Non-factoid question-answering (NFQA) poses a significant challenge due to its open-ended nature, diverse intents, and the need for multi-aspect reasoning, which renders conventional factoid QA approaches, including retrieval-augmented generation (RAG), inadequate. Unlike factoid questions, non-factoid questions (NFQs) lack definitive answers and require synthesizing information from multiple sources across various reasoning dimensions. To address these limitations, we introduce Typed-RAG, a type-aware multi-aspect decomposition framework within the RAG paradigm for NFQA. Typed-RAG classifies NFQs into distinct types -- such as debate, experience, and comparison -- and applies aspect-based decomposition to refine retrieval and generation strategies. By decomposing multi-aspect NFQs into single-aspect sub-queries and aggregating the results, Typed-RAG generates more informative and contextually relevant responses. To evaluate Typed-RAG, we introduce Wiki-NFQA, a benchmark dataset covering diverse NFQ types. Experimental results demonstrate that Typed-RAG outperforms baselines, thereby highlighting the importance of type-aware decomposition for effective retrieval and generation in NFQA. Our code and dataset are available at https://github.com/TeamNLP/Typed-RAG.
Motivation: With the development of third-generation sequencing technologies, people are able to obtain DNA sequences with lengths from 10s to 100s of kb. These long reads allow protein domain annotation without assembly, thus can produce important insights into the biological functions of the underlying data. However, the high error rate in third-generation sequencing data raises a new challenge to established domain analysis pipelines. The state-of-the-art methods are not optimized for noisy reads and have shown unsatisfactory accuracy of domain classification in third-generation sequencing data. New computational methods are still needed to improve the performance of domain prediction in long noisy reads. Results: In this work, we introduce ProDOMA, a deep learning model that conducts domain classification for third-generation sequencing reads. It uses deep neural networks with 3-frame translation encoding to learn conserved features from partially correct translations. In addition, we formulate our problem as an open-set problem and thus our model can reject unrelated DNA reads such as those from noncoding regions. In the experiments on simulated reads of protein coding sequences and real reads from the human genome, our model outperforms HMMER and DeepFam on protein domain classification. In summary, ProDOMA is a useful end-to-end protein domain analysis tool for long noisy reads without relying on error correction. Availability: The source code and the trained model are freely available at https://github.com/strideradu/ProDOMA. Contact: [email omitted]
We present "SemCity," a 3D diffusion model for semantic scene generation in real-world outdoor environments. Most 3D diffusion models focus on generating a single object, synthetic indoor scenes, or synthetic outdoor scenes, while the generation of real-world outdoor scenes is rarely addressed. In this paper, we concentrate on generating a real-outdoor scene through learning a diffusion model on a real-world outdoor dataset. In contrast to synthetic data, real-outdoor datasets often contain more empty spaces due to sensor limitations, causing challenges in learning real-outdoor distributions. To address this issue, we exploit a triplane representation as a proxy form of scene distributions to be learned by our diffusion model. Furthermore, we propose a triplane manipulation that integrates seamlessly with our triplane diffusion model. The manipulation improves our diffusion model's applicability in a variety of downstream tasks related to outdoor scene generation such as scene inpainting, scene outpainting, and semantic scene completion refinements. In experimental results, we demonstrate that our triplane diffusion model shows meaningful generation results compared with existing work in a real-outdoor dataset, SemanticKITTI. We also show our triplane manipulation facilitates seamlessly adding, removing, or modifying objects within a scene. Further, it also enables the expansion of scenes toward a city-level scale. Finally, we evaluate our method on semantic scene completion refinements where our diffusion model enhances predictions of semantic scene completion networks by learning scene distribution. Our code is available at https://github.com/zoomin-lee/SemCity.
Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback enable coherent, controllable multi-shot videos. In parallel, video world models provide action-conditioned observations and predicted futures, serving as interactive environments for agents. We study their intersection through the agent harness: an executable runtime that constructs context, exposes tools, maintains state, routes feedback, and manages budgets around video models. This report examines three directions. First, agentic video generation, where harnesses coordinate scripting, shot planning, asset management, production, and editing, alongside the evaluation challenges of these systems. Second, agentic world modeling, where harnesses mediate observation, control, execution, and state. We discuss hybrid designs in which game engines or agent-written programs maintain world state while video models render observations, and how agents and world models can mutually evaluate and improve one another. Third, recursive self-improvement (RSI) in video model development, distinguishing output revisions, updates to harness state, generator parameters, and evaluators, and changes to the improvement procedure itself. We identify how these improvements feed back into subsequent development. Across these directions, we analyze essential agent capabilities, including audiovisual perception, long-horizon planning, memory, code-based interaction, feedback-guided control, skill reuse, and multi-agent coordination. We conclude with challenges in autonomous video production, lifelong memory, programmable hybrid control, autonomous model development, provenance, cost accounting, and evaluation linking video quality and task performance to sustained improvements in models and harnesses.
There has been significant progress in the music generation technique utilizing deep learning. However, it is still hard for musicians and artists to use these techniques in their daily music-making practice. This paper proposes a Variational Autoencoder\cite{Kingma2014}(VAE)-based rhythm generation system, in which musicians can train a deep learning model only by selecting target MIDI files, then generate various rhythms with the model. The author has implemented the system as a plugin software for a DAW (Digital Audio Workstation), namely a Max for Live device for Ableton Live. Selected professional/semi-professional musicians and music producers have used the plugin, and they proved that the plugin is a useful tool for making music creatively. The plugin, source code, and demo videos are available online.
Recent advances in foundation models have enabled audio-generative models that produce high-fidelity sounds associated with music, events, and human actions. Despite the success achieved in modern audio-generative models, the conventional approach to assessing the quality of the audio generation relies heavily on distance metrics like Frechet Audio Distance. In contrast, we aim to evaluate the quality of audio generation by examining the effectiveness of using them as training data. Specifically, we conduct studies to explore the use of synthetic audio for audio recognition. Moreover, we investigate whether synthetic audio can serve as a resource for data augmentation in speech-related modeling. Our comprehensive experiments demonstrate the potential of using synthetic audio for audio recognition and speech-related modeling. Our code is available at https://github.com/usc-sail/SynthAudio.
Diverse and realistic floor plan data are essential for the development of useful computer-aided methods in architectural design. Today's large-scale floor plan datasets predominantly feature simple floor plan layouts, typically representing single-apartment dwellings only. To compensate for the mismatch between current datasets and the real world, we develop \textbf{Modified Swiss Dwellings} (MSD) -- the first large-scale floor plan dataset that contains a significant share of layouts of multi-apartment dwellings. MSD features over 5.3K floor plans of medium- to large-scale building complexes, covering over 18.9K distinct apartments. We validate that existing approaches for floor plan generation, while effective in simpler scenarios, cannot yet seamlessly address the challenges posed by MSD. Our benchmark calls for new research in floor plan machine understanding. Code and data are open.
Diffusion models have demonstrated excellent capabilities in text-to-image generation. Their semantic understanding (i.e., prompt following) ability has also been greatly improved with large language models (e.g., T5, Llama). However, existing models cannot perfectly handle long and complex text prompts, especially when the text prompts contain various objects with numerous attributes and interrelated spatial relationships. While many regional prompting methods have been proposed for UNet-based models (SD1.5, SDXL), but there are still no implementations based on the recent Diffusion Transformer (DiT) architecture, such as SD3 and FLUX.1.In this report, we propose and implement regional prompting for FLUX.1 based on attention manipulation, which enables DiT with fined-grained compositional text-to-image generation capability in a training-free manner. Code is available at https://github.com/antonioo-c/Regional-Prompting-FLUX.
Security misconfigurations in Container Orchestrators (COs) can pose serious threats to software systems. While Static Analysis Tools (SATs) can effectively detect these security vulnerabilities, the industry currently lacks automated solutions capable of fixing these misconfigurations. The emergence of Large Language Models (LLMs), with their proven capabilities in code understanding and generation, presents an opportunity to address this limitation. This study introduces LLMSecConfig, an innovative framework that bridges this gap by combining SATs with LLMs. Our approach leverages advanced prompting techniques and Retrieval-Augmented Generation (RAG) to automatically repair security misconfigurations while preserving operational functionality. Evaluation of 1,000 real-world Kubernetes configurations achieved a 94\% success rate while maintaining a low rate of introducing new misconfigurations. Our work makes a promising step towards automated container security management, reducing the manual effort required for configuration maintenance.
Vision AutoRegressive model (VAR) was recently introduced as an alternative to Diffusion Models (DMs) in image generation domain. In this work we focus on its adaptations, which aim to fine-tune pre-trained models to perform specific downstream tasks, like medical data generation. While for DMs there exist many techniques, adaptations for VAR remain underexplored. Similarly, differentially private (DP) adaptations-ones that aim to preserve privacy of the adaptation data-have been extensively studied for DMs, while VAR lacks such solutions. In our work, we implement and benchmark many strategies for VAR, and compare them to state-of-the-art DM adaptation strategies. We observe that VAR outperforms DMs for non-DP adaptations, however, the performance of DP suffers, which necessitates further research in private adaptations for VAR. Code is available at https://github.com/sprintml/finetuning_var_dp.
We propose GANCoder, an automatic programming approach based on Generative Adversarial Networks (GAN), which can generate the same functional and logical programming language codes conditioned on the given natural language utterances. The adversarial training between generator and discriminator helps generator learn distribution of dataset and improve code generation quality. Our experimental results show that GANCoder can achieve comparable accuracy with the state-of-the-art methods and is more stable when programming languages.
Frequent modifications of unit test cases are inevitable due to software's continuous underlying changes in source code, design, and requirements. Since manually maintaining software test suites is tedious, timely, and costly, automating the process of generation and maintenance of test units will significantly impact the effectiveness and efficiency of software testing processes. To this end, we propose an automated approach which exploits both structural and semantic properties of source code methods and test cases to recommend the most relevant and useful unit tests to the developers. The proposed approach initially trains a neural network to transform method-level source code, as well as unit tests, into distributed representations (embedded vectors) while preserving the importance of the structure in the code. Retrieving the semantic and structural properties of a given method, the approach computes cosine similarity between the method's embedding and the previously-embedded training instances. Further, according to the similarity scores between the embedding vectors, the model identifies the closest methods of embedding and the associated unit tests as the most similar recommendations. The results on the Methods2Test dataset showed that, while there is no guarantee to have similar relevant test cases for the group of similar methods, the proposed approach extracts the most similar existing test cases for a given method in the dataset, and evaluations show that recommended test cases decrease the developers' effort to generating expected test cases.
In recommendation systems, the choice of loss function is critical since a good loss may significantly improve the model performance. However, manually designing a good loss is a big challenge due to the complexity of the problem. A large fraction of previous work focuses on handcrafted loss functions, which needs significant expertise and human effort. In this paper, inspired by the recent development of automated machine learning, we propose an automatic loss function generation framework, AutoLossGen, which is able to generate loss functions directly constructed from basic mathematical operators without prior knowledge on loss structure. More specifically, we develop a controller model driven by reinforcement learning to generate loss functions, and develop iterative and alternating optimization schedule to update the parameters of both the controller model and the recommender model. One challenge for automatic loss generation in recommender systems is the extreme sparsity of recommendation datasets, which leads to the sparse reward problem for loss generation and search. To solve the problem, we further develop a reward filtering mechanism for efficient and effective loss generation. Experimental results show that our framework manages to create tailored loss functions for different recommendation models and datasets, and the generated loss gives better recommendation performance than commonly used baseline losses. Besides, most of the generated losses are transferable, i.e., the loss generated based on one model and dataset also works well for another model or dataset. Source code of the work is available at https://github.com/rutgerswiselab/AutoLossGen.
One challenge in text-to-image (T2I) generation is the inadvertent reflection of culture gaps present in the training data, which signifies the disparity in generated image quality when the cultural elements of the input text are rarely collected in the training set. Although various T2I models have shown impressive but arbitrary examples, there is no benchmark to systematically evaluate a T2I model's ability to generate cross-cultural images. To bridge the gap, we propose a Challenging Cross-Cultural (C3) benchmark with comprehensive evaluation criteria, which can assess how well-suited a model is to a target culture. By analyzing the flawed images generated by the Stable Diffusion model on the C3 benchmark, we find that the model often fails to generate certain cultural objects. Accordingly, we propose a novel multi-modal metric that considers object-text alignment to filter the fine-tuning data in the target culture, which is used to fine-tune a T2I model to improve cross-cultural generation. Experimental results show that our multi-modal metric provides stronger data selection performance on the C3 benchmark than existing metrics, in which the object-text alignment is crucial. We release the benchmark, data, code, and generated images to facilitate future research on culturally diverse T2I generation (https://github.com/longyuewangdcu/C3-Bench).
Guidance in conditional diffusion generation is of great importance for sample quality and controllability. However, existing guidance schemes are to be desired. On one hand, mainstream methods such as classifier guidance and classifier-free guidance both require extra training with labeled data, which is time-consuming and unable to adapt to new conditions. On the other hand, training-free methods such as universal guidance, though more flexible, have yet to demonstrate comparable performance. In this work, through a comprehensive investigation into the design space, we show that it is possible to achieve significant performance improvements over existing guidance schemes by leveraging off-the-shelf classifiers in a training-free fashion, enjoying the best of both worlds. Employing calibration as a general guideline, we propose several pre-conditioning techniques to better exploit pretrained off-the-shelf classifiers for guiding diffusion generation. Extensive experiments on ImageNet validate our proposed method, showing that state-of-the-art diffusion models (DDPM, EDM, DiT) can be further improved (up to 20%) using off-the-shelf classifiers with barely any extra computational cost. With the proliferation of publicly available pretrained classifiers, our proposed approach has great potential and can be readily scaled up to text-to-image generation tasks. The code is available at https://github.com/AlexMaOLS/EluCD/tree/main.
The frequent occurrence of cyber-attacks has made webshell attacks and defense gradually become a research hotspot in the field of network security. However, the lack of publicly available benchmark datasets and the over-reliance on manually defined rules for webshell escape sample generation have slowed down the progress of research related to webshell escape sample generation and artificial intelligence (AI)-based webshell detection. To address the drawbacks of weak webshell sample escape capabilities, the lack of webshell datasets with complex malicious features, and to promote the development of webshell detection, we propose the Hybrid Prompt algorithm for webshell escape sample generation with the help of large language models. As a prompt algorithm specifically developed for webshell sample generation, the Hybrid Prompt algorithm not only combines various prompt ideas including Chain of Thought, Tree of Thought, but also incorporates various components such as webshell hierarchical module and few-shot example to facilitate the LLM in learning and reasoning webshell escape strategies. Experimental results show that the Hybrid Prompt algorithm can work with multiple LLMs with excellent code reasoning ability to generate high-quality webshell samples with high Escape Rate (88.61% with GPT-4 model on VirusTotal detection engine) and (Survival Rate 54.98% with GPT-4 model).
Image generation technology has brought significant advancements across various fields but has also raised concerns about data misuse and potential rights infringements, particularly with respect to creating visual artworks. Current methods aimed at safeguarding artworks often employ adversarial attacks. However, these methods face challenges such as poor transferability, high computational costs, and the introduction of noticeable noise, which compromises the aesthetic quality of the original artwork. To address these limitations, we propose a Structurally Imperceptible and Transferable Adversarial (SITA) attacks. SITA leverages a CLIP-based destylization loss, which decouples and disrupts the robust style representation of the image. This disruption hinders style extraction during stylized image generation, thereby impairing the overall stylization process. Importantly, SITA eliminates the need for a surrogate diffusion model, leading to significantly reduced computational overhead. The method's robust style feature disruption ensures high transferability across diverse models. Moreover, SITA introduces perturbations by embedding noise within the imperceptible structural details of the image. This approach effectively protects against style extraction without compromising the visual quality of the artwork. Extensive experiments demonstrate that SITA offers superior protection for artworks against unauthorized use in stylized generation. It significantly outperforms existing methods in terms of transferability, computational efficiency, and noise imperceptibility. Code is available at https://github.com/A-raniy-day/SITA.
Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, because most visual tokenizers map local image patches into latent tokens, global information is limited. To address this, we introduce \textit{Hita}, a novel image tokenizer for autoregressive (AR) image generation. It introduces a holistic-to-local tokenization scheme with learnable holistic queries and local patch tokens. Hita incorporates two key strategies to better align with the AR generation process: 1) {arranging} a sequential structure with holistic tokens at the beginning, followed by patch-level tokens, and using causal attention to maintain awareness of previous tokens; and 2) adopting a lightweight fusion module before feeding the de-quantized tokens into the decoder to control information flow and prioritize holistic tokens. Extensive experiments show that Hita accelerates the training speed of AR generators and outperforms those trained with vanilla tokenizers, achieving \textbf{2.59 FID} and \textbf{281.9 IS} on the ImageNet benchmark. Detailed analysis of the holistic representation highlights its ability to capture global image properties, such as textures, materials, and shapes. Additionally, Hita also demonstrates effectiveness in zero-shot style transfer and image in-painting. The code is available at \href{https://github.com/CVMI-Lab/Hita}{https://github.com/CVMI-Lab/Hita}.
We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code. BenchPress synthesizes compiling functions by adding new code in any part of an empty or existing sequence by jointly observing its left and right context, achieving excellent compilation rate. BenchPress steers benchmark generation towards desired target features that has been impossible for state of the art synthesizers (or indeed humans) to reach. It performs better in targeting the features of Rodinia benchmarks in 3 different feature spaces compared with (a) CLgen - a state of the art ML synthesizer, (b) CLSmith fuzzer, (c) SRCIROR mutator or even (d) human-written code from GitHub. BenchPress is the first generator to search the feature space with active learning in order to generate benchmarks that will improve a downstream task. We show how using BenchPress, Grewe's et al. CPU vs GPU heuristic model can obtain a higher speedup when trained on BenchPress's benchmarks compared to other techniques. BenchPress is a powerful code generator: Its generated samples compile at a rate of 86%, compared to CLgen's 2.33%. Starting from an empty fixed input, BenchPress produces 10x more unique, compiling OpenCL benchmarks than CLgen, which are significantly larger and more feature diverse.
Generative Adversarial Networks (GANs) have made great success in synthesizing high-quality images. However, how to steer the generation process of a well-trained GAN model and customize the output image is much less explored. It has been recently found that modulating the input latent code used in GANs can reasonably alter some variation factors in the output image, but such manipulation usually presents to change the entire image as a whole. In this work, we propose an effective approach, termed as LoGAN, to support local editing of the output image. Concretely, we introduce two operators, i.e., content modulation and style modulation, together with a priority mask to facilitate the precise control of the intermediate generative features. Taking bedroom synthesis as an instance, we are able to seamlessly remove, insert, shift, and rotate the individual objects inside a room. Furthermore, our method can completely clear out a room and then refurnish it with customized furniture and styles. Experimental results show the great potentials of steering the image generation of pre-trained GANs for versatile image editing.