搜索结果：suggests

The aesthetic quality of a scene depends strongly on camera viewpoint. Existing approaches for aesthetic viewpoint suggestion are either single-view adjustments, predicting limited camera adjustments from a single image without understanding scene geometry, or 3D exploration approaches, which rely on dense captures or prebuilt 3D environments coupled with costly reinforcement learning (RL) searches. In this work, we introduce the notion of 3D aesthetic field that enables geometry-grounded aesthetic reasoning in 3D with sparse captures, allowing efficient viewpoint suggestions in contrast to costly RL searches. We opt to learn this 3D aesthetic field using a feedforward 3D Gaussian Splatting network that distills high-level aesthetic knowledge from a pretrained 2D aesthetic model into 3D space, enabling aesthetic prediction for novel viewpoints from only sparse input views. Building on this field, we propose a two-stage search pipeline that combines coarse viewpoint sampling with gradient-based refinement, efficiently identifying aesthetically appealing viewpoints without dense captures or RL exploration. Extensive experiments show that our method consistently suggests viewpoints wi

Large language models (LLMs) have gained widespread popularity and have steadily improved over time, enabling software developers to use them for various code-related tasks. One common task is code refactoring, where the LLM suggests changes for the developer to apply to their code to improve quality attributes such as readability or maintainability. While current research focuses on evaluating LLM-generated refactoring suggestions, there is a limited understanding of how developers apply these suggestions in practice. To explore this, we analyze 169 GitHub commits where developers refactor their code based on a ChatGPT conversation linked in the commit message. We found that developers mostly accept and use the suggestions without modifications. When changes are made, they are mostly major and fall into five different patterns that depend on the refactoring activity, the developer's prompt, and the validity of the response from ChatGPT.

AI-assisted programming tools are widely adopted, yet their practical utility is often undermined by undesired suggestions that interrupt developer workflows and cause frustration. While existing research has explored developer-AI interactions when programming qualitatively, a significant gap remains in quantitative analysis of developers' acceptance of AI-generated code suggestions, partly because the necessary fine-grained interaction data is often proprietary. To bridge this gap, this paper conducts an empirical study using 66,329 industrial developer-AI interactions from a large technology company. We analyze features that are significantly different between accepted code suggestions and rejected ones. We find that accepted suggestions are characterized by significantly higher historical acceptance counts and ratios for both developers and projects, longer generation intervals, shorter preceding code context in the project, and older IDE versions. Based on these findings, we introduce CSAP (Code Suggestion Acceptance Prediction) to predict whether a developer will accept the code suggestion before it is displayed. Our evaluation of CSAP shows that it achieves the accuracy of 0.

Bias in web search has been in the spotlight of bias detection research for quite a while. At the same time, little attention has been paid to query suggestions in this regard. Awareness of the problem of biased query suggestions has been raised. Likewise, there is a rising need for automatic bias detection approaches. This paper adds on the bias detection pipeline for bias detection in query suggestions of person-related search developed by Bonart et al. \cite{Bonart_2019a}. The sparseness and lack of contextual metadata of query suggestions make them a difficult subject for bias detection. Furthermore, query suggestions are perceived very briefly and subliminally. To overcome these issues, perception-aware metrics are introduced. Consequently, the enhanced pipeline is able to better detect systematic topical bias in search engine query suggestions for person-related searches. The results of an analysis performed with the developed pipeline confirm this assumption. Due to the perception-aware bias detection metrics, findings produced by the pipeline can be assumed to reflect bias that users would discern.

Creating high-quality 3D avatars using 3D Gaussian Splatting (3DGS) from a monocular video benefits virtual reality and telecommunication applications. However, existing automatic methods exhibit artifacts under novel poses due to limited information in the input video. We propose AvatarPerfect, a novel system that allows users to iteratively refine 3DGS avatars by manually editing the rendered avatar images. In each iteration, our system suggests a new body and camera pose to help users identify and correct artifacts. The edited images are then used to update the current avatar, and our system suggests the next body and camera pose for further refinement. To investigate the effectiveness of AvatarPerfect, we conducted a user study comparing our method to an existing 3DGS editor SuperSplat, which allows direct manipulation of Gaussians without automatic pose suggestions. The results indicate that our system enables users to obtain higher quality refined 3DGS avatars than the existing 3DGS editor.

Code suggestions have become an integral part of IDEs and developers use code suggestions generated by IDEs all the time. These code suggestions are mostly for calling a method of an object or for using a function of a library and not for possible next line of the code. GPT based models are too slow or resource intensive for real-time code suggestions in local environments. As a solution to this GraphSense was introduced which provide code suggestions with minimum amount of resource usage in real-time.

We explore a method for presenting word suggestions for non-visual text input using simultaneous voices. We conduct two perceptual studies and investigate the impact of different presentations of voices on a user's ability to detect which voice, if any, spoke their desired word. Our sets of words simulated the word suggestions of a predictive keyboard during real-world text input. We find that when voices are simultaneous, user accuracy decreases significantly with each added word suggestion. However, adding a slight 0.15 s delay between the start of each subsequent word allows two simultaneous words to be presented with no significant decrease in accuracy compared to presenting two words sequentially (84% simultaneous versus 86% sequential). This allows two word suggestions to be presented to the user 32% faster than sequential playback without decreasing accuracy.

This document presents a preliminary compilation of general-purpose AI (GPAI) evaluation practices that may promote internal validity, external validity and reproducibility. It includes suggestions for human uplift studies and benchmark evaluations, as well as cross-cutting suggestions that may apply to many different evaluation types. Suggestions are organised across four stages in the evaluation life cycle: design, implementation, execution and documentation. Drawing from established practices in machine learning, statistics, psychology, economics, biology and other fields recognised to have important lessons for AI evaluation, these suggestions seek to contribute to the conversation on the nascent and evolving field of the science of GPAI evaluations. The intended audience of this document includes providers of GPAI models presenting systemic risk (GPAISR), for whom the EU AI Act lays out specific evaluation requirements; third-party evaluators; policymakers assessing the rigour of evaluations; and academic researchers developing or conducting GPAI evaluations.

Diffusion Denoising models demonstrated impressive results across generative Computer Vision tasks, but they still fail to outperform standard autoregressive solutions in the discrete domain, and only match them at best. In this work, we propose a different paradigm by adopting diffusion models to provide suggestions to the autoregressive generation rather than replacing them. By doing so, we combine the bidirectional and refining capabilities of the former with the strong linguistic structure provided by the latter. To showcase its effectiveness, we present Show, Suggest and Tell (SST), which achieves State-of-the-Art results on COCO, among models in a similar setting. In particular, SST achieves 125.1 CIDEr-D on the COCO dataset without Reinforcement Learning, outperforming both autoregressive and diffusion model State-of-the-Art results by 1.5 and 2.5 points. On top of the strong results, we performed extensive experiments to validate the proposal and analyze the impact of the suggestion module. Results demonstrate a positive correlation between suggestion and caption quality, overall indicating a currently underexplored but promising research direction. Code will be available a

Chord diagrams are used by guitar players to show where and how to play a chord on the fretboard. They are useful to beginners learning chords or for sharing the hand positions required to play a song.However, the diagrams presented on guitar learning toolsare usually selected from an existing databaseand rarely represent the actual positions used by performers.In this paper, we propose a tool which suggests a chord diagram for achord label,taking into account the diagram of the previous chord.Based on statistical analysis of the DadaGP and mySongBook datasets, we show that some chord diagrams are over-represented in western popular musicand that some chords can be played in more than 20 different ways.We argue that taking context into account can improve the variety and the quality of chord diagram suggestion, and compare this approach with a model taking only the current chord label into account.We show that adding previous context improves the F1-score on this task by up to 27% and reduces the propensity of the model to suggest standard open chords.We also define the notion of texture in the context of chord diagrams andshow through a variety of metrics that our model improves t

Goal-conditioned policies, such as those learned via imitation learning, provide an easy way for humans to influence what tasks robots accomplish. However, these robot policies are not guaranteed to execute safely or to succeed when faced with out-of-distribution requests. In this work, we enable robots to know when they can confidently execute a user's desired goal, and automatically suggest safe alternatives when they cannot. Our approach is inspired by control-theoretic safety filtering, wherein a safety filter minimally adjusts a robot's candidate action to be safe. Our key idea is to pose alternative suggestion as a safe control problem in goal space, rather than in action space. Offline, we use reachability analysis to compute a goal-parameterized reach-avoid value network which quantifies the safety and liveness of the robot's pre-trained policy. Online, our robot uses the reach-avoid value network as a safety filter, monitoring the human's given goal and actively suggesting alternatives that are similar but meet the safety specification. We demonstrate our Safe ALTernatives (SALT) framework in simulation experiments with indoor navigation and Franka Panda tabletop manipulat

With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massive corpora of code mined from unvetted public sources. As a result, these models are susceptible to data poisoning attacks where an adversary manipulates the model's training by injecting malicious data. Poisoning attacks could be designed to influence the model's suggestions at run time for chosen contexts, such as inducing the model into suggesting insecure code payloads. To achieve this, prior attacks explicitly inject the insecure code payload into the training data, making the poison data detectable by static analysis tools that can remove such malicious data from the training set. In this work, we demonstrate two novel attacks, COVERT and TROJANPUZZLE, that can bypass static analysis by planting malicious poison data in out-of-context regions such as docstrings. Our most novel attack, TROJANPUZZLE, goes one step further in generating less suspicious poison data by never explicitly including certain (suspicious) parts of the payload in the poison data, while still inducing a model that suggests the en

Before implementing a function, programmers are encouraged to write a purpose statement i.e., a short, natural-language explanation of what the function computes. A purpose statement may be ambiguous i.e., it may fail to specify the intended behaviour when two or more inequivalent computations are plausible on certain inputs. Our paper makes four contributions. First, we propose a novel heuristic that suggests such inputs using Large Language Models (LLMs). Using these suggestions, the programmer may choose to clarify the purpose statement (e.g., by providing a functional example that specifies the intended behaviour on such an input). Second, to assess the quality of inputs suggested by our heuristic, and to facilitate future research, we create an open dataset of purpose statements with known ambiguities. Third, we compare our heuristic against GitHub Copilot's Chat feature, which can suggest similar inputs when prompted to generate unit tests. Fourth, we provide an open-source implementation of our heuristic as an extension to Visual Studio Code for the Python programming language, where purpose statements and functional examples are specified as docstrings and doctests respecti

Enhancing word usage is a desired feature for writing assistance. To further advance research in this area, this paper introduces "Smart Word Suggestions" (SWS) task and benchmark. Unlike other works, SWS emphasizes end-to-end evaluation and presents a more realistic writing assistance scenario. This task involves identifying words or phrases that require improvement and providing substitution suggestions. The benchmark includes human-labeled data for testing, a large distantly supervised dataset for training, and the framework for evaluation. The test data includes 1,000 sentences written by English learners, accompanied by over 16,000 substitution suggestions annotated by 10 native speakers. The training dataset comprises over 3.7 million sentences and 12.7 million suggestions generated through rules. Our experiments with seven baselines demonstrate that SWS is a challenging task. Based on experimental analysis, we suggest potential directions for future research on SWS. The dataset and related codes is available at https://github.com/microsoft/SmartWordSuggestions.