, CLEVR position tasks, and text-to-image synthesis. Our code is available at http://github.com/rainorangelemon/complift.
We present the PyHST2 code which is in service at ESRF for phase-contrast and absorption tomography. This code has been engineered to sustain the high data flow typical of the third generation synchrotron facilities (10 terabytes per experiment) by adopting a distributed and pipelined architecture. The code implements, beside a default filtered backprojection reconstruction, iterative reconstruction techniques with a-priori knowledge. These latter are used to improve the reconstruction quality or in order to reduce the required data volume and reach a given quality goal. The implemented a-priori knowledge techniques are based on the total variation penalisation and a new recently found convex functional which is based on overlapping patches. We give details of the different methods and their implementations while the code is distributed under free license. We provide methods for estimating, in the absence of ground-truth data, the optimal parameters values for a-priori techniques.
This paper presents a novel auto-encoder based end-to-end channel encoding and decoding. It integrates deep reinforcement learning (DRL) and graph neural networks (GNN) in code design by modeling the generation of code parity-check matrices as a Markov Decision Process (MDP), to optimize key coding performance metrics such as error-rates and code algebraic properties. An edge-weighted GNN (EW-GNN) decoder is proposed, which operates on the Tanner graph with an iterative message-passing structure. Once trained on a single linear block code, the EW-GNN decoder can be directly used to decode other linear block codes of different code lengths and code rates. An iterative joint training of the DRL-based code designer and the EW-GNN decoder is performed to optimize the end-end encoding and decoding process. Simulation results show the proposed auto-encoder significantly surpasses several traditional coding schemes at short block lengths, including low-density parity-check (LDPC) codes with the belief propagation (BP) decoding and the maximum-likelihood decoding (MLD), and BCH with BP decoding, offering superior error-correction capabilities while maintaining low decoding complexity.
LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs' capabilities to autonomously find and fix runtime logical errors in complex data science code remain largely unexplored. To address this gap, we introduce DSDBench: the Data Science Debugging Benchmark, the first benchmark for systematic evaluation of LLMs on multi-hop error tracing and multi-bug detection in data science code debugging. DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets. DSDBench includes 1,117 annotated samples with 741 cause-effect error pairs and runtime error messages. Evaluations of state-of-the-art LLMs on DSDBench show significant performance gaps, highlighting challenges in debugging logical runtime errors in data science code. DSDBench offers a crucial resource to evaluate and improve LLMs' debugging and reasoning capabilities, enabling more reliable AI-assisted data science in the future. DSDBench is publicly available at github.com/KevinCL16/DSDBench.
Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the representation power of VAEs is limited due to two reasons: (1) the Gaussian assumption is often made on the variational posteriors; and meanwhile (2) a notorious "posterior collapse" issue occurs. In this paper, we advocate sample-based representations of variational distributions for natural language, leading to implicit latent features, which can provide flexible representation power compared with Gaussian-based posteriors. We further develop an LVM to directly match the aggregated posterior to the prior. It can be viewed as a natural extension of VAEs with a regularization of maximizing mutual information, mitigating the "posterior collapse" issue. We demonstrate the effectiveness and versatility of our models in various text generation scenarios, including language modeling, unaligned style transfer, and dialog response generation. The source code to reproduce our experimental results is available on GitHub.
Video generation requires synthesizing consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite, using generative adversarial networks (GANs). First, towards composing adjacent frames, we show that the alias-free operation for single image generation, together with adequately pre-learned knowledge, brings a smooth frame transition without compromising the per-frame quality. Second, by incorporating the temporal shift module (TSM), originally designed for video understanding, into the discriminator, we manage to advance the generator in synthesizing more consistent dynamics. Third, we develop a novel B-Spline based motion representation to ensure temporal smoothness to achieve infinite-length video generation. It can go beyond the frame number used in training. A low-rank temporal modulation is also proposed to alleviate repeating contents for long video generation. We evaluate our approach on various datasets and show substantial improvements over video generation baselines. Code and models will be publicly available at https://genforce.github.io/StyleSV.
While Large language models (LLMs) have become excellent writing assistants, they still struggle with quotation generation. This is because they either hallucinate when providing factual quotations or fail to provide quotes that exceed human expectations. To bridge the gap, we systematically study how to evaluate and improve LLMs' performance in quotation generation tasks. We first establish a holistic and automatic evaluation system for quotation generation task, which consists of five criteria each with corresponding automatic metric. To improve the LLMs' quotation generation abilities, we construct a bilingual knowledge base that is broad in scope and rich in dimensions, containing up to 32,022 quotes. Moreover, guided by our critiria, we further design a quotation-specific metric to rerank the retrieved quotations from the knowledge base. Extensive experiments show that our metrics strongly correlate with human preferences. Existing LLMs struggle to generate desired quotes, but our quotation knowledge base and reranking metric help narrow this gap. Our dataset and code are publicly available at https://github.com/GraceXiaoo/QUILL.
Descriptive code comments are essential for supporting code comprehension and maintenance. We propose the task of automatically generating comments for overriding methods. We formulate a novel framework which accommodates the unique contextual and linguistic reasoning that is required for performing this task. Our approach features: (1) incorporating context from the class hierarchy; (2) conditioning on learned, latent representations of specificity to generate comments that capture the more specialized behavior of the overriding method; and (3) unlikelihood training to discourage predictions which do not conform to invariant characteristics of the comment corresponding to the overridden method. Our experiments show that the proposed approach is able to generate comments for overriding methods of higher quality compared to prevailing comment generation techniques.
Data generation and analysis is a fundamental aspect of many industries and disciplines, from strategic decision making in business to research in the physical and social sciences. However, data generated using software and algorithms can be subject to biases and errors. These can be due to problems with the original software, default settings that do not align with the specific needs of the situation, or even deeper problems with the underlying theories and models. This paper proposes an advanced search and optimization framework aimed at generating and choosing optimal source code capable of correcting errors and biases from previous versions to address typical problems in software systems specializing in data analysis and generation, especially those in the corporate and data science world. Applying this framework multiple times on the same software system would incrementally improve the quality of the output results. It uses Solomonoff Induction as a sound theoretical basis, extending it with Kolmogorov Conditional Complexity, a novel adaptation, to evaluate a set of candidate programs. We propose the use of generative models for the creation of this set of programs, with special emphasis on the capabilities of Large Language Models (LLMs) to generate high quality code.
Large language models have demonstrated great potential to assist programmers in generating code. For such human-AI pair programming scenarios, we empirically demonstrate that while generated code is most often evaluated in terms of their functional correctness (i.e., whether generations pass available unit tests), correctness does not fully capture (e.g., may underestimate) the productivity gains these models may provide. Through a user study with N = 49 experienced programmers, we show that while correctness captures high-value generations, programmers still rate code that fails unit tests as valuable if it reduces the overall effort needed to complete a coding task. Finally, we propose a hybrid metric that combines functional correctness and syntactic similarity and show that it achieves a 14% stronger correlation with value and can therefore better represent real-world gains when evaluating and comparing models.
Unifying visual understanding and generation within a single multimodal framework remains a significant challenge, as the two inherently heterogeneous tasks require representations at different levels of granularity. Current approaches that utilize vector quantization (VQ) or variational autoencoders (VAE) for unified visual representation prioritize intrinsic imagery features over semantics, compromising understanding performance. In this work, we take inspiration from masked image modelling (MIM) that learns rich semantics via a mask-and-reconstruct pre-training and its successful extension to masked autoregressive (MAR) image generation. A preliminary study on the MAR encoder's representation reveals exceptional linear probing accuracy and precise feature response to visual concepts, which indicates MAR's potential for visual understanding tasks beyond its original generation role. Based on these insights, we present \emph{Harmon}, a unified autoregressive framework that harmonizes understanding and generation tasks with a shared MAR encoder. Through a three-stage training procedure that progressively optimizes understanding and generation capabilities, Harmon achieves state-of-the-art image generation results on the GenEval, MJHQ30K and WISE benchmarks while matching the performance of methods with dedicated semantic encoders (e.g., Janus) on image understanding benchmarks. Our code and models will be available at https://github.com/wusize/Harmon.
Document-level text generation tasks are known to be more difficult than sentence-level text generation tasks as they require the understanding of longer context to generate high-quality texts. In this paper, we investigate the adaption of Minimum Bayes Risk (MBR) decoding for document-level text generation tasks. MBR decoding makes use of a utility function to estimate the output with the highest expected utility from a set of candidate outputs. Although MBR decoding is shown to be effective in a wide range of sentence-level text generation tasks, its performance on document-level text generation tasks is limited as many of the utility functions are designed for evaluating the utility of sentences. To this end, we propose MBR-OT, a variant of MBR decoding using Wasserstein distance to compute the utility of a document using a sentence-level utility function. The experimental result shows that the performance of MBR-OT outperforms that of the standard MBR in document-level machine translation, text simplification, and dense image captioning tasks. Our code is available at https://github.com/jinnaiyuu/mbr-optimal-transport